Complete guide to vibe coding with the CodyMaster skill kit โ from idea to deploy. Covers the full workflow, skills used at each phase, and common use cases. Read this first if you are new; reference it whenever you're unsure which skill to invoke.
From cmnpx claudepluginhub tody-agent/codymaster --plugin cmThis skill uses the workspace's default tool permissions.
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Implements distributed tracing with Jaeger/Tempo for microservices, including Kubernetes/Docker setup and OpenTelemetry instrumentation (Python/Flask). Use for debugging latency, dependencies, and request flows.
The CodyMaster (CM) kit transforms ideas into production code through 13 specialized, optimized skills. This workflow ensures the highest quality, absolute security, and maximum execution speed.
๐ก Idea โ ๐ Analysis โ ๐ Design โ ๐งช Test-first (TDD) โ ๐ป Code โ โ
Verify โ ๐ Deploy โ ๐ Iterate
Rule #1: Always verify identity before performing any action that could change the project state.
cm-identity-guardnode check-identity.js (or similar script) to verify GitHub/Cloudflare/Supabase accounts.For large codebases, establish the memory foundation before planning.
cm-codeintell + cm-dockit + cm-deep-search + cm-notebooklmcm-codeintell to build the Skeleton Index.cm-dockit.cm-deep-search (qmd).cm-notebooklm.For complex initiatives and enhancements on existing products.
cm-brainstorm-idea + cm-codeintellcm-codeintell).openspec/changes/[initiative]/proposal.md โ qualified problem + recommended option โ passes to cm-planning.Understand the 'Job to be Done' (JTBD) and architecture before writing code.
cm-planning (Combines brainstorming + writing-plans)openspec/changes/[init]/design.md and tasks.md).Turn the plan into actual source code safely.
cm-tdd: Red-Green-Refactor cycle. No production code without a failing test first.cm-execution: Execute plans intelligently (Manual, Parallel, or Subagent mode).cm-project-bootstrap: For new projects โ setup repo, i18n, SEO, and deploy pipeline from Day 0.cm-git-worktrees: Isolate different work items to avoid state mixing.Prove with evidence, not words.
cm-quality-gate: Setup test infrastructure (test:gate) and verify output before claiming "done".cm-debugging: When tests fail, use systematic investigation framework to find root cause.cm-code-review: Professional request and feedback review process.Ship code without fear of incidents.
cm-safe-deploy: Run 8-gate pipeline (Secret โ Syntax โ Test โ Build โ Deploy โ Smoke).cm-safe-i18n: Translate and synchronize languages consistently across the entire project.cm-terminal: Monitor all terminal commands to detect errors immediately.| Skill | Primary Function |
|---|---|
cm-tdd | Strict Red-Green-Refactor TDD โ no code without failing test first. |
cm-debugging | Systematic 5-phase error investigation (root cause first). |
cm-quality-gate | 6-gate verification: static analysis โ blind review โ ship. |
cm-test-gate | Setup 4-layer test infrastructure (unit โ integration โ e2e โ security). |
cm-code-review | Manage PR lifecycle: request โ receive feedback โ complete branch. |
cm-codeintell | AST knowledge graph + architecture diagrams + smart context (30% fewer tokens). |
| Skill | Primary Function |
|---|---|
cm-safe-deploy | Multi-gate deploy pipeline with rollback strategy. |
cm-identity-guard | Verify account before push/deploy to prevent wrong-project incidents. |
cm-git-worktrees | Isolate feature work in separate worktrees โ no state mixing. |
cm-terminal | Safe terminal execution with progress logging and error capture. |
cm-secret-shield | Defense-in-depth: pre-commit hooks, repo scanning, token lifecycle. |
cm-safe-i18n | Safe multi-language management with multi-pass batching and 8-gate audit. |
| Skill | Primary Function |
|---|---|
cm-project-bootstrap | Full project setup: design system โ CI โ staging โ deploy from Day 0. |
cm-brainstorm-idea | Strategic analysis gate: 9 Windows + Double Diamond โ 2-3 qualified options. |
cm-planning | Brainstorm intent โ write implementation plan โ coordinate execution. |
cm-ux-master | 48 UX Laws + 37 Design Tests + Figma/Stitch + BM25 semantic design search. |
cm-ui-preview | Live UI concept generation via Google Stitch or Pencil MCP. |
cm-dockit | Generate complete knowledge bases, SOPs, and API docs from codebase. |
cm-readit | Web audio engine: TTS reader, MP3 audio player, Voice CRO trigger system. |
cm-jtbd | JTBD customer discovery: Switch Interview โ Canvas โ Opportunity Scoring. |
| Skill | Primary Function |
|---|---|
cm-content-factory | Self-learning content engine: research โ generate โ audit โ deploy. |
cm-ads-tracker | Conversion tracking setup: GTM, Meta CAPI, TikTok, Google Ads. |
cm-cro-methodology | CRO audit: funnel mapping โ persuasion assets โ A/B test design. |
| Skill | Primary Function |
|---|---|
cm-execution | Execute plans: Manual / Parallel / Subagent / RARV batch modes. |
cm-continuity | Working memory protocol: read at session start, update at session end. |
cm-skill-mastery | Meta-skill: when to invoke which skill, how to create new skills. |
cm-skill-chain | Compose skills into automated multi-step pipelines (5 built-in chains). |
cm-skill-index | Progressive disclosure index โ 90% token savings on skill discovery. |
cm-deep-search | Semantic search via qmd for large codebases (>200 src / >50 docs files). |
cm-notebooklm | Cloud Brain sync โ cross-machine knowledge persistence via NotebookLM. |
cm-how-it-work | Full vibe coding guide โ phases, skills per phase, use cases. |
| Skill | Primary Function |
|---|---|
cm-start | Orchestrate full workflow from objective to production code. |
cm-dashboard | Render Kanban board from cm-tasks.json โ visual status overview. |
cm-status | Ultra-concise 1-2 sentence progress summary (what's done, what's next). |
The kit supports autonomous mode by applying the Reason โ Act โ Reflect โ Verify (RARV) loop.
/cm-start [objective]: Start work. The system will automatically initialize the OpenSpec structure (openspec/changes/[objective]/), break down tasks into tasks.md and sync with cm-tasks.json, launch the tracking interface, and autonomously use CM skills to complete them./cm-dashboard: Open the visual tracking Dashboard in browser (shows Kanban board, reasoning log, and progress)./cm-status: View quick progress summary in Terminal.There are 2 ways to use CodyMaster: Fully autonomous (Via Workflows) or Manual skill activation (Via Prompting).
Best way to delegate complete work packages.
/cm-start "Build user management feature with list screen and CRUD form"cm-tdd and cm-quality-gate for each task until done.Bugs need close supervision and AI should not blindly change too much code.
cm-debugging to find Root Cause.cm-tdd to write test reproducing the bug and fix it.cm-safe-deploy to ship code safely.Establish a solid foundation to avoid technical debt later.
cm-identity-guard to ensure correct account, then run cm-project-bootstrap to setup a new Next.js project."Tedious work that's error-prone if AI loses focus.
cm-safe-i18n to extract all hardcoded text in /components directory to vi.json and en.json files."cm-identity-guard) before push/deploy.cm-tdd).cm-safe-deploy).cm-secret-shield).cm-execution).cm-continuity).