cm-autopilot
Easy-to-use conversational CLI (Claude Code style) for non-technical users to spawn parallel AI tasks supervised by a visual web…
Use when implementing any feature or bugfix. Routes to the core Red-Green-Refactor loop, test quality guidance, rationalization handling, examples, or stuck-state recovery.
Claude Code
$ npx -y skills add tody-agent/codymaster --skill cm-tdd --agent claude-code
Codex
$ npx skills add tody-agent/codymaster --skill cm-tdd -a codex -y
Cursor
$ npx skills add tody-agent/codymaster --skill cm-tdd -a cursor -y
Gemini CLI
$ npx skills add tody-agent/codymaster --skill cm-tdd -a gemini-cli -y
GitHub Copilot
$ npx skills add tody-agent/codymaster --skill cm-tdd -a github-copilot -y
OpenCode
$ npx skills add tody-agent/codymaster --skill cm-tdd -a opencode -y
Windsurf
$ npx skills add tody-agent/codymaster --skill cm-tdd -a windsurf -y
name: cm-tdd description: Use when implementing any feature or bugfix. Routes to the core Red-Green-Refactor loop, test quality guidance, rationalization handling, examples, or stuck-state recovery. token_budget: 1500 token_core: 380 token_refs: red-green-refactor: 620 test-quality: 360 rationalizations: 520 bugfix-example: 340 stuck-debugging: 260 compressed: true deprecated: false
NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST
Need to execute the normal TDD loop? └─ YES → Red-Green-Refactor Need help designing or reviewing test quality? └─ YES → Test Quality Need to counter "skip TDD" rationalizations? └─ YES → Rationalizations Need a worked bug-fix example? └─ YES → Bugfix Example Are you blocked or unsure how to continue? └─ YES → Stuck / Debugging
| Need | Summary | Load | |---|---|---| | Normal execution | core TDD loop and verification | `references/red-green-refactor.md` | | Test quality | what good tests look like | `references/test-quality.md` | | Reinforcement | anti-rationalization guidance | `references/rationalizations.md` | | Example | concrete bug-fix walkthrough | `references/bugfix-example.md` | | Recovery | how to proceed when stuck | `references/stuck-debugging.md` |
**Write the failing test first. Pass it minimally. Refactor only after green.**
"I can't write code. But in 6 months, I shipped 12 real products using AI. CodyMaster is everything I learned — so you don't have to repeat my mistakes." — Tody Le, Head of Product, Creator of CodyMaster 50+ skills. One install.
Easy-to-use conversational CLI (Claude Code style) for non-technical users to spawn parallel AI tasks supervised by a visual web…
Strategic analysis gate for existing products — multi-dimensional evaluation (tech, product, design, business) using Design…
Fallback local Playwright daemon for real-browser visual QA / screenshots / smoke. Use ONLY when the host platform has no native…
Code hygiene gate — detect and eliminate dead code, duplicates, naming mess, and code smells. TRIZ-powered. Run after features,…
Full review lifecycle — request reviews, handle feedback with technical rigor, and complete branch integration. Use when…
Unified code intelligence — routes to Skeleton Index, CodeGraph, Architecture Diagram, or Smart Context Builder based on task…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.