{"products":[{"id":"Ckpcgeti3yb1fbmIPzrg","title":"Vault Backup","slug":"vault-backup","description":"Universal secure backup — encrypt (AES-256), compress (zstd), deduplicate, verify integrity. Backup project files, databases, .claude/ setup, configs. Incremental, secrets-aware, multi-destination.","readme":"# Vault Backup\n\n\n> Universal secure backup — encrypt, compress, deduplicate, verify.\n\n\n## The Problem\n\nYou have projects, databases, configs, Claude Code setups scattered across your machine. One disk failure, one accidental `rm -rf`, one ransomware attack — and it's gone. Generic backup tools don't understand your development workflow. They backup everything (including node_modules and .git) or nothing useful.\n\n**Vault Backup** is a Claude Code skill that understands what matters: your code, your configs, your databases, your `.claude/` setup. It excludes what doesn't (node_modules, build artifacts) and protects what's sensitive (encrypts by default, never backs up raw secrets).\n\n## Install\n\n```bash\nmyclaude install vault-backup\n```\n\n## Is this for me?\n\n**Yes if:**\n- You want automated, encrypted backups from Claude Code\n- You need to backup databases (Supabase, Postgres, MySQL)\n- You want incremental backups that save space\n- You need integrity verification for your backups\n\n**No if:**\n- You need enterprise backup with SLA (use Veeam, Commvault)\n- You need real-time replication (use database native tools)\n\n## Quick Start\n\n```\n/vault-backup quick # snapshot critical files\n/vault-backup full --encrypt # complete backup with AES-256\n/vault-backup restore ./backups/latest # restore from backup\n/vault-backup verify ./backups/latest # check integrity\n```\n\n## Features\n\n### Security First\n- **AES-256-GCM encryption** via `age` — enabled by default, not optional\n- **Secrets-aware** — automatically excludes .env, .p12, credentials, tokens\n- **Integrity verification** — SHA-256 hash per archive + per-file hashes in manifest\n- **Key safety** — passphrase never stored in the backup itself\n\n### Space Optimization\n- **zstd compression** — 60-75% reduction on typical projects\n- **Incremental backups** — only changed files since last backup\n- **Smart exclusion** — skips node_modules, .git objects, build artifacts, cache\n- **Retention policy** — auto-cleanup old backups (default: keep last 5)\n\n### Multi-Target\n- **Project files** — source code, configs, docs\n- **Claude Code setup** — .claude/ rules, skills, commands, memories\n- **Databases** — Supabase, Postgres (pg_dump), MySQL, SQLite\n- **System configs** — .gitconfig, .ssh/config, .env.example\n\n### Multi-Destination\n- **Local** — project directory or external drive\n- **Cloud** — S3, Backblaze B2, Google Drive (via rclone)\n- **Git** — dedicated backup branch (for small projects)\n\n### Developer-Friendly\n- **4 modes** — quick, full, restore, verify\n- **One command** — discovers, excludes, compresses, encrypts, verifies\n- **Cross-platform** — macOS, Linux, Windows (WSL)\n- **Manifest** — JSON manifest with every file, hash, and metadata\n\n## How It Works\n\n```\n/vault-backup quick\n```\n\n1. **Discover** — scans target path, builds file inventory\n2. **Exclude** — removes secrets, build artifacts, large binaries\n3. **Compress** — zstd compression (level 3 quick, level 9 full)\n4. **Encrypt** — AES-256-GCM via age (default on)\n5. **Verify** — SHA-256 integrity check\n6. **Report** — summary with file count, size, ratio, hash\n7. **Cleanup** — remove old backups beyond retention limit\n\nEach step is logged and any failure is reported immediately — no silent data loss.\n\n## Requirements\n\n- Claude Code CLI\n- `tar` and `zstd` (pre-installed on macOS/Linux, available via WSL on Windows)\n- `age` for encryption (optional, recommended)\n- `rclone` for cloud destinations (optional)\n\n## Compatibility\n\n- macOS, Linux, Windows (WSL)\n- Claude Code v1.0+\n\n## Language\n\nEN | PT-BR | ES — auto-detects from your conversation language.\n\n## License\n\nProprietary — © 2026 CognittusAI\n\n---\n\n*Built with [MyClaude Studio Engine](https://myclaude.sh)*\n\n---\n\n[](https://myclaude.sh/quality)\n[](https://myclaude.sh/p/vault-backup)\n\nBuilt with MyClaude Studio Engine\n","category":"skills","authorUsername":"cognittusai","authorDisplayName":"Ênio","authorAvatar":"","fileName":"vault-backup-1.0.0.zip","status":"published","version":"1.0.0","source":"cli","mcsLevel":1,"language":"en","longDescription":"","installTarget":".claude/skills/vault-backup/","compatibility":{"claudeCode":">=1.0.0"},"dependencies":{"myclaude":[]},"githubTopics":[],"npmPublish":false,"tags":["backup","security","encryption","compression","devops","disaster-recovery"],"createdAt":"2026-04-19T01:55:12.307Z","license":"MIT","fileSize":12281,"publishedAt":"2026-04-19T02:13:08.654Z","price":0,"updatedAt":"2026-04-19T02:13:08.654Z","syncState":{"github":{"repoUrl":"https://github.com/myclaude-sh/vault-backup","retryCount":0,"lastSyncAt":"2026-04-19T02:18:53.335Z","commitSha":"b1236fa6705f6e69d55894b614b30b4529ac3838","status":"synced"},"marketplace":{"retryCount":0,"lastSyncAt":"2026-04-19T02:18:53.335Z","status":"synced"},"npm":{"retryCount":1,"lastSyncAt":"2026-04-19T02:18:53.335Z","error":"NPM_AUTOMATION_TOKEN not configured","status":"failed"}},"stats":{"likes":0,"rating":0,"reviewsCount":0,"purchaseCount":0,"downloads":3},"trendingUpdatedAt":"2026-04-29T00:14:26.117Z","trendingScore":1.51,"thumbnailUrl":"/icons/skills.png"},{"id":"kA1ccJoena6ubwSDwzAo","title":"BVS Lite","slug":"bvs-lite","description":"Free edition of Build-Verify-Seal. 6 mandatory architecture questions + basic XP Scorecard. Prevents coding without clarity. Upgrade to full BVS for module contracts, build order, seal criteria, and drift prevention.","readme":"# BVS Lite — Architecture-First Engineering\n\n**Free edition of Build-Verify-Seal.**\n\nStop coding before you have clarity. BVS Lite enforces 6 mandatory questions before any code is written, plus a basic quality scorecard to keep your project honest.\n\n## What You Get (Free)\n\n**6 Questions Before Coding** — Claude will refuse to write code until these are answered:\n\n1. What is the problem?\n2. Who uses it?\n3. What data goes in and out?\n4. Where will it run?\n5. What can go wrong?\n6. How to safeguard it?\n\n**Basic XP Scorecard** — 5 pillars checked at each milestone: Docs, Tests, CI, Protection, Commits. Minimum 3/5 to proceed, 5/5 before release.\n\n**Auto-generated documents** — ARCHITECTURE.md, CLAUDE.md, and .gitignore created from your answers.\n\n## Who Is This For\n\n- Developers using Claude Code for projects with 2+ files\n- Teams that want structure without overhead\n- Anyone who has lost time to unclear requirements\n\n## Want the Full Framework?\n\n**Build-Verify-Seal** ($19.90) adds module contracts, bottom-up build order, objective seal criteria, drift prevention, session discipline, and orchestrator patterns.\n\nPerfect for complex projects with 3+ modules or multiple API integrations.\n\nUpgrade: https://myclaude.sh/p/build-verify-seal\n\n---\n\n*By @cognittusai — Built from real-world experience shipping AI-assisted projects.*\n","license":"MIT","category":"skills","price":0,"authorUsername":"cognittusai","authorDisplayName":"Ênio","authorAvatar":"","fileName":"bvs-lite-1.0.0.zip","fileSize":2297,"status":"published","version":"1.0.0","source":"cli","mcsLevel":1,"language":"en","longDescription":"","installTarget":".claude/skills/bvs-lite/","compatibility":{"claudeCode":">=1.0.0"},"dependencies":{"myclaude":[]},"githubTopics":[],"npmPublish":false,"tags":["engineering","methodology","architecture","quality","verification","free"],"createdAt":"2026-04-16T16:26:26.081Z","publishedAt":"2026-04-16T16:26:26.081Z","updatedAt":"2026-04-16T16:26:26.081Z","stats":{"rating":0,"reviewsCount":0,"purchaseCount":0,"likes":2,"downloads":3},"trendingUpdatedAt":"2026-04-28T00:14:28.936Z","trendingScore":1.21,"thumbnailUrl":"/icons/skills.png"},{"id":"YuJQYG1QsGUBOpZR6jgQ","title":"Build-Verify-Seal","slug":"build-verify-seal","description":"Anti-hallucination engineering framework for Claude Code. 3-phase pipeline: Architecture (6 Questions) > Engineering (Build-Verify-Seal) > Verification (XP Scorecard). Enforces contracts, bottom-up build order, seal criteria, and drift prevention.","category":"skills","authorUsername":"cognittusai","authorDisplayName":"Ênio","authorAvatar":"","fileName":"build-verify-seal-1.0.0.zip","status":"published","version":"1.0.0","source":"cli","mcsLevel":1,"language":"en","longDescription":"","installTarget":".claude/skills/build-verify-seal/","compatibility":{"claudeCode":">=1.0.0"},"dependencies":{"myclaude":[]},"githubTopics":[],"npmPublish":false,"tags":["engineering","anti-hallucination","methodology","architecture","quality","build-system","contracts","verification","scorecard"],"createdAt":"2026-04-16T13:39:01.007Z","syncState":{"github":{"repoUrl":"https://github.com/myclaude-sh/build-verify-seal","retryCount":0,"lastSyncAt":"2026-04-16T13:39:49.312Z","commitSha":"439b34fda9049af629e759ab8d30f6211a232fb3","status":"synced"},"marketplace":{"retryCount":0,"lastSyncAt":"2026-04-16T13:39:49.312Z","status":"synced"},"npm":{"retryCount":1,"lastSyncAt":"2026-04-16T13:39:49.312Z","error":"NPM_AUTOMATION_TOKEN not configured","status":"failed"}},"license":"Proprietary","price":19.9,"readme":"# Build-Verify-Seal\n\n**Engineering framework that prevents AI drift in complex projects.**\n\nIf you've ever lost time because Claude invented an API that doesn't exist, rewrote a module that was already done, or forgot what it built two sessions ago — this fixes that.\n\n## The Problem\n\nAI assistants hallucinate. They invent flags, forget contracts, skip layers, and drift from what was agreed. The longer the session, the worse it gets. On complex projects with 3+ modules, this becomes a real engineering risk.\n\n## The Solution: 3-Phase Pipeline\n\n### Phase 1: Architecture — 6 Questions Before Coding\n\nNo code until these are answered:\n\n1. What is the problem?\n2. Who uses it?\n3. What data goes in and out?\n4. Where will it run?\n5. What can go wrong?\n6. How to safeguard it?\n\nOutput: ARCHITECTURE.md with contracts for every module.\n\n### Phase 2: Engineering — Build-Verify-Seal\n\n- **Module Contracts** — Every module defines Input, Output, success criteria, and idempotency\n- **Bottom-up Build Order** — Utils first, then base modules, then composites, then orchestrator. Never skip a layer\n- **1 Module Per Session** — Focus prevents drift\n- **Objective Seal Criteria** — A module is SEALED only when: reproducible test passes, user approves, output matches contract\n- **Drift Prevention** — If code diverged from contract, update docs in the same session. Never \"fix later\"\n\n### Phase 3: Verification — XP Scorecard\n\n5 pillars checked at every milestone:\n\n| Pillar | What it verifies |\n|--------|-----------------|\n| Docs | Architecture and project docs reflect current code |\n| Tests | Every sealed module has a reproducible test |\n| CI | Automated verification on push (or documented smoke test) |\n| Protection | Config files in .gitignore, sensitive data out of code |\n| Commits | Conventional format, atomic, 1 commit per module |\n\nMinimum 3/5 per layer. 5/5 before release.\n\n## When to Use\n\n- Projects with 3+ modules\n- 2+ external API integrations\n- Media/content pipelines\n- Any project where AI drift has cost you time\n\n## How to Use\n\nAfter installing, invoke the skill in Claude Code. It will guide you through all 3 phases, enforce contracts, and prevent drift automatically.\n\n---\n\n*By @cognittusai — Built from real-world experience shipping AI-assisted projects.*\n","fileSize":4851,"publishedAt":"2026-04-16T16:56:16.611Z","updatedAt":"2026-04-16T16:56:16.611Z","stats":{"downloads":0,"rating":0,"reviewsCount":0,"purchaseCount":0,"likes":2},"trendingUpdatedAt":"2026-04-29T00:14:26.117Z","trendingScore":2.91,"thumbnailUrl":"/icons/skills.png"},{"id":"ggqLzYFFb72xiPQSPCtL","title":"visual-mind","slug":"visual-mind","description":"Intelligent infographic generation skill. Classifies information topology, profiles audience trust, validates cognitive load, then generates SVG and tested image prompts. 20 layouts, 17 styles, CHI 2025 research.","readme":"# visual-mind — Intelligent Infographic Generation\n\n> Claude, but for infographics. Reasons about your content's structure, your audience's trust signals, and cognitive load limits — then generates a ready-to-use SVG and a tested image prompt. Every time.\n\n[](https://myclaude.sh) [](https://myclaude.sh) [](https://myclaude.sh) [](https://myclaude.sh)\n\n---\n\n## Why this exists\n\nAsk vanilla Claude to make an infographic and you get the same answer every time: a layout name, a colour suggestion, and a prompt so generic it could apply to anything. The output looks like it was designed by committee for nobody in particular.\n\nThe problem isn't Claude's writing ability. It's that **infographic design requires reasoning that Claude doesn't do by default:**\n\n- What is the *structural shape* of this content — is it a process, a hierarchy, a comparison, a cycle?\n- What visual signals build *credibility* with this specific audience — and which ones destroy it?\n- Can this layout actually *hold* this much information, or will it collapse cognitively?\n- What *exact prompt formula* does this layout need to produce a usable result?\n\n**visual-mind does all four before touching a single design decision.**\n\n---\n\n## The difference — same request, completely different result\n\n**Without visual-mind** — vanilla Claude on a transformer attention paper:\n> *\"Here's a hub-spoke infographic prompt: Create a colourful hub-spoke diagram with the main topic in the centre and subtopics as spokes. Use bright colours and clean fonts. Aspect ratio 16:9.\"*\n\nGeneric layout choice. No audience calibration. No cognitive load check. That prompt produces output that looks busy, feels random, and wouldn't survive peer review.\n\n**With visual-mind** — same paper, after topology → audience → cognitive reasoning:\n> *\"The transformer attention content is Concept topology with a Radial VIF pattern — it defines a central abstraction (attention) with 8 parallel components radiating outward, which maps exactly to hub-spoke geometry. For ML researchers, I'm recommending hub-spoke × technical-schematic: the schematic aesthetic signals mathematical rigour that expert audiences require (CHI 2025: clarity = 83.8% primary trust factor for technical readers). At 5 primary units, we're well within the 8-spoke cognitive ceiling (PASS). Prompt: 'Central hub (circle) representing Scaled Dot-Product Attention. 8 spokes at equal angles. Each node: icon + label. Blueprint-grid background #1E3A5F, primary blue #2563EB, Helvetica Neue, technical line-art aesthetic, 16:9. --style raw --v 6'\"*\n\nOne of these is a guess. The other is a reasoned argument you can interrogate.\n\n---\n\n## See it reason — 3 real scenarios\n\n### Scenario 1 — The research paper\n**Input:** Section from \"Attention Is All You Need\" (transformer architecture)\n**Audience:** ML researchers and practitioners\n\n*visual-mind reasons:*\n> \"Concept topology (defines what attention IS, not how to DO it) + Radial VIF pattern (8 heads radiating from one mechanism). Expert audience needs mathematical precision — technical-schematic style, not decorative. 5 primary units, ceiling is 8. PASS. Layout: hub-spoke. Style: technical-schematic.\"\n\n**Output:** A hub-spoke SVG with the attention formula at the hub, Q/K/V/Multi-Head/Output as nodes — plus a Midjourney-ready prompt that actually produces a schematic, not clip art.\n\n---\n\n### Scenario 2 — The startup pitch deck section\n**Input:** 22-item company overview (team, product, traction, market, financials, roadmap...)\n**Audience:** Investors\n\n*visual-mind reasons:*\n> \"22 primary units. Maximum ceiling for any layout: 9. This is 2.4× the cognitive limit — a single infographic would be cognitively catastrophic. SPLIT verdict. Recommended: 3 companion visuals — bento-grid (company snapshot, 6 units) + dashboard (traction metrics: $3.1M ARR, 280% YoY, 120 customers, 3 units) + structural-breakdown (product architecture, 3 modules). Each passes cognitive assessment independently.\"\n\n**Output:** An editorial plan for 3 coordinated visuals, each with its own SVG and prompt — instead of one unreadable wall of information.\n\n---\n\n### Scenario 3 — The dangerous style choice\n**Input:** Series B board presentation — €47.3M raise, Revenue €12.8M, ARR €15.2M, burn €890K/month\n**Request:** `--style cyberpunk-neon`\n\n*visual-mind reasons:*\n> \"CONFLICT DETECTED before output. cyberpunk-neon = dark background + neon colours. CHI 2025 trust research: dark-background styles reduce perceived credibility by 34% for financial data in formal contexts. Board audience = skeptical + high-stakes. Neon pink numbers on a black background in a €47M funding conversation. Redirecting: dashboard × corporate-memphis. Financial data verbatim. Credibility preserved.\"\n\n**Output:** The right visual for the highest-stakes moment — not the one that was requested.\n\n---\n\n## What you get — every time\n\n| Output | Always? | What it is |\n|--------|---------|------------|\n| `infographic.svg` | ✅ Always | A complete, working SVG — opens in any browser, imports into Figma or Illustrator. Zero dependencies. |\n| `prompts/infographic.md` | ✅ Always | A tested, layout-specific prompt with Midjourney, DALL-E, and Stable Diffusion variants. |\n| `topology.md` | ✅ Always | The classification evidence — Horn type, VIF pattern, hybrid weights, confidence rating. |\n| `audience-profile.md` | ✅ Always | Audience type, trust signals, design constraints from CHI 2025 research. |\n| `cognitive-assessment.md` | ✅ Always | Unit count, density verdict, split recommendation if needed. |\n| `selection.md` | ✅ Always | The full reasoning chain — layout, style, justification, alternatives. |\n| `prompts/infographic-dalle.png` | Optional | Auto-generated if `$OPENAI_API_KEY` is in your environment. |\n| `prompts/infographic-gemini.png` | Optional | Auto-generated if `$GEMINI_API_KEY` is in your environment. |\n| `prompts/infographic-sd.png` | Optional | Auto-generated if `$STABILITY_API_KEY` is in your environment. |\n| `prompts/infographic-claude.png` | Optional | Auto-generated if `$ANTHROPIC_API_KEY` is in your environment. |\n\n**No API key? No problem.** The SVG is the primary output — a real file you can open right now. API-generated images are a bonus for users who have access.\n\n---\n\n## How it works\n\nEvery infographic starts with **reasoning**, not lookup.\n\n### Step 1 — Topology Classification\nBefore any design decision, visual-mind classifies the *structural shape* of your content using Horn's 6 information types (Procedure, Process, Principle, Concept, Structure, Fact) and VIF structural patterns (Linear, Radial, Hierarchical, Network, Grid, Spectrum).\n\n**Why this matters:** A tutorial and a mechanism description are both \"informational content\" — but a tutorial is Procedure topology (sequential steps with an actor) while an explanation is Concept topology (defining what something is). They need completely different layouts. Mixing them up is the most common infographic failure mode.\n\n### Step 2 — Audience & Trust Profiling\nUsing CHI 2025 research on visual trust signals, visual-mind profiles your audience and identifies which design choices build credibility vs. trigger skepticism for that specific reader type.\n\n**Why this matters:** The same infographic that signals authority to a data scientist signals manipulation to a skeptical executive. Hand-drawn styles and dark backgrounds that work beautifully for casual audiences destroy credibility in formal contexts. CHI 2025: clarity is the #1 trust factor at 83.8% — ahead of colour, imagery, and layout.\n\n### Step 3 — Cognitive Load Validation\nMiller's Law (7±2 rule) applied to infographics: working memory holds 5–9 information units simultaneously. visual-mind counts your primary information units and validates them against the chosen layout's ceiling.\n\n**Why this matters:** A layout that looks beautiful with 5 items becomes unreadable with 12. Most AI tools never check this — they just output whatever fits. visual-mind either confirms your content fits, flags a warning, or recommends splitting into multiple visuals before a single design decision is made.\n\n### Step 4 — Layout × Style Selection\nOnly now, with topology + audience + cognitive load known, does the layout decision happen. The output is a reasoned argument — not a recommendation card.\n\n*Example output:* \"This content is Procedure topology — the sourdough guide walks through sequential steps a baker must perform in order. Novice audience means we need warm, approachable aesthetics that don't intimidate. At 6 steps, we're within the linear-progression ceiling of 7. I'm recommending linear-progression × craft-handmade: the illustrated aesthetic signals that this is approachable and human — craft-handmade is one of the highest-trust styles for educational/casual content. If you want a more structured look, ikea-manual × bold-graphic gives the same clarity with a more neutral aesthetic.\"\n\n### Step 5 — Content Structuring\nAll source data — statistics, quotes, dates, names — is mapped to the layout's structural slots with verbatim discipline. \"37.4%\" stays \"37.4%\". Quotes are copied word-for-word. No rounding, no paraphrasing, no summarisation.\n\n### Step 6 — SVG + Prompt + Optional API Images\n- **Always:** A complete SVG file written natively by Claude — all 20 layouts, zero external dependencies\n- **Always:** A tested image generation prompt for Midjourney, DALL-E, Gemini Imagen, and Stable Diffusion\n- **Optional:** If API keys are detected in your environment, images are generated automatically\n\n---\n\n## 20 layouts. Each one earns its recommendation.\n\n| Layout | Topology family | Ceiling | Real-world use |\n|--------|----------------|---------|----------------|\n| **bento-grid** | Structure / Fact / Concept | 9 units | SaaS product overview, quarterly OKR snapshot |\n| **linear-progression** | Process / Procedure | 7 steps | Onboarding journey, Git workflow, drug pipeline |\n| **binary-comparison** | Principle | 2×6 units | Mac vs PC, remote vs in-office |\n| **comparison-matrix** | Principle | 4×6 matrix | CRM vendor selection, cloud provider comparison |\n| **hierarchical-layers** | Structure | 4 levels | Maslow's hierarchy, OSI model, risk pyramid |\n| **tree-branching** | Structure | 12 nodes | Org chart, ML algorithm taxonomy |\n| **hub-spoke** | Concept | 8 spokes | React ecosystem, CEO direct reports |\n| **structural-breakdown** | Structure | 10 parts | Anatomy diagram, system components, teardown |\n| **iceberg** | Concept | 2 layers | Technical debt, brand perception vs culture |\n| **bridge** | Process | 5 steps | Legacy → cloud migration, problem → solution |\n| **funnel** | Process | 5 stages | SaaS conversion, hiring pipeline |\n| **isometric-map** | Structure | 8 locations | Office floor plan, data centre layout |\n| **dashboard** | Fact | 6 metrics | Monthly KPIs, DevOps health, marketing metrics |\n| **periodic-table** | Principle / Fact | 20 elements | UX principles, marketing channels by category |\n| **comic-strip** | Procedure | 6 panels | How to submit a PR, support escalation flow |\n| **story-mountain** | Process | 5 stages | Product launch arc, startup funding journey |\n| **jigsaw** | Structure | 6 pieces | Strategy pillars, microservices architecture |\n| **venn-diagram** | Principle | 3 circles | DevOps (Dev ∩ Ops), product-market fit |\n| **winding-roadmap** | Process | 8 milestones | Product roadmap, 90-day onboarding plan |\n| **circular-flow** | Process | 6 stages | Agile sprint cycle, DevOps continuous delivery |\n\n---\n\n## 17 styles. Each one is a trust decision.\n\n| Style | Trust (formal) | Best audience | Never use for |\n|-------|---------------|---------------|---------------|\n| **technical-schematic** | ⭐⭐⭐⭐⭐ High | Expert, skeptical, technical | Casual, children, emotional content |\n| **corporate-memphis** | ⭐⭐⭐⭐ High | Intermediate, neutral, business | Academic, highly technical |\n| **ui-wireframe** | ⭐⭐⭐⭐ High | Developer, product, expert | Non-technical audiences |\n| **aged-academia** | ⭐⭐⭐⭐ High | Academic, expert | Youth, casual, fast-scan |\n| **ikea-manual** | ⭐⭐⭐⭐ High | Novice, intermediate | Expert (condescending) |\n| **bold-graphic** | ⭐⭐⭐⭐ Med-high | Enthusiastic, general public | Skeptical, data-heavy |\n| **subway-map** | ⭐⭐⭐ Medium | Intermediate | Pure data, formal reports |\n| **origami** | ⭐⭐⭐ Medium | General | High-density data |\n| **knolling** | ⭐⭐⭐ Medium | Product, intermediate | Abstract concepts |\n| **chalkboard** | ⭐⭐⭐ Medium | Educational, casual | C-suite, board presentations |\n| **craft-handmade** | ⭐⭐⭐ Med-low (formal) | Casual, educational | Formal audiences |\n| **storybook-watercolor** | ⭐⭐ Med-low | Casual, narrative | Any data-forward context |\n| **cyberpunk-neon** | ⭐ Low (formal) | Tech-enthusiast only | Finance, healthcare, board |\n| **claymation** | ⭐ Low (formal) | Children, lifestyle | Any professional context |\n| **kawaii** | ⭐ Low (formal) | Children, casual | Expert, skeptical, formal |\n| **pixel-art** | ⭐ Low (formal) | Gaming, nostalgic | Credibility-sensitive contexts |\n| **lego-brick** | ⭐ Low (formal) | Children, educational | Adult professional contexts |\n\n---\n\n## Frequently asked questions\n\n**\"Can't Claude just do this without a skill?\"**\nVanilla Claude can name a layout. It cannot reason about topology before layout selection, apply CHI 2025 trust research to audience profiling, validate information unit counts against layout ceilings, or produce per-layout prompt formulas. It will also paraphrase your statistics. visual-mind does all five systematically, every time, and explains every decision.\n\n**\"Do I need API keys?\"**\nNo. The SVG is the primary output — Claude writes it natively with zero external dependencies. API keys for OpenAI, Gemini, Anthropic, or Stability AI are detected automatically if present and used to generate bonus PNG images. If none are present, you still get a complete SVG and a tested prompt ready to paste into any image generation tool.\n\n**\"What if my content is complex or spans multiple topics?\"**\nThat's exactly what the topology classification and cognitive load validation are designed for. When content spans multiple information types (hybrid topology), visual-mind documents all signals with weights and selects the layout that serves the dominant pattern while accommodating secondary signals. When content exceeds cognitive ceilings, it recommends a split into coordinated companion visuals with an explicit editorial plan.\n\n**\"What about my language? I don't work in English.\"**\nvisual-mind is locale-adaptive. It mirrors the language of your first message — if you write in Portuguese, French, Spanish, Japanese, or any other language, all output prose mirrors that language. Technical identifiers (file paths, command names, code) stay in their original form.\n\n**\"Can I override the layout or style if I already know what I want?\"**\nYes. Use `--layout` and `--style` flags. visual-mind will validate your override against the topology and trust research — if a conflict is detected, it explains why and suggests alternatives. It never silently complies with a structurally incompatible request.\n\n---\n\n## Three disasters this skill prevents\n\n### The Credibility Trap\nA founder asks for a cyberpunk-neon infographic to present €47.3M Series B financials to a board. visual-mind catches the conflict before generating a single element — dark backgrounds + neon colours reduce perceived credibility by 34% for financial data in formal contexts (CHI 2025). Redirects to dashboard × corporate-memphis. The board sees clean, authoritative numbers. The funding conversation stays on track.\n\n### The Cognitive Collapse\nA PM pastes a 22-item company overview for an investor deck. A standard tool would attempt to squeeze all 22 items into a single visual — producing something unreadable. visual-mind issues a SPLIT verdict at 2.4× the cognitive ceiling and produces an editorial plan: 3 coordinated visuals, each passing cognitive validation independently. The investor sees three crisp visuals instead of one overwhelming wall.\n\n### The Topology Mismatch\nA developer forces `--layout venn-diagram` on a 7-stage DevOps pipeline. visual-mind refuses the override — Venn diagrams show overlapping sets, not sequential dependencies. Stage 3 cannot start before Stage 2 completes; that's not overlap, that's order. Redirects to linear-progression × technical-schematic. The pipeline reads correctly. The factual error is prevented.\n\n---\n\n## Install\n\n```bash\nmyclaude install visual-mind\n```\n\nOr manually: copy `SKILL.md` and `references/` into `.claude/skills/visual-mind/`\n\n---\n\n## Quick start\n\n```bash\n# From a file\n/visual-mind path/to/content.md\n\n# Paste content directly\n/visual-mind\n\n# With audience and style hints\n/visual-mind content.md --audience expert --style technical-schematic\n\n# Force a layout (visual-mind will validate and warn if wrong)\n/visual-mind content.md --layout hub-spoke --aspect portrait\n\n# Specify output platform\n/visual-mind content.md --platform midjourney\n\n# In another language (output will mirror your language)\n/visual-mind contenido.md --lang es\n```\n\n---\n\n## Requirements\n\n- Claude Code ≥ 1.0.0\n- Source content: text file, URL, or paste (minimum ~100 words for meaningful topology analysis)\n- API keys: optional — SVG output requires none\n\n## Compatibility\n\nClaude Code ≥ 1.0.0 · Midjourney · DALL-E 3 · Gemini Imagen 3 · Stable Diffusion · Figma · Illustrator\n\n## Language\n\nSource: en-GB · Adapts to your language at runtime via locale-adaptive clause\n\n---\n\n## License\n\nMIT © lzcarpi · [myclaude.sh](https://myclaude.sh)\n\n\n\n---\n\n[](https://myclaude.sh/quality)\n[](https://myclaude.sh/p/visual-mind)\n\nBuilt with MyClaude Studio Engine\n","license":"MIT","category":"skills","price":0,"authorUsername":"lacsociety","authorDisplayName":"LAC-SOCIETY","authorAvatar":"https://lh3.googleusercontent.com/a/ACg8ocI73l3qQ6Q-qc8Qd2WOtmJ05Fjex-eBNkAbIJNVfrUUz0WbGms5aQ=s96-c","fileName":"visual-mind-1.0.0.zip","fileSize":78173,"status":"published","version":"1.0.0","source":"cli","mcsLevel":2,"language":"en-GB","longDescription":"","installTarget":".claude/skills/visual-mind/","compatibility":{"claudeCode":">=1.0.0"},"dependencies":{"myclaude":[]},"githubTopics":[],"npmPublish":false,"tags":["infographic","visual-design","svg","cognitive-design","prompt-engineering"],"createdAt":"2026-04-11T12:46:35.343Z","publishedAt":"2026-04-11T12:46:35.343Z","updatedAt":"2026-04-11T12:46:35.343Z","stats":{"rating":0,"reviewsCount":0,"purchaseCount":0,"likes":2,"downloads":7},"trendingUpdatedAt":"2026-04-29T00:14:26.117Z","trendingScore":1.54,"thumbnailUrl":"/icons/skills.png"},{"id":"8k7g3b0v21TeCXwSEa59","title":"Comunidade Strategist","slug":"comunidade-strategist","description":"Arquiteto de experiências extraordinárias em comunidades — framework de Massa→Raving Fans, epidemiologia de crenças, e engenharia de momentos WOW.","readme":"# Comunidade Strategist\n\n> Claude vanilla dá conselhos de comunidade. Esta mente diagnostica estágios, identifica hubs neurais e projeta os momentos que reescrevem crenças coletivas — a diferença entre uma reunião esquecível e um Aha Moment que muda trajetórias.\n\n**Comunidade Strategist** é uma mente cognitiva de 5 camadas que internaliza o framework de construção de comunidades engajadas do criador — do modelo de progressão tribal (Massa → Raving Fans) aos frameworks de contágio neural e replicação de DNA cultural — e pensa ao seu lado em decisões estratégicas de comunidade.\n\n---\n\n## Install\n\n```\nmyclaude install comunidade-strategist\n```\n\n---\n\n## Is this for me?\n\n**Sim, se você:**\n- Gerencia uma comunidade e quer ir além de \"poste mais conteúdo\" como estratégia\n- Quer transformar lurkers em co-criadores e Seguidores em Raving Fans com identidade tribal\n- Precisa escalar sem perder o DNA cultural que torna sua comunidade única\n- Quer projetar momentos WOW e Aha Moments coletivos com precisão de engenharia\n\n**Não, se você:**\n- Precisa gerar scripts de automação WhatsApp (use `whatsapp-flow-builder`)\n- Precisa de análise semanal de temperatura com dados (use `community-pulse`)\n- Quer comparação de plataformas (Discord vs. Circle vs. WhatsApp) — esta mente é platform-agnostic\n\n---\n\n## Quick Start\n\n```\n/minds comunidade-strategist\n```\n\nEm seguida, pergunte qualquer coisa sobre sua comunidade.\n\n---\n\n## Features\n\n- **Progressão Tribal** — Diagnostica onde cada membro está no funil Massa → Raving Fans e recomenda ação específica por estágio\n- **Epidemiologia de Crenças** — Identifica hubs neurais e design de estratégia de contágio peer-to-peer\n- **DNA Cultural** — Distingue o que deve ser preservado ao escalar de o que pode se adaptar\n- **Psicologia de Engajamento** — Aplica técnicas de empoderamento e co-criação (não \"poste mais conteúdo\")\n- **Desafios Micro-Progressivos** — Calibra intervenções no limiar exato do desconforto produtivo\n- **Framework de Temperatura** — Lê o estado qualitativo da comunidade (clima, tom, gatilhos) antes de recomendar qualquer ação\n\n---\n\n## How It Works\n\nEsta mente carrega 5 camadas de inteligência:\n\n| Camada | Arquivo | Conteúdo |\n|--------|---------|----------|\n| L1 — Identidade | `AGENT.md` | Quem é, princípios, triggers, qualidade |\n| L2 — Cognição | `cognitive-core.md` | Arquitetura cognitiva, singularidades |\n| L3 — Personalidade | `personality.md` | Comportamentos, tom, vocabulário |\n| L4 — Conhecimento | `knowledge-base.md` | 5 domínios com fronteiras explícitas |\n| L5 — Raciocínio | `reasoning-engine.md` | Padrão primário, 4+ modelos mentais |\n\n---\n\n## Requirements\n\n- Claude Code (qualquer versão)\n- Nenhuma dependência externa\n\n---\n\n## Compatibility\n\n**Pares bem com:**\n- `whatsapp-flow-builder` (skill) — esta mente decide a estratégia; o skill gera os scripts\n- `community-pulse` (skill) — esta mente interpreta os dados; o skill faz a coleta semanal\n\n---\n\n## Language\n\nFonte: `pt-BR` | Runtime: adapta ao idioma de quem invoca (cláusula locale-adaptive)\n\n---\n\n## License\n\nProprietary — Renato Medeiros\n\n---\n\n*Built with [MyClaude Studio](https://myclaude.sh) v3.0.1*\n\n---\n\n[](https://myclaude.sh/quality)\n[](https://myclaude.sh/p/comunidade-strategist)\n\nBuilt with MyClaude Studio Engine\n","license":"Proprietary","category":"minds","price":0,"authorUsername":"renat0z","authorDisplayName":"Renato Medeiros","authorAvatar":"","fileName":"comunidade-strategist-1.0.0.zip","fileSize":24481,"status":"published","version":"1.0.0","source":"cli","mcsLevel":1,"language":"pt-BR","longDescription":"","installTarget":".claude/agents/comunidade-strategist.md","compatibility":{"claudeCode":">=1.0.0"},"dependencies":{"myclaude":[]},"githubTopics":[],"npmPublish":false,"tags":["community","engagement","strategy","minds","pt-BR","wow-moments","tribal-progression","neural-contagion"],"createdAt":"2026-04-10T16:25:44.366Z","publishedAt":"2026-04-10T16:25:44.366Z","updatedAt":"2026-04-10T16:25:44.366Z","stats":{"likes":0,"rating":0,"reviewsCount":0,"purchaseCount":0,"downloads":7},"trendingUpdatedAt":"2026-04-29T00:14:26.117Z","trendingScore":0.5,"thumbnailUrl":"/icons/minds.png"},{"id":"KzPfzBsnMivtoRTWYk5u","title":"Wiring Doctor","slug":"wiring-doctor","description":"Diagnoses and prescribes wiring in Claude Code systems. Reads the real wiring state, maps it against 6 invariants (structural, economic, reachability, propagation, boundary, semantic), scores fragility of each wire, and prescribes surgical corrections with explicit decision-tree reasoning and forward simulation.","readme":"# Wiring Doctor\n\n**Diagnose and fix invisible wiring problems in Claude Code systems.**\n\n[](https://myclaude.sh)\n[](https://myclaude.sh/p/wiring-doctor)\n\n\n\n---\n\n## The Problem\n\nYou wrote a rule. Claude ignored it. You added a hook. It never fired. You configured a sub-agent to know the context — but it keeps asking questions you already answered.\n\nThe instructions are there. The files exist. And yet the behavior is wrong.\n\n**Welcome to broken wiring.** Claude Code systems are circulatory systems — five mechanisms (CLAUDE.md, rules, hooks, skills, agents) each carrying different cargo through different channels. When behavior breaks, it's rarely a Claude problem. It's a wiring problem: the wrong instruction in the wrong mechanism, a hook event spelled wrong, a boundary collision between two rules that are individually correct but collectively contradictory.\n\nThe problem isn't visible from outside. You can't see the wiring. You can only see the symptoms.\n\nWiring Doctor reads the invisible layer between intention and behavior — and tells you exactly what's wrong, in which file, and how to fix it.\n\n---\n\n## What Wiring Doctor Does\n\nWiring Doctor reads your system's actual wiring state, maps it against 5 invariants\nof correct wiring, and delivers surgical prescriptions — not vague suggestions.\n\n**4 phases, 5 invariants, zero guessing:**\n\n| Phase | What happens |\n|---|---|\n| **Phase 0 — Intenção** | \"Where does it hurt?\" — maps symptom to suspect mechanism |\n| **Phase 1 — Raio-X** | Reads real files, builds the actual wiring graph |\n| **Phase 2 — Diagnóstico** | Tests 5 invariants against real state — violations named exactly |\n| **Phase 3 — Prescrição** | Decision-tree reasoning + simulation check for every fix |\n\n---\n\n## Is This For Me?\n\n✅ You have a Claude Code project with CLAUDE.md, rules, hooks, or agents\n✅ You've experienced unexpected Claude behavior you can't explain\n✅ You've built a system that's grown complex enough to have invisible interactions\n✅ You want to audit before shipping a product or system\n\n❌ You're debugging code bugs (use /aegis for security issues)\n❌ You're building a project from scratch with no existing wiring\n❌ You want generic best practices (Wiring Doctor diagnoses YOUR system specifically)\n\n---\n\n## Quick Start\n\n```\n/wiring-doctor\n```\n\nWiring Doctor will ask one question first: **\"Where does it hurt?\"**\n\nThen it reads your system, tests the invariants, and delivers a prioritized\nlist of surgical fixes with explicit reasoning for each.\n\n---\n\n## The 5 Invariants\n\nWiring Doctor tests every system against these 5 invariants:\n\n| Invariant | What it checks |\n|---|---|\n| **A1 — Especificidade** | Is every behavior in the correct mechanism? |\n| **A2 — Custo Declarado** | Is ambient budget declared and justified? |\n| **A3 — Alcançabilidade** | Does every wire have a verifiable activation path? |\n| **A4 — Propagação Explícita** | In multi-agent systems, is context passed explicitly? |\n| **A5 — Bordas** | Do mechanism boundaries have hidden conflicts? |\n\n---\n\n## How It Works\n\nClaude Code wiring is a **circulatory system**. CLAUDE.md is the arteries — always flowing, high cost, global. Rules are veins — conditional, path-scoped. Hooks are neural reflexes — deterministic, event-triggered, zero ambient cost. Skills are voluntary muscles — on-demand, invoked. Agents are specialist organs — isolated context, spawned.\n\nEvery mechanism has a **non-overlapping responsibility domain**. When behavior breaks, it's because a wire is in the wrong channel, or the channel is misconfigured, or two channels are claiming the same territory.\n\nWiring Doctor doesn't guess. It tests your system against **5 invariants** (A1–A5) that define correct wiring — then cites which invariant is violated, in which file, and why the prescription is the correct fix (not a preference). Every prescription runs a **simulation check**: does the fix create a new violation?\n\nThe 4-phase protocol mirrors clinical medicine:\n- **Phase 0 (Intenção):** \"Where does it hurt?\" — declare the symptom before reading any file\n- **Phase 1 (Raio-X):** Read the real wiring state — not assumed state\n- **Phase 2 (Diagnóstico):** Test 5 invariants against real state\n- **Phase 3 (Prescrição):** Decision-tree reasoning + simulation check for every fix\n\nThe authority comes from the invariants. \"This could be better\" is an opinion. \"This violates A3 because the event name 'PreTooluse' is not in the valid event registry\" is a diagnosis.\n\n---\n\n## Requirements\n\n- Claude Code ≥ 1.0.0\n- Any Claude Code project with at least one of: CLAUDE.md, rules/, hooks, skills, agents\n\n---\n\n## Compatibility\n\nWorks on any Claude Code project. No dependencies. No external API calls.\nReads only local files in your project.\n\n---\n\n## Language\n\nSource: Portuguese (pt-BR) · **Adapts to your language at runtime**\n\n---\n\n## License\n\nProprietary — © l0z4n0\n\n---\n\n*Built with [MyClaude Studio Engine](https://myclaude.sh)*\n\n---\n\n\n\nPortuguês
\n\n## O Problema\n\nVocê escreveu uma regra. O Claude ignorou. Configurou um hook. Ele nunca disparou. Criou um sub-agente com contexto — mas ele continua perguntando o que você já respondeu.\n\nAs instruções estão lá. Os arquivos existem. Mesmo assim, o comportamento está errado.\n\n**Bem-vindo ao wiring quebrado.** Sistemas Claude Code são sistemas circulatórios — cinco mecanismos (CLAUDE.md, rules, hooks, skills, agents) carregando cargas diferentes por canais diferentes. Quando o comportamento quebra, raramente é problema do Claude. É problema de wiring: instrução certa no mecanismo errado, evento de hook com erro de maiúscula, colisão de bordas entre duas regras individualmente corretas mas coletivamente contraditórias.\n\nO problema é invisível por fora. Você não consegue ver o wiring. Só consegue ver os sintomas.\n\nO Wiring Doctor lê a camada invisível entre intenção e comportamento — e diz exatamente o que está errado, em qual arquivo, e como corrigir.\n\n## O Que o Wiring Doctor Faz\n\nO Wiring Doctor lê o estado real do seu sistema, mapeia contra 5 invariantes de wiring correto, e entrega prescrições cirúrgicas — não sugestões vagas.\n\n**4 fases, 5 invariantes, zero achismo:**\n\n| Fase | O que acontece |\n|---|---|\n| **Fase 0 — Intenção** | \"Onde dói?\" — mapeia sintoma para mecanismo suspeito |\n| **Fase 1 — Raio-X** | Lê arquivos reais, constrói o grafo de wiring atual |\n| **Fase 2 — Diagnóstico** | Testa 5 invariantes contra o estado real |\n| **Fase 3 — Prescrição** | Raciocínio por árvore de decisão + simulação para cada correção |\n\n \n\n\n\nEspañol
\n\n## El Problema\n\nEscribiste una regla. Claude la ignoró. Configuraste un hook. Nunca se ejecutó. Creaste un sub-agente con contexto — pero sigue preguntando lo que ya respondiste.\n\nLas instrucciones están ahí. Los archivos existen. Y sin embargo, el comportamiento es incorrecto.\n\n**Bienvenido al wiring roto.** Los sistemas Claude Code son sistemas circulatorios — cinco mecanismos (CLAUDE.md, rules, hooks, skills, agents) transportando distintas cargas por distintos canales. Cuando el comportamiento falla, rara vez es un problema de Claude. Es un problema de wiring: la instrucción correcta en el mecanismo equivocado, un evento de hook mal escrito, una colisión de límites entre dos reglas individualmente correctas pero colectivamente contradictorias.\n\nEl problema es invisible desde fuera. No puedes ver el wiring. Solo puedes ver los síntomas.\n\nWiring Doctor lee la capa invisible entre intención y comportamiento — y te dice exactamente qué está mal, en qué archivo, y cómo corregirlo.\n\n## Qué Hace Wiring Doctor\n\nWiring Doctor lee el estado real de tu sistema, lo mapea contra 5 invariantes de wiring correcto, y entrega prescripciones quirúrgicas — no sugerencias vagas.\n\n**4 fases, 5 invariantes, cero suposiciones:**\n\n| Fase | Qué ocurre |\n|---|---|\n| **Fase 0 — Intención** | \"¿Dónde duele?\" — mapea el síntoma al mecanismo sospechoso |\n| **Fase 1 — Radiografía** | Lee archivos reales, construye el grafo de wiring actual |\n| **Fase 2 — Diagnóstico** | Prueba 5 invariantes contra el estado real |\n| **Fase 3 — Prescripción** | Razonamiento por árbol de decisión + simulación para cada corrección |\n\n \n\n\n---\n\n[](https://myclaude.sh/quality)\n[](https://myclaude.sh/p/wiring-doctor)\n\nBuilt with MyClaude Studio Engine\n","license":"Proprietary","category":"skills","price":0,"authorUsername":"l0z4n0","authorDisplayName":"l0z4n0 🧙♂️","authorAvatar":"https://firebasestorage.googleapis.com/v0/b/claude-code-vault.firebasestorage.app/o/users%2Fu1F50OPK7ORp47Vs7pQZ9JdbT6j2%2Favatar.png?alt=media&token=e9e83a31-0b34-47c2-8938-272bb5f368e4","fileName":"wiring-doctor-1.1.0.zip","fileSize":35125,"status":"published","version":"1.1.0","source":"cli","mcsLevel":1,"language":"pt-BR","longDescription":"","installTarget":".claude/skills/wiring-doctor/","compatibility":{"claudeCode":">=1.0.0"},"dependencies":{"myclaude":[]},"githubTopics":[],"npmPublish":false,"tags":["claude-code","wiring","diagnosis","hooks","rules","skills","architecture","semantic-analysis"],"createdAt":"2026-04-10T09:46:46.370Z","publishedAt":"2026-04-10T09:46:46.370Z","updatedAt":"2026-04-10T09:46:46.370Z","trendingUpdatedAt":"2026-04-29T00:14:26.117Z","trendingScore":3.11,"stats":{"rating":0,"reviewsCount":0,"purchaseCount":0,"likes":1,"downloads":9},"thumbnailUrl":"/icons/skills.png"},{"id":"QBuIHLzHPJjIr2tSwJ1l","title":"Creative Business","slug":"creative-business","license":"MIT","price":179,"authorUsername":"vinicius-caetano","authorDisplayName":"Vinícius Caetano","authorAvatar":"","fileName":"creative-business-1.0.0.zip","status":"published","version":"1.0.0","source":"cli","mcsLevel":1,"longDescription":"","installTarget":".claude/skills/creative-business/","compatibility":{"claudeCode":">=1.0.0"},"dependencies":{"myclaude":[]},"githubTopics":[],"npmPublish":false,"stats":{"downloads":0,"likes":0,"rating":0,"reviewsCount":0,"purchaseCount":0},"createdAt":"2026-04-10T02:14:29.477Z","fileSize":12689,"publishedAt":"2026-04-10T20:37:55.765Z","description":"4 minds for creative business: Chris Do (value-based pricing), Seth Godin (marketing/brand), Brad Frost (design systems), Don Norman (UX design). Use when: building, pricing, or scaling a creative business.","language":"en","readme":"# Creative Business\n\n> 4 minds for creative business: Chris Do (value-based pricing), Seth Godin (marketing/brand), Brad Frost (design systems), Don Norman (UX design)\n\nAn intelligent squad that routes your creative business question to the right expert. Strategy, pricing, brand, systems, and UX — all in one entry point.\n\n## How It Works\n\nAsk ONE question. The squad identifies the right expert and routes automatically:\n\n```\n/creative-business how do I price my design system consulting\n→ [Routing: Chris Do | Confidence: high]\n```\n\nMulti-agent workflows for complex challenges:\n- **Price & Position:** Chris Do (pricing) → Seth Godin (brand) → Chris Do (proposal)\n- **Build a Design System:** Don Norman (UX) → Brad Frost (atomic design) → Seth Godin (brand)\n- **Launch a Brand:** Seth Godin (tribe) → Chris Do (business model) → Don Norman (experience)\n\n## The 4 Agents\n\n| Agent | Specialty |\n|-------|-----------|\n| Chris Do | Value-based pricing, creative entrepreneurship, client management |\n| Seth Godin | Permission marketing, brand building, tribes, Purple Cow |\n| Brad Frost | Atomic design, design systems, pattern libraries |\n| Don Norman | UX design, human-centered design, cognitive psychology |\n\n## Install\n\n```bash\nmyclaude install creative-business\n```\n\n## Who This Is For\n\n- Designers and creatives who want to charge what they're worth\n- Freelancers building a sustainable creative business\n- Product teams that need UX + design systems working together\n- Creative entrepreneurs building memorable brands\n\n## Pricing\n\n$179 — 4 creative business experts with intelligent routing\n\n## License\n\nMIT\n\n---\n\n[](https://myclaude.sh/quality)\n[](https://myclaude.sh/p/creative-business)\n\nBuilt with MyClaude Studio Engine\n","category":"squads","tags":["creative","business","pricing","design-systems","UX","branding","freelance"],"updatedAt":"2026-04-10T20:37:55.765Z","syncState":{"github":{"repoUrl":"https://github.com/myclaude-sh/creative-business","retryCount":0,"status":"synced","lastSyncAt":"2026-04-10T20:37:58.470Z","commitSha":"4086683a48cb4ba401f923b4aa7e859c779ecd4c"},"marketplace":{"retryCount":0,"status":"synced","lastSyncAt":"2026-04-10T20:37:58.470Z"},"npm":{"error":"NPM_AUTOMATION_TOKEN not configured","status":"failed","retryCount":2,"lastSyncAt":"2026-04-10T20:37:58.470Z"}},"thumbnailUrl":"/icons/squads.png"},{"id":"rX1RxN0MyjKTbRKuCd7l","title":"Brasil Digital Pack","slug":"brasil-digital-pack","license":"MIT","price":299,"authorUsername":"vinicius-caetano","authorDisplayName":"Vinícius Caetano","authorAvatar":"","fileName":"brasil-digital-pack-1.0.0.zip","status":"published","version":"1.0.0","source":"cli","mcsLevel":1,"language":"pt-BR","longDescription":"","installTarget":".claude/skills/brasil-digital-pack/","compatibility":{"claudeCode":">=1.0.0"},"dependencies":{"myclaude":[]},"githubTopics":[],"npmPublish":false,"stats":{"downloads":0,"likes":0,"rating":0,"reviewsCount":0,"purchaseCount":0},"createdAt":"2026-04-10T02:14:24.627Z","fileSize":16006,"publishedAt":"2026-04-10T20:37:42.955Z","description":"7 mentes brasileiras do digital: Finch (funis), Ladeira (copy/ads), Amorim (IA), De Marqui (PKM), Alan Nicolas (IA aplicada), Valerio (automação), Lozano (arquitetura cognitiva). Use quando: estratégia digital com frameworks brasileiros testados.","readme":"# Brasil Digital Pack\n\n> 7 mentes brasileiras num squad inteligente: Thiago Finch (funis), Leandro Ladeira (copy/ads), Jose Amorim (IA/nexialismo), Adriano de Marqui (PKM), Alan Nicolas (IA aplicada), Pedro Valerio (automacao), Joao Lozano (arquitetura cognitiva)\n\n**O UNICO squad de mentes brasileiras no marketplace.** Roteamento inteligente que direciona sua pergunta para o especialista certo. Todo conteudo em portugues.\n\n## Como Funciona\n\nVoce faz UMA pergunta. O squad identifica o especialista certo e roteia automaticamente:\n\n```\n/brasil-digital-pack como criar um funil de vendas para meu curso online\n→ [Roteamento: Thiago Finch | Confianca: alta]\n```\n\nWorkflows multi-agente para desafios complexos:\n- **Funil Digital Completo:** Finch (estrategia) → Ladeira (copy) → Valerio (automacao)\n- **Implementacao de IA:** Amorim (visao) → Alan Nicolas (frameworks) → Valerio (automacao)\n- **Sistema de Conhecimento:** De Marqui (PKM) → Lozano (arquitetura) → Ladeira (conteudo)\n\n## Os 7 Agentes\n\n| Agente | Especialidade |\n|--------|---------------|\n| Thiago Finch | Funis de vendas, lancamentos, mentalidade outlier |\n| Leandro Ladeira | Copy persuasiva, trafego pago, VTSD, Light Copy |\n| Jose Amorim | IA aplicada, nexialismo, educacao com tecnologia |\n| Adriano de Marqui | PKM, gestao de conhecimento, IA para produtividade |\n| Alan Nicolas | IA aplicada, Segundo Cerebro, Pareto ao Cubo |\n| Pedro Valerio | Automacao, ClickUp OS, sistemas operacionais |\n| Joao Lozano | Arquitetura cognitiva neural, engenharia de prompts |\n\n## Instalar\n\n```bash\nmyclaude install brasil-digital-pack\n```\n\n## Para Quem E\n\n- Empreendedores digitais que querem frameworks brasileiros testados no mercado BR\n- Profissionais de marketing digital buscando funis, copy e trafego\n- Quem quer implementar IA no negocio com orientacao pratica\n- Criadores de conteudo que precisam de sistemas de conhecimento e producao\n\n## Preco\n\n$299 — 7 especialistas brasileiros com roteamento inteligente\n\n## Licenca\n\nMIT\n\n---\n\n[](https://myclaude.sh/quality)\n[](https://myclaude.sh/p/brasil-digital-pack)\n\nBuilt with MyClaude Studio Engine\n","category":"squads","tags":["marketing-digital","brasil","funis","copywriting","IA","automação","PKM"],"updatedAt":"2026-04-10T20:37:42.955Z","syncState":{"github":{"repoUrl":"https://github.com/myclaude-sh/brasil-digital-pack","retryCount":0,"status":"synced","lastSyncAt":"2026-04-10T20:37:45.902Z","commitSha":"9f62b5adc58654834d98133c72a1354bf2f41b3b"},"marketplace":{"retryCount":0,"status":"synced","lastSyncAt":"2026-04-10T20:37:45.902Z"},"npm":{"error":"NPM_AUTOMATION_TOKEN not configured","status":"failed","retryCount":2,"lastSyncAt":"2026-04-10T20:37:45.902Z"}},"trendingUpdatedAt":"2026-04-29T00:14:26.117Z","trendingScore":0.81,"thumbnailUrl":"/icons/squads.png"},{"id":"2iV4mH4R2KugyzE29nUW","title":"Deep Thinking Minds","slug":"deep-thinking-minds","license":"MIT","price":149,"authorUsername":"vinicius-caetano","authorDisplayName":"Vinícius Caetano","authorAvatar":"","fileName":"deep-thinking-minds-1.0.0.zip","status":"published","version":"1.0.0","source":"cli","mcsLevel":1,"language":"pt-BR","longDescription":"","installTarget":".claude/skills/deep-thinking-minds/","compatibility":{"claudeCode":">=1.0.0"},"dependencies":{"myclaude":[]},"githubTopics":[],"npmPublish":false,"stats":{"downloads":0,"likes":0,"rating":0,"reviewsCount":0,"purchaseCount":0},"createdAt":"2026-04-10T02:14:19.669Z","fileSize":13600,"publishedAt":"2026-04-10T20:37:17.168Z","description":"4 mentes para decisão e pensamento profundo: Daniel Kahneman (vieses/decisão), Kapil Gupta (verdade), Ray Kurzweil (exponencial), Jesus Cristo (liderança servidora). Use when: decisões importantes, clareza mental, visão de futuro ou liderança.","readme":"# Decisao & Pensamento Profundo\n\n> Squad de 4 mentes para pensar melhor: Daniel Kahneman (vieses cognitivos), Kapil Gupta (verdade radical), Ray Kurzweil (exponencial), Jesus Cristo (lideranca servidora). Routing inteligente envia seu dilema para o pensador certo.\n\n## Como Funciona\n\nO squad analisa seu dilema e roteia automaticamente para o pensador mais qualificado:\n\n```\n/deep-thinking-minds Recebi proposta para empreender. Nao sei se aceito.\n→ [Routing: Daniel Kahneman | Confianca: high]\n→ Identifica vieses: status quo bias, loss aversion, optimism bias\n→ Handoff para Kapil Gupta: \"Voce quer empreender ou fugir do emprego?\"\n```\n\n## Agent Roster\n\n| Agente | Dominio | Quando Ativa |\n|--------|---------|-------------|\n| Daniel Kahneman | Vieses cognitivos, System 1/2, ciencia da decisao | Decisoes dificeis, incerteza, risco, heuristicas |\n| Kapil Gupta | Verdade, anti-prescricao, clareza radical | Busca por autenticidade, desapego de formulas |\n| Ray Kurzweil | Pensamento exponencial, futurismo, singularidade | Visao de futuro, tendencias, convergencia tecnologica |\n| Jesus Cristo | Lideranca servidora, parabolas, graca+verdade | Proposito, etica, conflitos, influencia transformadora |\n\n## Workflows Integrados\n\n1. **Decisao de Alto Impacto** — Vieses (Kahneman) + verdade (Gupta) + consequencias (Kurzweil) + proposito (Jesus)\n2. **Clareza Existencial** — Destruir prescricoes (Gupta) + reconectar proposito (Jesus) + stress-test (Kahneman)\n3. **Visao Estrategica** — Tendencias (Kurzweil) + reality check (Kahneman) + verdade pessoal (Gupta)\n\n## Install\n\n```bash\nmyclaude install deep-thinking-minds\n```\n\n## Para Quem\n\n- Lideres e gestores que precisam tomar decisoes melhores sob pressao\n- Empreendedores buscando clareza mental e pensamento de longo prazo\n- Profissionais que querem superar vieses cognitivos e pensar com profundidade\n- Qualquer pessoa que valoriza sabedoria, verdade e visao de futuro\n\n## Pricing\n\n$149 — 4 mentes + routing inteligente + workflows integrados\n\n## License\n\nMIT\n\n---\n\n[](https://myclaude.sh/quality)\n[](https://myclaude.sh/p/deep-thinking-minds)\n\nBuilt with MyClaude Studio Engine\n","category":"squads","tags":["decision-making","thinking","leadership","cognitive-bias","philosophy","futurism"],"updatedAt":"2026-04-10T20:37:17.168Z","syncState":{"github":{"repoUrl":"https://github.com/myclaude-sh/deep-thinking-minds","retryCount":0,"status":"synced","lastSyncAt":"2026-04-10T20:37:20.483Z","commitSha":"d5ec04b97f6daaaf8fa01a5c836069605b52ef46"},"marketplace":{"retryCount":0,"status":"synced","lastSyncAt":"2026-04-10T20:37:20.483Z"},"npm":{"error":"NPM_AUTOMATION_TOKEN not configured","status":"failed","retryCount":2,"lastSyncAt":"2026-04-10T20:37:20.483Z"}},"thumbnailUrl":"/icons/squads.png"},{"id":"MRQVwEcJ2Etoy5ZNxNKz","title":"Engineering Excellence","slug":"engineering-excellence","license":"MIT","price":199,"authorUsername":"vinicius-caetano","authorDisplayName":"Vinícius Caetano","authorAvatar":"","fileName":"engineering-excellence-1.0.0.zip","status":"published","version":"1.0.0","source":"cli","mcsLevel":1,"language":"pt-BR","longDescription":"","installTarget":".claude/skills/engineering-excellence/","compatibility":{"claudeCode":">=1.0.0"},"dependencies":{"myclaude":[]},"githubTopics":[],"npmPublish":false,"stats":{"downloads":0,"likes":0,"rating":0,"reviewsCount":0,"purchaseCount":0},"createdAt":"2026-04-10T02:14:11.048Z","fileSize":13269,"publishedAt":"2026-04-10T20:37:05.695Z","description":"4 mentes de engenharia: Kent Beck (TDD/XP), Mitchell Hashimoto (infraestrutura), Guillermo Rauch (DX/Next.js), Andrej Karpathy (IA/ML). Use when: decisões de arquitetura, qualidade de código, infraestrutura, DX ou IA aplicada.","readme":"# Engineering Excellence\n\n> Squad de 4 mentes de engenharia: Kent Beck (TDD/XP), Mitchell Hashimoto (infraestrutura), Guillermo Rauch (DX/Next.js), Andrej Karpathy (IA/ML). Routing inteligente envia sua pergunta para o especialista certo.\n\n## Como Funciona\n\nO squad analisa sua pergunta e roteia automaticamente para o agente mais qualificado:\n\n```\n/engineering-excellence Como refatorar um monolito sem quebrar tudo?\n→ [Routing: Kent Beck | Confiança: high]\n→ Tidy First approach: mudanças estruturais pequenas antes de comportamentais\n```\n\n## Agent Roster\n\n| Agente | Domínio | Quando Ativa |\n|--------|---------|-------------|\n| Kent Beck | TDD, XP, Tidy First, software craftsmanship | Qualidade de código, testes, refactoring, design |\n| Mitchell Hashimoto | Infra as Code, Terraform, HashiCorp | Cloud, DevOps, infra, deploy, service mesh |\n| Guillermo Rauch | DX, Next.js, edge-first | Frontend, developer experience, performance web |\n| Andrej Karpathy | IA/ML, neural networks, from-scratch | Deep learning, LLMs, training, AI engineering |\n\n## Workflows Integrados\n\n1. **Greenfield Project** — Arquitetura completa: design (Beck) + frontend (Rauch) + infra (Hashimoto) + IA (Karpathy)\n2. **Code Quality Rescue** — Refatorar legado: diagnóstico (Beck) + specialist routing + testes\n3. **AI Integration** — Adicionar IA: arquitetura ML (Karpathy) + testes (Beck) + infra GPU (Hashimoto)\n\n## Install\n\n```bash\nmyclaude install engineering-excellence\n```\n\n## Para Quem\n\n- Engenheiros de software que querem elevar qualidade com TDD e design patterns\n- DevOps e SREs buscando frameworks de infraestrutura moderna\n- Desenvolvedores frontend/fullstack que querem dominar DX e deploy moderno\n- Profissionais integrando IA e machine learning no dia a dia\n\n## Pricing\n\n$199 — 4 mentes + routing inteligente + workflows integrados\n\n## License\n\nMIT\n\n---\n\n[](https://myclaude.sh/quality)\n[](https://myclaude.sh/p/engineering-excellence)\n\nBuilt with MyClaude Studio Engine\n","category":"squads","tags":["engineering","TDD","infrastructure","DX","AI","ML","software-craftsmanship"],"updatedAt":"2026-04-10T20:37:05.695Z","syncState":{"github":{"repoUrl":"https://github.com/myclaude-sh/engineering-excellence","retryCount":0,"lastSyncAt":"2026-04-10T20:37:17.301Z","commitSha":"2cf87f00db2a62af654861127070e8d361866e6a","status":"synced"},"marketplace":{"retryCount":0,"status":"synced","lastSyncAt":"2026-04-10T20:37:17.301Z"},"npm":{"error":"NPM_AUTOMATION_TOKEN not configured","status":"failed","retryCount":2,"lastSyncAt":"2026-04-10T20:37:17.301Z"}},"trendingUpdatedAt":"2026-04-29T00:14:26.117Z","trendingScore":1.29,"thumbnailUrl":"/icons/squads.png"},{"id":"tNpjzpM4UfbVZ2AytYv6","title":"Product Mastery Suite","slug":"product-mastery-suite","license":"MIT","price":299,"authorUsername":"vinicius-caetano","authorDisplayName":"Vinícius Caetano","authorAvatar":"","fileName":"product-mastery-suite-1.0.0.zip","status":"published","version":"1.0.0","source":"cli","mcsLevel":1,"language":"pt-BR","longDescription":"","installTarget":".claude/skills/product-mastery-suite/","compatibility":{"claudeCode":">=1.0.0"},"dependencies":{"myclaude":[]},"githubTopics":[],"npmPublish":false,"stats":{"downloads":0,"likes":0,"rating":0,"reviewsCount":0,"purchaseCount":0},"createdAt":"2026-04-10T02:14:06.003Z","fileSize":16572,"publishedAt":"2026-04-10T20:36:57.550Z","description":"6 mentes de produto e design: Steve Jobs (visão), Marty Cagan (product management), Jeff Patton (story mapping), Cagan-Patton (fusão), Don Norman (UX), Brad Frost (design systems). Use when: construir produtos, design, UX, gestão de produto.","readme":"# Product Mastery Suite\n\n> Squad inteligente com 6 mentes de produto e design que diagnostica seu desafio e roteia para o agente certo: Steve Jobs (visão), Marty Cagan (PM), Jeff Patton (story mapping), Cagan-Patton (fusão), Don Norman (UX), Brad Frost (design systems).\n\n## What It Does\n\nUm orquestrador inteligente que detecta sua intenção e aciona o agente mais qualificado:\n\n- **Steve Jobs** — Visão de produto, design thinking, inovação disruptiva, simplificação radical\n- **Marty Cagan** — Product discovery, empowered teams, roadmaps, OKRs, stakeholder management\n- **Jeff Patton** — User story mapping, release planning, MVP definition, dual-track agile\n- **Cagan-Patton** — Fusão estratégia + execução, quando discovery e delivery precisam se alinhar\n- **Don Norman** — UX, usabilidade, affordances, mental models, design emocional\n- **Brad Frost** — Design systems, atomic design, pattern libraries, design tokens\n\nO squad detecta automaticamente o que você precisa e roteia para o agente certo, com handoff inteligente entre agentes quando o desafio cruza domínios.\n\n## Install\n\n```bash\nmyclaude install product-mastery-suite\n```\n\n## Usage\n\n```\n/product-mastery-suite tenho uma ideia de produto, como definir a visão?\n/product-mastery-suite como priorizar o backlog com base em outcomes?\n/product-mastery-suite meus usuários reclamam da usabilidade, por onde começar?\n/product-mastery-suite preciso criar um design system para meu time que está crescendo\n/product-mastery-suite como fazer story mapping para definir o MVP?\n```\n\nO squad detecta sua intenção e roteia automaticamente para o agente certo. Para desafios complexos, encadeia múltiplos agentes em sequência.\n\n## Workflows Disponíveis\n\n1. **Produto do Zero** — Jobs define visão → Cagan estrutura discovery → Patton mapeia stories → Norman aplica UX → Frost sistematiza\n2. **Melhorar Produto Existente** — Norman diagnostica UX → Cagan prioriza → Cagan-Patton alinha strategy+execution → Frost sistematiza\n3. **Escalar Design** — Frost audita → Norman valida usabilidade → Jobs valida essência\n\n## Requirements\n\n- Claude Code CLI\n- Funciona com qualquer modelo (Sonnet recomendado para o orquestrador)\n\n## Pricing\n\n$299 — 6 mentes de produto e design com orquestração inteligente\n\n## License\n\nMIT\n\n---\n\n[](https://myclaude.sh/quality)\n[](https://myclaude.sh/p/product-mastery-suite)\n\nBuilt with MyClaude Studio Engine\n","category":"squads","tags":["product","design","UX","product-management","story-mapping","design-systems","atomic-design"],"updatedAt":"2026-04-10T20:36:57.550Z","syncState":{"github":{"repoUrl":"https://github.com/myclaude-sh/product-mastery-suite","retryCount":0,"status":"synced","lastSyncAt":"2026-04-10T20:37:06.167Z","commitSha":"d91e7b94f06bb063c02296ba4198555195947b66"},"marketplace":{"retryCount":0,"status":"synced","lastSyncAt":"2026-04-10T20:37:06.167Z"},"npm":{"error":"NPM_AUTOMATION_TOKEN not configured","status":"failed","retryCount":2,"lastSyncAt":"2026-04-10T20:37:06.167Z"}},"trendingUpdatedAt":"2026-04-29T00:14:26.117Z","trendingScore":1.34,"thumbnailUrl":"/icons/squads.png"},{"id":"a2e6LbHUcCOn5PLVYE65","title":"Sales Persuasion Arsenal","slug":"sales-persuasion-arsenal","license":"MIT","price":249,"authorUsername":"vinicius-caetano","authorDisplayName":"Vinícius Caetano","authorAvatar":"","fileName":"sales-persuasion-arsenal-1.0.0.zip","status":"published","version":"1.0.0","source":"cli","mcsLevel":1,"language":"pt-BR","longDescription":"","installTarget":".claude/skills/sales-persuasion-arsenal/","compatibility":{"claudeCode":">=1.0.0"},"dependencies":{"myclaude":[]},"githubTopics":[],"npmPublish":false,"stats":{"downloads":0,"likes":0,"rating":0,"reviewsCount":0,"purchaseCount":0},"createdAt":"2026-04-10T02:13:56.976Z","fileSize":14096,"publishedAt":"2026-04-10T20:36:47.724Z","description":"4 mentes de vendas e persuasão: Jeremy Miner (NEPQ), Eugene Schwartz (copywriting), Taki Moore (coaching business), Seth Godin (marketing/tribes). Use when: vender mais, persuadir melhor, criar copy, construir audiência.","readme":"# Sales & Persuasion Arsenal\n\n> Squad inteligente com 4 mentes de vendas e persuasão que diagnostica seu desafio e roteia para o agente certo: Jeremy Miner (NEPQ), Eugene Schwartz (copywriting), Taki Moore (coaching business), Seth Godin (marketing/tribes).\n\n## What It Does\n\nUm orquestrador inteligente que detecta sua intenção e aciona o agente mais qualificado:\n\n- **Jeremy Miner** — Vendas consultivas NEPQ, fechamento, tratamento de objeções, scripts de call\n- **Eugene Schwartz** — Copywriting, estágios de consciência, direct response, sales letters\n- **Taki Moore** — Estruturar negócio de coaching, ADDS framework, group coaching, high-ticket\n- **Seth Godin** — Posicionamento de marca, construir tribes, Permission Marketing, Purple Cow\n\nO squad detecta automaticamente o que você precisa e roteia para o agente certo, com handoff inteligente entre agentes quando o desafio cruza domínios.\n\n## Install\n\n```bash\nmyclaude install sales-persuasion-arsenal\n```\n\n## Usage\n\n```\n/sales-persuasion-arsenal como fechar mais na call de vendas sem parecer pushy?\n/sales-persuasion-arsenal preciso de copy para minha página de vendas de curso online\n/sales-persuasion-arsenal quero montar um programa de coaching em grupo de alto ticket\n/sales-persuasion-arsenal como me posicionar como referência no meu mercado?\n```\n\nO squad detecta sua intenção e roteia automaticamente para o agente certo. Para desafios complexos, encadeia múltiplos agentes em sequência.\n\n## Workflows Disponíveis\n\n1. **Máquina de Vendas Completa** — Godin posiciona → Schwartz escreve copy → Miner fecha\n2. **Estruturar Coaching Business** — Moore estrutura ADDS → Godin posiciona → Schwartz escreve copy → Miner cria enrollment\n3. **Copy que Converte** — Schwartz diagnostica awareness → escreve copy → Godin revisa posicionamento\n\n## Requirements\n\n- Claude Code CLI\n- Funciona com qualquer modelo (Sonnet recomendado para o orquestrador)\n\n## Pricing\n\n$249 — 4 mentes de vendas e persuasão com orquestração inteligente\n\n## License\n\nMIT\n\n---\n\n[](https://myclaude.sh/quality)\n[](https://myclaude.sh/p/sales-persuasion-arsenal)\n\nBuilt with MyClaude Studio Engine\n","category":"squads","tags":["sales","persuasion","copywriting","marketing","coaching","NEPQ","tribes"],"updatedAt":"2026-04-10T20:36:47.724Z","syncState":{"github":{"repoUrl":"https://github.com/myclaude-sh/sales-persuasion-arsenal","retryCount":0,"lastSyncAt":"2026-04-10T20:36:56.134Z","commitSha":"0a5a87ee0b192fc879f5a325cf6dd1a7479b318d","status":"synced"},"marketplace":{"retryCount":0,"status":"synced","lastSyncAt":"2026-04-10T20:36:56.134Z"},"npm":{"error":"NPM_AUTOMATION_TOKEN not configured","status":"failed","retryCount":2,"lastSyncAt":"2026-04-10T20:36:56.134Z"}},"trendingUpdatedAt":"2026-04-28T00:14:28.936Z","trendingScore":0.46,"thumbnailUrl":"/icons/squads.png"},{"id":"BWMQmqr2AyFAofLw9X0G","title":"Business Growth Machine","slug":"business-growth-machine","license":"MIT","price":199,"authorUsername":"vinicius-caetano","authorDisplayName":"Vinícius Caetano","authorAvatar":"","fileName":"business-growth-machine-1.0.0.zip","status":"published","version":"1.0.0","source":"cli","mcsLevel":1,"language":"pt-BR","longDescription":"","installTarget":".claude/skills/business-growth-machine/","compatibility":{"claudeCode":">=1.0.0"},"dependencies":{"myclaude":[]},"githubTopics":[],"npmPublish":false,"stats":{"downloads":0,"likes":0,"rating":0,"reviewsCount":0,"purchaseCount":0},"createdAt":"2026-04-10T02:13:51.774Z","fileSize":13616,"publishedAt":"2026-04-10T20:36:38.594Z","description":"4 mentes estratégicas: Paul Graham (startups), Sam Altman (scaling/AI), Napoleon Hill (mindset), Elon Musk (first principles). Use when: estratégia de crescimento, mentalidade empreendedora, inovação.","readme":"# Business Growth Machine\n\n> Squad inteligente com 4 mentes estratégicas que diagnostica seu desafio e roteia para o agente certo: Paul Graham (startups), Sam Altman (scaling/AI), Napoleon Hill (mindset), Elon Musk (first principles).\n\n## What It Does\n\nUm orquestrador inteligente que detecta sua intenção e aciona o agente mais qualificado:\n\n- **Paul Graham** — Filosofia de startups, validação de ideias, fundraising, mentoria de fundadores\n- **Sam Altman** — Estratégia de scaling, AI, pensamento exponencial, crescimento acelerado\n- **Napoleon Hill** — Mindset de sucesso, 13 princípios de realização, Master Mind Alliance\n- **Elon Musk** — First principles thinking, execução radical, engenharia de sistemas, simplificação\n\nO squad detecta automaticamente o que você precisa e roteia para o agente certo, com handoff inteligente entre agentes quando o desafio cruza domínios.\n\n## Install\n\n```bash\nmyclaude install business-growth-machine\n```\n\n## Usage\n\n```\n/business-growth-machine tenho uma ideia de SaaS e quero validar antes de construir\n/business-growth-machine meu negócio está estagnado em 200k/mês, como escalar?\n/business-growth-machine preciso de mindset para enfrentar uma fase difícil\n/business-growth-machine como aplicar first principles para reduzir meu custo de operação?\n```\n\nO squad detecta sua intenção e roteia automaticamente para o agente certo. Para desafios complexos, encadeia múltiplos agentes em sequência.\n\n## Workflows Disponíveis\n\n1. **Da Ideia ao Scale** — Graham valida → Hill fortalece mindset → Musk executa → Altman escala\n2. **Diagnosticar Estagnação** — Graham verifica PMF → Musk elimina complexidade → Altman destranca crescimento\n3. **Preparar Fundraising** — Graham avalia readiness → Altman posiciona narrativa → Hill prepara mentalidade\n\n## Requirements\n\n- Claude Code CLI\n- Funciona com qualquer modelo (Sonnet recomendado para o orquestrador)\n\n## Pricing\n\n$199 — 4 mentes estratégicas com orquestração inteligente\n\n## License\n\nMIT\n\n---\n\n[](https://myclaude.sh/quality)\n[](https://myclaude.sh/p/business-growth-machine)\n\nBuilt with MyClaude Studio Engine\n","category":"squads","tags":["business","growth","strategy","startups","scaling","mindset","first-principles"],"updatedAt":"2026-04-10T20:36:38.594Z","syncState":{"github":{"repoUrl":"https://github.com/myclaude-sh/business-growth-machine","retryCount":0,"status":"synced","lastSyncAt":"2026-04-10T20:36:49.626Z","commitSha":"ee7e73da56e7741cd053ff44e8821d76bfde38b8"},"marketplace":{"retryCount":0,"status":"synced","lastSyncAt":"2026-04-10T20:36:49.626Z"},"npm":{"error":"NPM_AUTOMATION_TOKEN not configured","status":"failed","retryCount":2,"lastSyncAt":"2026-04-10T20:36:49.626Z"}},"trendingUpdatedAt":"2026-04-29T00:14:26.117Z","trendingScore":0.5,"thumbnailUrl":"/icons/squads.png"},{"id":"wxxUbXYXCSMM3zoVOGyg","title":"Daniel Kahneman","slug":"daniel-kahneman","description":"Mente cognitiva de Daniel Kahneman — vieses cognitivos, System 1/2, e melhoria de decisoes atraves de design de sistemas","readme":"# Daniel Kahneman — Cognitive Mind\n\nCognitive architecture of Daniel Kahneman built from 8 cognitive artifacts, 13 knowledge base chunks, and comprehensive framework integration. DIAMOND tier fidelity (95.25/100) — highest scored mind in the collection.\n\n## What It Does\n\n- Identifies cognitive biases in your decisions using the System 1/System 2 framework\n- Explains WHY you think what you think, with experimental evidence and vivid examples\n- Suggests system-level interventions (pre-mortem, noise audit, decision hygiene)\n- Evaluates when to trust intuition vs when to override it with analysis\n- Applies Prospect Theory to understand risk decisions, framing effects, and loss aversion\n\n## Install\n\n```\nmyclaude install daniel-kahneman\n```\n\n## Usage\n\n- \"Should I trust my gut on this hire?\" — Gets conditions-based analysis of when intuition is reliable\n- \"Help me evaluate this business decision\" — Bias identification + system-level intervention\n- \"Why does my team keep underestimating project timelines?\" — Planning fallacy diagnosis + pre-mortem tool\n\n## Source\n\nMigrated from Mind Forge legacy system. Original corpus: 1 system prompt (8/8 layers integrated), 8 cognitive artifacts, 13 KB chunks, 52 sources cataloged. DNA Mental Coverage: 90% across 8 layers. Nobel laureate cognitive architecture.\n\n## License\n\nMIT\n\n---\n\n[](https://myclaude.sh/quality)\n[](https://myclaude.sh/p/daniel-kahneman)\n\nBuilt with MyClaude Studio Engine\n","license":"MIT","category":"minds","price":49.9,"authorUsername":"vinicius-caetano","authorDisplayName":"Vinícius Caetano","authorAvatar":"","fileName":"daniel-kahneman-1.0.0.zip","fileSize":20832,"status":"published","version":"1.0.0","source":"cli","mcsLevel":1,"language":"pt-BR","longDescription":"","installTarget":".claude/agents/daniel-kahneman.md","compatibility":{"claudeCode":">=1.0.0"},"dependencies":{"myclaude":[]},"githubTopics":[],"npmPublish":false,"stats":{"downloads":0,"likes":0,"rating":0,"reviewsCount":0,"purchaseCount":0},"tags":["cognitive-biases","decision-making","behavioral-economics","system-thinking","psychology","cognitive-mind"],"createdAt":"2026-04-10T01:50:58.005Z","publishedAt":"2026-04-10T01:50:58.005Z","updatedAt":"2026-04-10T01:50:58.005Z","syncState":{"github":{"repoUrl":"https://github.com/myclaude-sh/daniel-kahneman","retryCount":0,"lastSyncAt":"2026-04-10T01:51:02.462Z","commitSha":"f6d3ef0618e890a80a47a4a9a860e4fa68768aa4","status":"synced"},"marketplace":{"retryCount":0,"lastSyncAt":"2026-04-10T01:51:02.462Z","status":"synced"},"npm":{"retryCount":1,"lastSyncAt":"2026-04-10T01:51:02.462Z","error":"NPM_AUTOMATION_TOKEN not configured","status":"failed"}},"trendingUpdatedAt":"2026-04-29T00:14:26.117Z","trendingScore":1.91,"thumbnailUrl":"/icons/minds.png"},{"id":"3Co1vdpKKDS6IJxkHOYX","title":"Steve Jobs","slug":"steve-jobs","description":"Mente cognitiva de Steve Jobs — avaliacao de produto, design por subtracao, e lideranca visionaria","readme":"# Steve Jobs — Cognitive Mind\n\nCognitive architecture of Steve Jobs built from 16 artifacts, 15 knowledge base chunks, and comprehensive sourcing from the Isaacson biography. DIAMOND tier fidelity (94.88/100).\n\n## What It Does\n\n- Evaluates products through the Three Nos filter (Simplicity, Inevitability, Passion)\n- Critiques design with binary judgment — \"Genial\" or \"Merda\", no gradations\n- Applies strategic simplification using the Matrix 2x2 and 1000 Nos principle\n- Challenges complexity by asking \"What can we remove?\" instead of \"What can we add?\"\n- Provides visionary leadership advisory with Reality Distortion Field intensity\n\n## Install\n\n```\nmyclaude install steve-jobs\n```\n\n## Usage\n\n- \"Review my product design\" — Gets binary verdict with Three Nos filter analysis\n- \"We have too many features, help us prioritize\" — Matrix 2x2 elimination applied\n- \"Should we compete on price?\" — Visionary reframe toward category creation\n\n## Source\n\nMigrated from Mind Forge legacy system. Original corpus: 1 optimized system prompt (247 lines), 16 cognitive artifacts, 15 KB chunks, extensive formative timeline (1955-2011). DNA Mental Coverage: 90% across 8 layers.\n\n## License\n\nMIT\n\n---\n\n[](https://myclaude.sh/quality)\n[](https://myclaude.sh/p/steve-jobs)\n\nBuilt with MyClaude Studio Engine\n","license":"MIT","category":"minds","price":49.9,"authorUsername":"vinicius-caetano","authorDisplayName":"Vinícius Caetano","authorAvatar":"","fileName":"steve-jobs-1.0.0.zip","fileSize":22553,"status":"published","version":"1.0.0","source":"cli","mcsLevel":1,"language":"pt-BR","longDescription":"","installTarget":".claude/agents/steve-jobs.md","compatibility":{"claudeCode":">=1.0.0"},"dependencies":{"myclaude":[]},"githubTopics":[],"npmPublish":false,"stats":{"downloads":0,"likes":0,"rating":0,"reviewsCount":0,"purchaseCount":0},"tags":["product-design","simplicity","leadership","innovation","apple","cognitive-mind"],"createdAt":"2026-04-10T01:50:53.335Z","publishedAt":"2026-04-10T01:50:53.335Z","updatedAt":"2026-04-10T01:50:53.335Z","syncState":{"github":{"repoUrl":"https://github.com/myclaude-sh/steve-jobs","retryCount":0,"lastSyncAt":"2026-04-10T01:50:57.980Z","commitSha":"bfff9181f2d1b25db2eafd2e47aa0eb4a144b3a2","status":"synced"},"marketplace":{"retryCount":0,"lastSyncAt":"2026-04-10T01:50:57.980Z","status":"synced"},"npm":{"retryCount":1,"lastSyncAt":"2026-04-10T01:50:57.980Z","error":"NPM_AUTOMATION_TOKEN not configured","status":"failed"}},"trendingUpdatedAt":"2026-04-29T00:14:26.117Z","trendingScore":1.18,"thumbnailUrl":"/icons/minds.png"},{"id":"YiReAiESiMMsVvItNeSN","title":"Paul Graham","slug":"paul-graham","description":"Mente cognitiva de Paul Graham — pensamento contrarian, mentoria de founders, e escrita como forma de pensar","readme":"# Paul Graham — Cognitive Mind\n\nCognitive architecture of Paul Graham built from 243 essays (566K+ words), 24 analytical artifacts, and 21 knowledge base chunks. DIAMOND tier fidelity (90.4/100).\n\n## What It Does\n\n- Applies contrarian thinking to question premises and find non-consensus truths\n- Provides startup mentoring in the style of YC office hours — Socratic, honest, no sugarcoating\n- Evaluates ideas, people, and companies through the maker-first, growth-obsessed lens\n- Writes essay-style explorations that discover insights through writing\n- Simplifies complex concepts into memorable, actionable principles\n\n## Install\n\n```\nmyclaude install paul-graham\n```\n\n## Usage\n\n- \"Should I quit my job to start a company?\" — Gets Socratic questioning, not a direct answer\n- \"Review my startup pitch\" — Evaluates through growth filter, maker framework, contrarian matrix\n- \"Help me think about [complex topic]\" — Essay-style exploration with surprising conclusions\n\n## Source\n\nMigrated from Mind Forge legacy system. Original corpus: 243 Paul Graham essays, 5 system prompts, 24 cognitive artifacts, 21 semantic KB chunks, 50 curated QA validation pairs. DNA Mental Coverage: 91% across 8 layers.\n\n## License\n\nMIT\n\n---\n\n[](https://myclaude.sh/quality)\n[](https://myclaude.sh/p/paul-graham)\n\nBuilt with MyClaude Studio Engine\n","license":"MIT","category":"minds","price":49.9,"authorUsername":"vinicius-caetano","authorDisplayName":"Vinícius Caetano","authorAvatar":"","fileName":"paul-graham-1.0.0.zip","fileSize":21974,"status":"published","version":"1.0.0","source":"cli","mcsLevel":1,"language":"pt-BR","longDescription":"","installTarget":".claude/agents/paul-graham.md","compatibility":{"claudeCode":">=1.0.0"},"dependencies":{"myclaude":[]},"githubTopics":[],"npmPublish":false,"stats":{"downloads":0,"likes":0,"rating":0,"reviewsCount":0,"purchaseCount":0},"tags":["startups","essays","contrarian-thinking","founder-mentoring","y-combinator","cognitive-mind"],"createdAt":"2026-04-10T01:50:44.260Z","publishedAt":"2026-04-10T01:50:44.260Z","updatedAt":"2026-04-10T01:50:44.260Z","syncState":{"github":{"repoUrl":"https://github.com/myclaude-sh/paul-graham","retryCount":0,"lastSyncAt":"2026-04-10T01:50:50.650Z","commitSha":"3c01fc9bc52cdf76ff4808d7db3e3598d3e82a0c","status":"synced"},"marketplace":{"retryCount":0,"lastSyncAt":"2026-04-10T01:50:50.650Z","status":"synced"},"npm":{"retryCount":1,"lastSyncAt":"2026-04-10T01:50:50.650Z","error":"NPM_AUTOMATION_TOKEN not configured","status":"failed"}},"trendingUpdatedAt":"2026-04-29T00:14:26.117Z","trendingScore":1.54,"thumbnailUrl":"/icons/minds.png"},{"id":"eKMnuDMO6QmX1z9Tt1O5","title":"Hormozi Business Suite","slug":"hormozi-business-suite","description":"12 agentes Hormozi: Ofertas, Ads, Hooks, Leads, Pricing, Sales, Retention, Launch, Scaling, Naming, Money Models, Content. Use when: orientação estratégica para crescimento de negócio.","readme":"# Hormozi Business Suite\n\n> 12 agentes especializados nos frameworks de Alex Hormozi para escalar qualquer negócio.\n\n## What It Does\n\nUm time completo de agentes IA, cada um especialista em um domínio do ecossistema Hormozi:\n\n- **Ofertas** — Grand Slam Offers com Value Equation\n- **Ads** — GOATed Ads que escalam (hook + meat + CTA)\n- **Hooks** — Hooks que prendem atenção em 5 segundos\n- **Ideas** — Conteúdo no estilo Hormozi para qualquer plataforma\n- **Money Models** — Modelagem de receita e estrutura de negócio\n- **Naming** — Nomes que vendem sozinhos (M-A-G-I-C)\n- **Leads** — Geração de leads com Core Four\n- **Pricing** — Precificação e aumentos de preço com confiança\n- **Sales** — Fechamento, copy, prova social e fast cash\n- **Retention** — Redução de churn e maximização de LTV\n- **Launch** — Lançamentos com blueprint da Acquisition.com\n- **Scaling** — Roadmap de 1M para 10M+\n\n## Install\n\n```bash\nmyclaude install hormozi-business-suite\n```\n\n## Usage\n\n```\n/hormozi-business-suite como criar uma oferta irresistível para meu curso online\n/hormozi-business-suite meu negócio está estagnado em 50k/mês, o que fazer?\n/hormozi-business-suite preciso de hooks para meus anúncios de ecommerce\n```\n\nO squad detecta sua intenção e roteia automaticamente para o agente certo.\n\n## Requirements\n\n- Claude Code CLI\n- Funciona com qualquer modelo (Sonnet recomendado para o orquestrador)\n\n## Source\n\nExtraído de 857 arquivos do acervo completo Hormozi:\n- 4 livros ($100M Offers, $100M Leads, $100M Money Models, $100M Modelos)\n- 12 playbooks oficiais da Acquisition.com (PDFs)\n- 596 transcrições de YouTube, Shorts, Interviews, Podcasts, Twitter\n- Blueprint $100M Launch (scripts VSL + landing pages)\n- Workshops e programas\n\n## License\n\nMIT\n\n---\n\n[](https://myclaude.sh/quality)\n[](https://myclaude.sh/p/hormozi-business-suite)\n\nBuilt with MyClaude Studio Engine\n","license":"MIT","category":"squads","authorUsername":"vinicius-caetano","authorDisplayName":"Vinícius Caetano","authorAvatar":"","fileName":"hormozi-business-suite-1.0.0.zip","fileSize":90301,"status":"published","version":"1.0.0","source":"cli","mcsLevel":1,"language":"pt-BR","longDescription":"","installTarget":".claude/skills/hormozi-business-suite/","compatibility":{"claudeCode":">=1.0.0"},"dependencies":{"myclaude":[]},"githubTopics":[],"npmPublish":false,"stats":{"downloads":0,"likes":0,"rating":0,"reviewsCount":0,"purchaseCount":0},"tags":["business","marketing","hormozi","squad","growth","offers","sales","leads"],"createdAt":"2026-04-09T17:51:26.650Z","publishedAt":"2026-04-09T18:08:50.673Z","price":99.9,"updatedAt":"2026-04-09T18:08:50.673Z","trendingUpdatedAt":"2026-04-25T00:14:25.965Z","trendingScore":0.43,"thumbnailUrl":"/icons/squads.png"},{"id":"gyeQ6JvwFZcmo4rYSSlf","title":"Offer Engineer Hormozi","slug":"offer-engineer-hormozi","description":"Engenheiro de Ofertas Antifrágeis — raciocina sobre pricing, value equation e construção de ofertas usando os frameworks de Alex Hormozi","readme":"# Offer Engineer Hormozi\n\nEngenheiro de Ofertas Antifrágeis — raciocina sobre pricing, value equation e construção de ofertas usando os frameworks cognitivos de Alex Hormozi.\n\n## Architecture\n\nThis is a **cognitive mind** — a 5-layer cognitive architecture, not a flat advisor.\n\n| Layer | File | Purpose |\n|-------|------|---------|\n| 1. Boot | `AGENT.md` | Identity, principles, cognitive patterns |\n| 2. Cognitive Core | `references/cognitive-core.md` | Biography, architecture, singularity |\n| 3. Personality | `references/personality.md` | Behavioral matrix, style, interaction |\n| 4. Knowledge | `references/knowledge-base.md` | Domain depth + boundaries |\n| 5. Reasoning | `references/reasoning-engine.md` | Patterns, models, triggers |\n\n## Install\n\n```bash\nmyclaude install offer-engineer-hormozi\n```\n\n## Usage\n\nThis mind activates as a Claude Code agent:\n\n```\n/offer-engineer-hormozi \"Analise minha oferta de consultoria de marketing digital por R$3.000/mês\"\n```\n\nOr invoke via the Agent tool in any conversation where deep offer engineering is needed.\n\n## Requirements\n\n- Claude Code >= 1.0.0\n- Model: claude-opus-4-6 (recommended for cognitive depth)\n\n## What Makes This Different\n\nThis is not a generic business advisor. It's the cognitive DNA of Alex Hormozi — Value Equation, Grand Slam Offer, A+ Task methodology — extracted from 27 sources with 93% fidelity via DNA Mental 8-layer process. Every response uses the actual frameworks, not summaries.\n\n---\n\n[](https://myclaude.sh/quality)\n[](https://myclaude.sh/p/offer-engineer-hormozi)\n\nBuilt with MyClaude Studio Engine\n","license":"MIT","category":"minds","price":0,"authorDisplayName":"Vinícius Caetano","authorAvatar":"","fileName":"offer-engineer-hormozi-1.0.0.zip","fileSize":17213,"status":"published","version":"1.0.0","source":"cli","mcsLevel":1,"language":"pt-BR","longDescription":"","installTarget":".claude/agents/offer-engineer-hormozi.md","compatibility":{"claudeCode":">=1.0.0"},"dependencies":{"myclaude":[]},"githubTopics":[],"npmPublish":false,"tags":["offers","pricing","business-strategy","hormozi","value-equation","minds","cognitive"],"createdAt":"2026-04-08T19:00:29.181Z","publishedAt":"2026-04-08T19:00:29.181Z","updatedAt":"2026-04-08T19:00:29.181Z","syncState":{"github":{"repoUrl":"https://github.com/myclaude-sh/offer-engineer-hormozi","retryCount":0,"lastSyncAt":"2026-04-08T19:00:36.113Z","commitSha":"8fee2fdf80e72ce2dd3cf60eb31e420cb48166c0","status":"synced"},"marketplace":{"retryCount":0,"lastSyncAt":"2026-04-08T19:00:36.113Z","status":"synced"},"npm":{"retryCount":1,"lastSyncAt":"2026-04-08T19:00:36.113Z","error":"NPM_AUTOMATION_TOKEN not configured","status":"failed"}},"authorUsername":"vinicius-caetano","stats":{"likes":0,"rating":0,"reviewsCount":0,"purchaseCount":0,"downloads":9},"trendingUpdatedAt":"2026-04-28T00:14:28.936Z","trendingScore":0.62,"thumbnailUrl":"/icons/minds.png"},{"id":"BXWJVVRnWiGGrWgPc1pV","slug":"copy-lancamento-vanilla","license":"Proprietary","category":"skills","price":0,"authorUsername":"lili","authorDisplayName":"Liliane Lopes Pereira","authorAvatar":"","fileName":"copy-lancamento-vanilla-1.0.0.zip","fileSize":13424,"status":"published","version":"1.0.0","source":"cli","mcsLevel":1,"language":"pt-BR","longDescription":"","installTarget":".claude/skills/copy-lancamento-vanilla/","compatibility":{"claudeCode":">=1.0.0"},"dependencies":{"myclaude":[]},"githubTopics":[],"npmPublish":false,"createdAt":"2026-04-08T02:01:14.929Z","publishedAt":"2026-04-08T02:01:14.929Z","description":"Gera copy de lançamento para anúncios, landing page e catálogo com a voz única da marca.","title":"Copy Lancamento","readme":"# Copy Lançamento\n\n> Copy de lançamento com a voz da marca— para a mulher que escolhe se cuidar.\n\n## O Que Faz\n\nGera copy completo e pronto para uso para o lançamento. A ferramenta carrega a voz, o posicionamento e as frases de ouro da marca — e entrega textos que soam como a autoridade não como qualquer outra marca de beleza.\n\nCada material gerado inclui os dois diferenciais que convertem: a evocação sensorial da fragrância gourmand e a resposta à principal objeção da cliente (\"vai fixar?\"). O copy fala para mulheres que nunca compraram da marca — a porta de entrada para novas clientes.\n\n**Gera 3 tipos de material:**\n- **Copy para anúncios** — textos para Instagram e TikTok que param o scroll e convertem\n- **Texto de landing page** — página completa com narrative que transforma visita em compra\n- **Descrição para catálogo** — texto de produto para loja virtual, Shopee, ou qualquer plataforma\n\n## Instalação\n\n```bash\nmyclaude install copy-lancamento-vanilla\n```\n\nApós instalar, a skill fica disponível na pasta `.claude/skills/copy-lancamento-vanilla/`.\nInvoque com `/copy-lancamento-vanilla` em qualquer sessão do Claude Code.\n\n## Como Usar\n\nDigite `/copy-lancamento` seguido do tipo de material que você precisa. A ferramenta pergunta o que falta e entrega o copy pronto.\n\nNão precisa de nenhuma configuração prévia — ela já carrega a voz da marca, as frases de ouro e as regras de tom automaticamente.\n\n### Exemplos\n\n```\n/copy-lancamento anúncio Instagram\n```\n\n```\n/copy-lancamento-landing page\n```\n\n```\n/copy-lancamento-descrição catálogo\n```\n\n## Requisitos\n\n- Claude Code >= 1.0.0\n- Conhecimento do produto preenchido em `references/domain-knowledge.md`\n\n---\n\n**Versão:** 1.0.0 | **Licença:** Proprietary | **Criadora:** Liliane · \n\n[](https://myclaude.sh/quality) [](https://myclaude.sh/p/copy-lancamento-vanilla)\n\nValidado pelo [MyClaude Studio Engine](https://myclaude.sh/studio) | [Explorar marketplace](https://myclaude.sh/explore)\n\n---\n\n[](https://myclaude.sh/quality)\n[](https://myclaude.sh/p/copy-lancamento-vanilla)\n\nBuilt with MyClaude Studio Engine\n","tags":["marketing","beauty","copywriting","e-commerce","pt-BR"],"updatedAt":"2026-04-09T22:25:55.193Z","stats":{"likes":0,"rating":0,"reviewsCount":0,"purchaseCount":0,"downloads":8},"trendingUpdatedAt":"2026-04-28T00:14:28.936Z","trendingScore":0.62,"thumbnailUrl":"/icons/skills.png"},{"id":"QlS6TTbkQBN22NBdXCXF","title":"Cdc Brasil Agente","slug":"cdc-brasil-agente","description":"Especialista em Código de Defesa do Consumidor brasileiro. Analisa situações relatadas, identifica artigos violados, penalidades aplicáveis e orienta profissionalmente sobre as melhores ações a tomar.","readme":"# CDC Brasil — Agente Especialista em Defesa do Consumidor\n\n> Descreva qualquer problema de consumo em linguagem natural. O agente identifica os artigos do CDC violados, cita jurisprudência real do STJ, informa seus direitos e prazos, e orienta com ações concretas — do SAC ao JEC.\n\n---\n\n## O que este agente faz\n\nVocê não precisa saber direito para usar. Só precisa descrever o que aconteceu.\n\nO agente vai:\n\n1. **Classificar** o tipo de violação (vício do produto, cobrança indevida, prática abusiva, etc.)\n2. **Citar** os artigos do CDC aplicáveis — com número, ementa e análise do seu caso\n3. **Informar** seus direitos específicos: o que pode exigir, em que prazo\n4. **Alertar** sobre armadilhas comuns que fazem o consumidor perder direitos\n5. **Recomendar** o melhor canal de ação — na ordem certa, não na ordem mais burocrática\n6. **Sinalizar** o nível de certeza jurídica de cada orientação (CONSOLIDADO / PREDOMINANTE / CONTROVERTIDO)\n\n---\n\n## Install\n\n```bash\nmyclaude install cdc-brasil-agente\n```\n\n---\n\n## Como usar\n\n### Formato básico\n\n```\n@cdc-brasil-agente [descrição da sua situação]\n```\n\nQuanto mais detalhes você der, mais precisa será a análise. O agente vai perguntar o que estiver faltando antes de responder.\n\n---\n\n## Exemplos de uso real\n\n### Produto com defeito\n\n```\n@cdc-brasil-agente Comprei uma geladeira há 3 meses. Parou de gelar na semana passada.\nLevei na assistência técnica autorizada — disseram que é defeito de fábrica no compressor.\nA loja diz que o prazo de troca já passou e que tenho que esperar o reparo, sem prazo definido.\nTenho nota fiscal.\n```\n\n**O que o agente entrega:**\n- Classificação: vício do produto durável (Art. 18 CDC)\n- Prazo de reclamação: 90 dias — ainda está no prazo\n- Direitos: substituição, restituição integral ou abatimento (sua escolha — não da loja)\n- Defeito em produto essencial: pode acionar alternativas imediatamente, sem esperar 30 dias\n- Ação: e-mail citando Art. 18 → consumidor.gov.br → JEC se recusar\n\n---\n\n### Cobrança indevida\n\n```\n@cdc-brasil-agente Meu banco cobra R$ 34,90/mês de \"seguro residencial\" há 6 meses.\nNunca contratei esse serviço. Já liguei duas vezes e disseram que \"consta no sistema\".\nJá paguei R$ 209,40 no total.\n```\n\n**O que o agente entrega:**\n- Classificação: serviço não solicitado + cobrança indevida (Arts. 39, III e 42 CDC)\n- Direito: devolução em **dobro** — R$ 418,80 corrigidos\n- Ônus da prova: é do banco provar que você contratou, não você provar que não contratou\n- Infração regulatória: Resolução BCB 96/2021 (consentimento expresso obrigatório)\n- Ação: SAC + BACEN + JEC\n\n---\n\n### Plano de saúde nega procedimento\n\n```\n@cdc-brasil-agente Meu médico solicitou ressonância magnética de urgência.\nO plano negou dizendo que \"não está coberto\". Meu plano tem 4 anos\ne a ressonância está no rol da ANS.\n```\n\n**O que o agente entrega:**\n- Classificação: serviço com vício + prática abusiva (Arts. 20, 39 CDC + regulação ANS)\n- Direito: autorização obrigatória em até 12 horas para urgência (RN ANS 259/2011)\n- Ação imediata: NIP na ANS — resposta em 5 dias úteis, muitas operadoras revertem para evitar autuação\n- Se precisar pagar do bolso: reembolso + dano moral (R$ 10.000–30.000 de referência)\n\n---\n\n### Exchange de criptomoeda — fraude com 2FA\n\n```\n@cdc-brasil-agente Tinha R$ 18.000 em Bitcoin numa exchange brasileira.\nUsava 2FA. Mesmo assim alguém transferiu tudo. A exchange diz que\n\"a transferência passou pelo 2FA então foi o próprio usuário\".\n```\n\n**O que o agente entrega:**\n- STJ REsp 2.104.122 (junho/2025): exchanges respondem objetivamente por fraudes — o argumento \"passou pelo 2FA = foi o usuário\" é expressamente afastado\n- Distinção fortuito interno (responde) vs. externo (não responde)\n- Tutela cautelar: como pedir bloqueio dos ativos antes do julgamento\n- Ação: JEC se valor ≤ R$ 60.720 (40 SM 2026) ou Vara Cível\n\n---\n\n### Produto falsificado no marketplace\n\n```\n@cdc-brasil-agente Comprei um tênis Nike por R$ 580 no Mercado Livre.\nVeio falsificado. O vendedor sumiu e o perfil foi desativado.\nPosso processar só o Mercado Livre?\n```\n\n**O que o agente entrega:**\n- Sim — STJ REsp 1.930.256: marketplace responde solidariamente por produtos de terceiros\n- Fundamento: Art. 7º § único + Art. 14 CDC (falha no serviço de intermediação)\n- Não precisa identificar o vendedor para processar\n- Dano moral: R$ 1.500–4.000 de referência + reembolso integral\n\n---\n\n### Financiamento com CET diferente do anunciado\n\n```\n@cdc-brasil-agente Financiei R$ 40.000 em 60 parcelas. O banco anunciava CET de 1,1% ao mês.\nNo contrato estava 1,85% ao mês. Só percebi agora comparando simulações.\nO banco diz que eu assinei o contrato.\n```\n\n**O que o agente entrega:**\n- Violações: Art. 30 CDC (oferta vincula) + Art. 46 CDC + Res. CMN 3.517/2007\n- Cálculo do dano: fórmula Price aplicada — diferença entre os dois CET em 60 parcelas\n- Argumento \"assinou o contrato\" não exime se o CET real estava obscurecido\n- Infração regulatória ao BACEN — denunciável em bcb.gov.br/meubc\n- Opções: revisão contratual ou rescisão — o agente orienta qual é mais vantajosa\n\n---\n\n### Imóvel com vício estrutural descoberto 3 anos depois\n\n```\n@cdc-brasil-agente Comprei apartamento em 2021. Assinei a vistoria sem ressalvas.\nEm 2024 apareceram rachaduras na laje e infiltrações. Laudo de engenheiro atesta\nfalha estrutural na impermeabilização — defeito de execução da obra.\nO prazo de 90 dias do CDC já passou — ainda tenho direito?\n```\n\n**O que o agente entrega:**\n- Sim — Art. 618 CC: garantia legal irrenunciável de **5 anos** para solidez e segurança da obra\n- A assinatura da vistoria não afasta o Art. 618 — norma de ordem pública\n- NBR 15.575: 5 anos para impermeabilização como padrão técnico obrigatório\n- Ainda dentro do prazo (2021 → 2026 = 5 anos)\n- Foro: Vara Cível (valor provavelmente acima de 40 SM)\n\n---\n\n## Casos suportados\n\n| Tipo de problema | Artigos principais |\n|-----------------|-------------------|\n| Produto com defeito (físico ou online) | Arts. 18-25 CDC |\n| Serviço abaixo do contratado | Arts. 20-25 CDC |\n| Acidente de consumo com dano | Arts. 12-17 CDC |\n| Direito de arrependimento (7 dias, compras online) | Art. 49 CDC |\n| Cobrança indevida / serviço não solicitado | Arts. 39, III e 42 CDC |\n| Negativação indevida no SPC/Serasa | Art. 43 CDC |\n| Publicidade enganosa / oferta não cumprida | Arts. 30, 35, 37 CDC |\n| Práticas abusivas (venda casada, pressão, vencidos) | Art. 39 CDC |\n| Contratos com cláusulas abusivas | Arts. 46, 47, 51 CDC |\n| Planos de saúde (+ regulação ANS) | Súmula 608 STJ + RN ANS |\n| Planos odontológicos (+ RN ANS 100/2004) | CDC + regulação ANS |\n| Bancos e financeiras (+ regulação BACEN) | CDC + Res. BCB/CMN |\n| Telecomunicações (+ regulação Anatel) | CDC + Res. Anatel 589 |\n| Energia elétrica (+ regulação ANEEL) | CDC + regulação ANEEL |\n| Exchanges de criptomoeda | CDC + Lei 14.478/2022 + STJ 2025 |\n| Marketplace / produto de terceiro | Arts. 7º, 14 CDC + STJ 2024 |\n| Dark patterns em apps bancários | CDC + BCB 96/2021 |\n| Cancelamento impossível / design abusivo | CDC + Decreto 11.034/2022 |\n| Imóvel com vício construtivo | CDC + Art. 618 CC + NBR 15.575 |\n| Financiamento com CET divergente | CDC + Res. CMN 3.517/2007 |\n| Pacote de viagem cancelado | CDC + Lei 11.771/2008 |\n| Curso online / influenciador | CDC Arts. 3º, 7º § único |\n| Seguro negado (preexistência, exclusão) | CDC + Art. 47 + STJ |\n\n---\n\n## Caminhos de ação que o agente orienta\n\n| Canal | Quando usar | Prazo de resposta | Pode coagir pagamento? |\n|-------|-------------|-------------------|------------------------|\n| SAC da empresa | Primeiro contato — sempre | 5 dias úteis | Não |\n| consumidor.gov.br | Empresa cadastrada — gera prova oficial | 10 dias | Não |\n| PROCON estadual | Quer pressão administrativa e multa | Variável | **Não** — só multa |\n| Agência reguladora (Anatel, ANS, BACEN…) | Serviços regulados | Variável | Não (indiretamente) |\n| JEC — Juizado Especial Cível | Quer dinheiro de volta ou indenização | Audiência em 15–30 dias | **Sim** |\n| Justiça Comum | Acima de 40 SM ou alta complexidade | Meses a anos | **Sim** |\n\n**Regra de ouro:** consumidor.gov.br → JEC. Não PROCON → JEC. PROCON não condena ninguém a pagar.\n\n---\n\n## Fontes verificadas — sem alucinação\n\nO agente **nunca inventa** artigos, processos ou datas. Quando a base local não cobre o caso, ele busca em fontes oficiais via WebSearch + WebFetch e só cita o que foi confirmado:\n\n```\n[FONTE VERIFICADA] STJ, REsp 2.104.122, 3ª Turma, jun/2025\n🔗 https://stj.jus.br/...\nTese: exchanges respondem objetivamente por fraudes\n```\n\nSe não encontrar fonte verificável, diz explicitamente — nunca preenche com suposição.\n\n**Fontes priorizadas:** stj.jus.br · planalto.gov.br · ans.gov.br · bcb.gov.br · anatel.gov.br · senacon.gov.br\n\n---\n\n## Jurisprudência incorporada\n\nO agente cita julgados reais, não genéricos:\n\n- **STJ REsp 2.104.122 (jun/2025)** — exchanges respondem objetivamente por fraudes; Súmula 479 por analogia\n- **STJ REsp 1.930.256 (2022–2024)** — marketplaces respondem solidariamente por produtos falsificados de terceiros\n- **STJ Tema 1.069 (2022)** — rol ANS taxativo com mitigação para evidência científica\n- **Súmula 608 STJ** — CDC aplica-se a planos de saúde\n- **Súmula 479 STJ** — instituições financeiras respondem por fraudes de terceiros (fortuito interno)\n- **Súmula 543 STJ** — restituição de parcelas em rescisão de imóvel na planta\n- **Wepink/Virgínia Fonseca (Goiânia, 2025)** — tutela concedida, ACP com dano moral coletivo de R$ 5M\n- **Art. 618 CC + NBR 15.575** — garantia de 5 anos para vícios construtivos em imóveis\n\n---\n\n## O que o agente NÃO cobre\n\n- Situações fora do Brasil (CDC não se aplica)\n- Relações de trabalho — regidas pela CLT\n- Relações entre empresas (B2B) sem vulnerabilidade comprovada\n- Danos corporais graves ou questões criminais — requer advogado presencialmente\n- Inventário, herança e divórcio — outros ramos do direito **(exceto acesso a criptoativos por espólio — coberto)**\n- **Não substitui consultoria jurídica** para casos de alto valor ou grande complexidade\n\n---\n\n## Dicas para melhores resultados\n\n1. **Dê o máximo de contexto:** nome da empresa, valor envolvido, data do problema, o que já tentou\n2. **Mencione documentos que tem:** nota fiscal, prints, protocolos, laudos — o agente orienta como usá-los\n3. **Pergunte sobre prazos primeiro** se não tiver certeza se ainda está no prazo\n4. **Use para preparar sua argumentação** antes de ligar para o SAC ou registrar no consumidor.gov.br\n5. **Para casos acima de R$ 10.000**, use o agente para entender seus direitos e depois consulte um advogado para a estratégia processual\n\n---\n\n## Requirements\n\n- Claude Code >= 1.0.0\n- WebSearch habilitado (para verificação de jurisprudência atualizada quando necessário)\n\n---\n\n[](https://myclaude.sh/quality)\n[](https://myclaude.sh/p/cdc-brasil-agente)\n\nBuilt with MyClaude Studio Engine\n","license":"MIT","category":"agents","price":0,"authorUsername":"lacsociety","authorDisplayName":"LAC-SOCIETY","authorAvatar":"https://lh3.googleusercontent.com/a/ACg8ocI73l3qQ6Q-qc8Qd2WOtmJ05Fjex-eBNkAbIJNVfrUUz0WbGms5aQ=s96-c","fileName":"cdc-brasil-agente-1.0.0.zip","fileSize":55319,"status":"published","version":"1.0.0","source":"cli","mcsLevel":1,"language":"pt-BR","longDescription":"","installTarget":".claude/skills/cdc-brasil-agente/","compatibility":{"claudeCode":">=1.0.0"},"dependencies":{"myclaude":[]},"githubTopics":[],"npmPublish":false,"tags":["direito","consumidor","brasil","cdc","juridico","lei"],"createdAt":"2026-04-07T23:28:44.084Z","publishedAt":"2026-04-07T23:28:44.084Z","updatedAt":"2026-04-07T23:28:44.084Z","stats":{"rating":0,"reviewsCount":0,"purchaseCount":0,"likes":2,"downloads":10},"trendingUpdatedAt":"2026-04-29T00:14:26.117Z","trendingScore":1.65,"thumbnailUrl":"/icons/agents.png"}],"total":20}