Skills Library
Quick Reference
- Total Skills: 60 across 7 domains
- Format: Universal — works on any AI coding platform
- Open Source: Full SKILL.md visible for every skill
- License: MIT
Cody Master skills are the instructions that turn AI agents into disciplined engineers. Each skill is a SKILL.md file with structured protocols any AI agent can follow. Browse them all below — nothing is hidden.
🔧 Engineering
Skills that enforce code quality, testing, and review processes.
| Skill | Description | Full Docs |
|---|---|---|
| cm-tdd | Red-Green-Refactor cycle — no production code without a failing test first. | View → |
| cm-debugging | Systematic 5-phase root cause investigation before any fix. | View → |
| cm-quality-gate | Evidence-based verification: test gates, blind review, anti-sycophancy, security scan. | View → |
| cm-test-gate | Setup 4-layer test infrastructure (unit → integration → e2e → security scan) for any stack. | View → |
| cm-code-review | Full PR lifecycle — request reviews, handle feedback, complete branch integration. | View → |
| cm-codeintell | 4-layer code intelligence: Skeleton Index (zero-dep, <4s) + AST graph + architecture diagrams + smart context. | View → |
| cm-clean-code | Code hygiene gate — detect and eliminate dead code, duplicates, naming mess, and code smells. | View → |
| cm-security-gate | Pre-production vulnerability audit. Run scans using Snyk and set up automated GitHub security checks. | View → |
⚙️ Operations
Skills that ensure safe deployment, isolation, and secret management.
| Skill | Description | Full Docs |
|---|---|---|
| cm-safe-deploy | Multi-gate deploy pipeline: secret scan → syntax → test → build → deploy → smoke test. | View → |
| cm-identity-guard | Verify project identity before push, Cloudflare, or Supabase operations. Prevents wrong-account deploys. | View → |
| cm-git-worktrees | Isolated git worktrees for parallel feature work — smart directory selection and safety checks. | View → |
| cm-terminal | Safe terminal protocol — progress logging, output reading, error-stop. | View → |
| cm-secret-shield | Defense-in-depth: pre-commit hooks (Gitleaks), repo-wide scan, token lifecycle management. | View → |
| cm-safe-i18n | Mass i18n conversion — multi-pass batching, parallel dispatch, 8 audit gates. Battle-tested. | View → |
| cm-google-form | Google App Script form-to-sheet integration with auto-retry, toast notifications, and Zalo/contact fallback. | View → |
🎨 Product
Skills for planning, design, documentation, and bootstrapping.
| Skill | Description | Full Docs |
|---|---|---|
| cm-brainstorm-idea | Strategic analysis gate: 9 Windows (TRIZ) + Double Diamond → 2-3 qualified options for existing products. | View → |
| cm-planning | Brainstorm intent → write implementation plan → coordinate execution. Required before complex tasks. | View → |
| cm-ux-master | Ultimate design intelligence: 48 UX Laws, 37 Design Tests, Stitch & Pencil.dev integration, BM25 search. | View → |
| cm-design-system | Manage, extract, and replicate UI design systems. Visual token harvesting from any URL. | View → |
| cm-ui-preview | AI-powered UI generation via Google Stitch & Pencil.dev MCP. Dual engine: quick concepts (Stitch) or precise control (Pencil). | View → |
| cm-dockit | Knowledge systematization engine — generates tech docs, SOPs, API references as VitePress or Markdown. | View → |
| cm-readit | Web audio engine: TTS reader (SpeechSynthesis), pre-recorded MP3 player, Voice CRO trigger system. | View → |
| cm-project-bootstrap | Full project setup from Day 0 — design system, CI, staging, i18n, SEO, AGENTS.md, 8-gate pipeline. | View → |
| cm-jtbd | Customer discovery via JTBD theory — Switch Interviews, JTBD Canvas, Opportunity Scoring. | View → |
📈 Growth
Skills for content creation, marketing, and conversion optimization.
| Skill | Description | Full Docs |
|---|---|---|
| cm-content-factory | Self-learning content engine: StoryBrand, Cialdini, SUCCESs, Hook Model, JTBD, CRO. Research → generate → audit → deploy. | View → |
| cm-ads-tracker | Complete conversion tracking: Facebook/Meta Pixel + CAPI, TikTok Pixel, Google Ads, GTM. | View → |
| cm-cro-methodology | CRO audit: funnel mapping → persuasion assets → objection handling → A/B test design. | View → |
| cm-booking-calendar | Booking & Calendar CRO Engine — Packages booking, scheduling, and Calendar integration into a revenue-boosting system. | View → |
| cm-growth-hacking | Growth Hacking Engine — Modular system for popups, lead capture, flash sales, surveys, re-engagement. | View → |
🎯 Orchestration
Skills that coordinate workflows, manage memory, and enable autonomous execution.
| Skill | Description | Full Docs |
|---|---|---|
| cm-execution | Execute plans in 4 modes: Manual / Parallel / Subagent / RARV batch. | View → |
| cm-continuity | Working memory protocol — 4-Tier Memory System, context persistence, learnings across sessions. | View → |
| cm-skill-chain | Compose skills into automated pipelines — 5 built-in chains (feature-dev, bug-fix, content-launch…). | View → |
| cm-skill-index | Progressive disclosure index — 90% token savings on skill discovery. Always loaded at session start. | View → |
| cm-skill-mastery | Meta-skill: when to invoke which skill, how to create new skills, skill discovery guide. | View → |
| cm-deep-search | Semantic search via qmd — BM25 + Vector + LLM re-ranking for large codebases (>200 src files). | View → |
| cm-how-it-work | Complete vibe coding guide — 6 phases, 60 skills, 9 golden rules. Read this first if you're new. | View → |
| cm-start | Start the full CM workflow from objective → plan → TDD implement → verify → done. | — |
| cm-dashboard | Render Kanban board from cm-tasks.json — visual TO DO / IN PROGRESS / DONE view. | — |
| cm-status | Ultra-concise 1-2 sentence progress: what's done, what's next, what's blocked. | — |
| cm-notebooklm | Cloud-based AI brain/soul engine. Stores valuable knowledge into NotebookLM for sync and recall. | View → |
| cm-reactor | Strategic codebase re-direction when requirements change, architecture doesn't fit, or tech debt blocks progress. | View → |
🤖 Automation & Frameworks
Skills that provide specialized automation for specific platforms or deployment processes.
| Skill | Description | Full Docs |
|---|---|---|
| cm-auto-publisher | Comprehensive publishing automation skill bridging AI agents to the Content Factory Router. | View → |
| cm-frappe-agent | Master Frappe Framework and ERPNext full-stack development. Build, upgrade, and maintain custom apps. | View → |
🧩 Specialized & Community Skills
Specialized skills for specific domains, platforms, or advanced research tasks.
| Skill | Description | Full Docs |
|---|---|---|
| skill-creator-ultra | Create new AI Skills from ideas or work processes. Smart interview + pattern detection. | View → |
| medical-research | Evidence-based medical writing protocol for OB/GYN research articles. | View → |
| mom-test | Customer discovery without leading questions. Discuss life, not ideas. | View → |
| pandasai-analytics | Natural language data analysis and visual reports for pandas DataFrames. | View → |
| release-it | Stability patterns: circuit breakers, bulkheads, timeouts, and retry logic. | View → |
| tailwind-mastery | Master Tailwind CSS utilities, responsive design, and accessibility patterns. | View → |
| vercel-best-practices | Next.js and React performance optimization guidelines from Vercel. | View → |
| web-design-guide | UI review for Web Interface Guidelines compliance and accessibility. | View → |
| marketplace-crawler | Automated marketplace report crawler for Shopee, Lazada, TikTok seller portals. | View → |
| vulnerability-scan | Comprehensive client-side injection assessment (XSS/HTML injection). | View → |
| boxme-local-dev | Environment setup for Boxme localized development (VN, TH, PH). | — |
| boxme-git-config | Git configuration management for multi-account environments. | — |
Creating Your Own Skills
Every skill follows the universal format:
yaml
---
name: cm-your-skill
description: "One line — when to activate this skill"
---
# Skill Name
## When to Use
[Trigger conditions — be specific]
## Procedure
[Step-by-step workflow]
## Output
[What this skill produces]
## Integration
| Skill | Relationship |
|-------|-------------|
| cm-xxx | UPSTREAM / DOWNSTREAM / COMPLEMENT |See cm-example for the complete template, and cm-skill-mastery for the meta-guide on skill creation and discovery.
Transparency
Every skill is fully open. Click "View →" to read the complete SKILL.md — nothing simplified, summarized, or hidden. The best way to trust AI automation is to see exactly what instructions the AI follows.