📖 Operational Guide

The SkillPlaybook

"I want to do X — which skills do I use?" This page answers that question for every scenario you'll face.

QUICK START

Pick Your Goal

Find your goal below. Each card shows exactly which skills to use.

🚀

"I want to build a new project"

Start from zero: create repo, set up CI/CD, design system, and deploy — all in one session.

cm-identity-guard cm-project-bootstrap cm-planning cm-tdd cm-safe-deploy
🐛

"Something is broken!"

Find the real cause first, write a test to prove it, fix it, then deploy safely.

cm-debugging cm-tdd cm-safe-deploy
🎨

"I want to improve the UI"

Analyze what to change, design with proven UX rules, preview the result, then build it.

cm-brainstorm-idea cm-ux-master cm-ui-preview cm-planning
🌍

"I need multi-language support"

Extract text, translate in batches, and auto-audit to catch errors before they go live.

cm-safe-i18n
📈

"I need content + tracking"

Generate SEO articles, set up ad pixels (Meta, TikTok, Google), and measure what works.

cm-content-factory cm-ads-tracker cro-methodology
📚

"I need documentation"

Scan your codebase and auto-generate docs, SOPs, and API references.

cm-dockit

STEP BY STEP

How Each Workflow Works

Click any scenario to see the exact steps. Follow them in order.

🚀

Build a New Project from Scratch

Start from nothing. In 1-2 chat sessions you'll have a live project with tests, CI, and auto-deploy.

1
cm-identity-guard
Verify correct GitHub/Cloudflare account
2
cm-project-bootstrap
Scaffold repo, CI, deploy pipeline
3
cm-planning
Write implementation plan for feature
4
cm-tdd
Red → Green → Refactor per feature
5
cm-safe-deploy
8-gate pipeline to production
🐛

Fix a Production Bug

Don't let AI guess randomly. This workflow finds the real cause first, proving it with a test before fixing anything.

1
cm-debugging
5-phase root cause analysis
2
cm-tdd
Write regression test, then fix
3
cm-safe-deploy
Deploy hotfix with rollback
🌍

Add Multi-Language Support

One wrong translation key = broken page. This skill extracts, translates, and double-checks everything automatically.

1
cm-safe-i18n
Extract hardcoded strings → translate → audit → deploy
📈

Launch a Content / Marketing Campaign

Need blog articles + ad tracking? This chain auto-writes, quality-checks, deploys, and sets up tracking pixels.

1
cm-content-factory
Research → Generate → Audit → Deploy
2
cm-ads-tracker
FB Pixel, TikTok, Google Ads setup
3
cro-methodology
Funnel audit + A/B test design
🎨

Redesign or Enhance Existing UI

Don't jump straight to code. Analyze what to change, design it properly, preview it visually, then plan the build.

1
cm-brainstorm-idea
9 Windows + Double Diamond analysis
2
cm-ux-master
Design system + 48 UX Laws
3
cm-ui-preview
Visual preview via Stitch/Pencil
4
cm-planning
Write implementation plan

⚠️ TROUBLESHOOTING

When Things Don't Go as Planned

Hit a wall? Here's the fix for every common problem.

Context Lost

AI forgot what it was doing

Long chats fill up the AI's memory. It "forgets" earlier instructions and starts going off track.

cm-continuity
Saves context to a file. AI reads it at the start of every session — never loses track again.
Wrong Direction

Plan turns out to be wrong

You're halfway done and realize the approach won't work, or requirements changed.

cm-planning
Go back and update the plan. It's cheaper to rewrite a plan than to rewrite code.
Stuck in Loops

AI keeps "fixing" but nothing works

The AI guesses randomly instead of understanding why it's broken. Each attempt makes it worse.

cm-debugging
Forces AI to investigate the root cause first — no code changes until the "why" is clear.
Wrong Account

Code pushed to wrong repo

Multiple GitHub/Cloudflare accounts? One wrong push = your code ends up in someone else's project.

cm-identity-guard
Checks which account is active before every push. Blocks the action if it's the wrong one.
Too Many Files

AI only sees part of the project

Large codebase (200+ files). AI reads a few files but misses the rest — changes break things it never saw.

cm-deep-search
Adds semantic search so AI can find relevant code across the entire project instantly.
Leaked Secrets

API keys committed to Git

AI puts passwords or API keys directly in code. Push to a public repo = instant security breach.

cm-secret-shield
Scans every commit automatically. Blocks the push if any secret is detected.

🏆 GOLDEN RULES

The 9 Non-Negotiable Rules

Follow these and your AI-assisted development will be predictable, safe, and fast.

1

Identity First.Verify account (cm-identity-guard) before push/deploy. Every. Single. Time.

2

Design Before Code. Always have an approved plan before typing. Use cm-planning.

3

i18n Day 0. Always consider multi-language from the brainstorm step, not as an afterthought.

4

Test Before Code. RED → GREEN → REFACTOR. No exceptions. cm-tdd enforces this.

5

Evidence Over Claims. Only trust terminal/test output, not AI "saying" it's done.

6

Deploy via Gates. 8 gates must pass sequentially. Any fail = STOP. cm-safe-deploy.

7

Safe Secrets. Never commit secrets. Pre-commit hooks protect every push. cm-secret-shield.

8

Parallel Power. Use parallel execution for i18n or multi-bug fixes. cm-execution.

9

Working Memory. Read CONTINUITY.md at session start, update at end. cm-continuity.

Ready to run the playbook?

Install in 30 seconds. Follow the playbook. Ship with confidence.

Get Started → CLI Power Users →
Have questions? Check the FAQ →