Loading...
Loading...
Claude Code Command Selection Guide - Automatically recommend and select the right commands, agents, and skills in Claude Code. Use when: (1) user is unsure which command or tool to use, (2) needs to decide which agent/skill best fits the current task, (3) querying usage scenarios for /plan, /tdd, /compact, /loop and other commands, (4) understanding when to invoke planner, code-reviewer, build-error-resolver and other agents, (5) needs command cheat sheet or decision flowchart. Triggers: "which command to use", "which agent", "command selection", "how to use /plan", "when to use /compact", "agent selection guide", "command cheat sheet", "skill recommendation".
npx skill4agent add alirezarezvani/claude-skills command-guidegraph TD
A[User Request] --> B{Request Type?}
B -->|New Feature| C[/plan]
B -->|Bug Fix| D[/tdd or build-error-resolver]
B -->|Code Review| E[/code-review or code-reviewer agent]
B -->|Testing| F[/e2e or tdd-guide agent]
B -->|Context Too Long| G[/compact]
B -->|Documentation| H[/docs or docs-lookup agent]
B -->|Looping Task| I[/loop]
B -->|Security Review| J[security-reviewer agent]
C --> K[planner agent]
D --> L{Build Failed?}
L -->|Yes| M[build-error-resolver]
L -->|No| N[tdd-guide]
E --> O[code-reviewer]
F --> P[e2e-runner]| Command | Use Case | Example |
|---|---|---|
| Context too long (>150K tokens), slow response, task phase transition | |
| Start fresh conversation, clear history | |
| Periodic task execution, automated looping work | |
| View help, learn commands | |
| Need faster response (Opus 4.6 only) | |
| Switch model | |
| Command | Use Case | Activation Timing |
|---|---|---|
| Start new feature, architecture refactor, complex tasks | Enter Plan Mode |
| Write tests, TDD development workflow | When test guidance needed |
| E2E testing, critical user flow verification | When browser testing needed |
| Code quality review | After writing code |
| Build failure, type errors | When build fails |
| Extract patterns from session, learning | Before session ends |
| Create new skill from git history | When repeating patterns found |
| Command | Use Case | Example |
|---|---|---|
| Update project documentation | |
| Update code maps | |
| Save memory to memory system | |
| View task list | |
| Agent | Trigger Condition | Purpose |
|---|---|---|
| Complex feature request, architectural decision | Create implementation plan |
| System design, tech stack selection | Architecture analysis and decisions |
| New feature, bug fix | TDD workflow guidance |
| Invoke immediately after writing code | Code quality review |
| Handling auth, API, sensitive data | Security vulnerability detection |
| Agent | Trigger Condition | Purpose |
|---|---|---|
| Invoke immediately when build fails | Fix build/type errors |
| Critical user flows, before PR | E2E test execution |
| Code maintenance, dead code cleanup | Dead code detection and cleanup |
| Update docs, codemaps | Documentation sync |
| Agent | Trigger Condition | Purpose |
|---|---|---|
| Codebase exploration, file finding | Quick codebase exploration |
| Complex multi-step tasks | General task handling |
| Query library/framework docs | Get latest API documentation |
| Skill | Trigger Timing | Purpose |
|---|---|---|
| Developing new feature/fixing bug | Complete TDD workflow guidance |
| After feature completion, before PR | Comprehensive verification (build/test/lint/security) |
| Long session, context pressure | Guide when to manually |
| Skill | Trigger Timing | Purpose |
|---|---|---|
| Frontend development | React/Next.js/Vue best practices |
| Backend development | API/service architecture patterns |
| API design | RESTful/API design standards |
| MCP server development | MCP configuration and patterns |
| Skill | Trigger Timing | Purpose |
|---|---|---|
| E2E testing needs | Playwright test generation |
| Security review needs | OWASP Top 10 detection |
| Skill | Trigger Timing | Purpose |
|---|---|---|
| Need deep research | Multi-round search and research |
| Need web search | Web content search |
| Query library docs | Context7 documentation query |
| Phase | Recommended Tool Combination | Reason |
|---|---|---|
| Requirements Analysis | | Plan first, explore later |
| Architecture Design | | Professional architecture guidance |
| Pre-Development | | Test first |
| During Development | Direct edit + quick iteration | Stay in flow |
| Post-Development | | Quality gate |
| Testing Phase | | Complete test coverage |
| Before PR | | Final verification |
| Build Failure | | Focused fix |
| Problem | Invoke Immediately | Note |
|---|---|---|
| Build failure | | Minimal changes, quick fix |
| Type error | | TypeScript specialist |
| Bug fix | | Write test then fix |
| Security vulnerability | | OWASP detection |
| Poor code quality | | Immediate review |
| Missing documentation | | Auto update |
| Dead code | | Safe cleanup |
| Development Type | Skills Combination |
|---|---|
| Frontend feature | |
| Backend API | |
| MCP server | |
| Database | |
| Security feature | |
| Situation | Auto Action |
|---|---|
| Code written/modified | Immediately invoke |
| Build fails | Immediately invoke |
| Complex feature request | Immediately invoke |
| Handling auth/sensitive data | Immediately invoke |
| New feature/bug fix | Immediately invoke |
| Architectural decision | Immediately invoke |
| Indicator | Trigger |
|---|---|
| Token > 150K | Immediately compact |
| Slow response | Suggest compact |
| Task phase switch | Compact at boundary |
| Major milestone completed | Compact then continue |
| Debugging ends -> new task | Clear debug traces |
Development Workflow:
/plan -> Enter planning mode (complex tasks)
/tdd -> TDD workflow
/e2e -> E2E testing
/code-review -> Code review
/build-fix -> Fix build
Session Management:
/compact -> Compact context
/clear -> Clear session
/loop -> Looping task
/fast -> Fast mode
Documentation & Memory:
/docs -> Update docs
/remember -> Save memory
/tasks -> View tasks
Help:
/help -> View all commands/plantdd-guidecode-reviewerbuild-error-resolversecurity-reviewerverification-loop