Claude Code Learning

## What is CLAUDE.md?

A shared knowledge repository for the team. When Claude makes mistakes,
add rules to prevent the same mistakes from recurring.

## Example

# Development Workflow

## Package Management
- **Always use `pnpm`** (`npm`, `yarn` prohibited)

## Coding Conventions
- Prefer `type`, avoid `interface`
- **Never use `enum`** → Use string literal unions

## Prohibited
- ❌ No console.log (use logger)
- ❌ No any type

## What are Slash Commands?

Execute repetitive daily tasks with `/command-name`.

## Command Location

.claude/commands/{command-name}.md

## PostToolUse Hook

Auto-formatting after code modification:

// .claude/settings.local.json
{
  "hooks": {
    "PostToolUse": [{
      "matcher": "Write|Edit",
      "hooks": [{
        "type": "command",
        "command": "pnpm format || true"
      }]
    }]
  }
}

## What are Sub-agents?

AI agents specialized for specific tasks.

## What are Skills?

Domain-specific expert context. Claude auto-references when working on related tasks.

## MCP Integration

Connect external tools (Slack, GitHub, Jira, etc.) via .mcp.json.

## PR Automation with GitHub Action

Mention @claude in PR comments to auto-update documentation.

## Team Rule Standardization

1. Manage CLAUDE.md with Git
2. Add rules during PR review
3. Gradually accumulate team knowledge

## Agent Teams (v1.5.1)

Parallel PDCA execution with multiple AI agents working simultaneously.

Requirements:
  CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1

Usage:
  /pdca team {feature}     Start team mode
  /pdca team status        Check teammate progress
  /pdca team cleanup       End team session

Team composition by level:
  Dynamic:    2 teammates (developer, qa)
  Enterprise: 4 teammates (architect, developer, qa, reviewer)

## What is PDCA?

Document-driven development methodology.

Plan → Design → Do → Check → Act

## Folder Structure

docs/
├── 01-plan/      # Planning
├── 02-design/    # Design
├── 03-analysis/  # Analysis
└── 04-report/    # Reports

## Learn More

Use /pdca skill to learn PDCA methodology.

## Output Styles

Customize how Claude responds based on your project level.

Available styles:
  bkit-learning     Best for beginners (learning points, TODO markers)
  bkit-pdca-guide   Best for PDCA workflows (status badges, checklists)
  bkit-enterprise   Best for architects (tradeoff analysis, cost impact)

Usage:
  /output-style              Select interactively
  /output-style bkit-learning  Apply directly

Auto-recommendation:
  Starter → bkit-learning
  Dynamic → bkit-pdca-guide
  Enterprise → bkit-enterprise

## Agent Memory

All bkit agents automatically remember context across sessions.
No configuration needed.

Memory scopes:
  project   9 agents remember per-project context (.claude/agent-memory/)
  user      2 agents remember cross-project learning (~/.claude/agent-memory/)

Agents with user-scope memory:
  starter-guide     Remembers your learning progress across projects
  pipeline-guide    Remembers your pipeline preferences globally

## Agent Teams

Parallel PDCA execution for Dynamic and Enterprise projects.
See Level 4 for details.

📚 Claude Code Learning Complete!

**Current Level**: {level}
**Learned**: {summary}

🎯 Next Steps:
- Continue learning with /claude-code-learning learn {next_level}
- Auto-generate settings with /claude-code-learning setup
- Check latest trends with /claude-code-learning upgrade