Quick Start

Your first 5 minutes with Coding Friend — learn the core workflow.

Coding Friend enforces a disciplined engineering workflow. After installing the plugin, here are the steps to get started.

0. Scan your project into memory

# Enter claude code then run
/cf-scan

This will scan your project and extract the knowledge into the memory system. Read more about /cf-scan for more details.

1. Plan Your Work

/cf-plan Build a user authentication system

# Or even without /cf-plan (not recommended)
Build a user authentication system

Coding Friend explores your codebase, identifies existing patterns, and writes a structured implementation plan. The plan is saved to docs/plans/ by default. Check /cf-plan for more details.

2. Write Code with TDD

Simply describe what you want to build. The cf-tdd skill activates automatically and enforces:

  1. RED — Write a failing test first
  2. GREEN — Write minimal code to pass
  3. REFACTOR — Clean up while tests stay green

3. Review Your Code

/cf-review src/auth/

A multi-layer code review runs in a separate subagent, checking security, performance, style, and test coverage. Check /cf-review for more details.

4. Fix Bugs

/cf-fix Login fails with 401 error

A bug fix workflow with problem verification. Check /cf-fix for more details.

5. Optimize Code

/cf-optimize getUserById query

A structured optimization workflow with before/after measurement. This skill also auto-invokes when you mention performance issues — just say "this endpoint is slow" and it activates. Check /cf-optimize for more details.

6. Commit

/cf-commit Add user authentication

A smart conventional commit workflow with diff analysis. You should run it after you have written the code and verified that it works. Check /cf-commit for more details.

7. Ship It

/cf-ship Add user authentication

One command to verify all tests pass, create a conventional commit, push, and open a pull request. Check /cf-ship for more details.

8. Research

/cf-research GraphQL vs REST for mobile APIs

A deep research workflow with web search. The research is saved to docs/research/ by default. Check /cf-research for more details.

9. Capture Knowledge

/cf-remember auth flow

Capture project knowledge for the AI to use in future sessions. The knowledge is saved to docs/memory/ by default. Check /cf-remember for more details.

10. Learn From Your Work

/cf-learn

Extract what you learned during the session into structured docs. Use /cf-teach for a deeper, conversational breakdown of what happened and why. Host them locally with cf host or integrate with other LLM clients via cf mcp. Check /cf-learn for more details.

Learning Notes hosted locally

Use cf host to run a local website at http://localhost:3333

11. Ask Questions

/cf-ask How does the auth middleware work?

Ask questions about your codebase. The question is saved to docs/memory/ by default. Check /cf-ask for more details.

12. Save Session for Another Machine

/cf-session refactor auth flow

Save the current conversation to docs/sessions/ so you can resume it on another machine with cf session load + claude --resume. Check /cf-session for more details.

Tips

  • Use /cf-help to see all available commands or ask about skills, agents, or workflows (e.g. "/cf-help what skills are available?") or just ask naturally about Coding Friend (e.g. "how does cf-plan work?")
  • Skills like cf-tdd, cf-verification, and cf-optimize activate automatically — no slash needed