Command Guide
Pick the right Claude Code slash command, subagent, or skill when you are unsure which workflow fits the current task.
Overview
command-guide is a journey-wide agent skill that recommends Claude Code commands and agents—usable whenever a solo builder needs to choose the right /command or specialist before committing.
Install
npx skills add https://github.com/alirezarezvani/claude-skills --skill command-guideWhat is this skill?
- Mermaid quick decision flowchart from request type to command or agent
- Maps scenarios to /plan, /tdd, /compact, /loop, /code-review, /e2e, /docs, and more
- Routes build failures to build-error-resolver versus tdd-guide
- Covers when to invoke planner, code-reviewer, security-reviewer, and docs-lookup agents
- Explicit triggers for command selection, cheat sheet, and skill recommendation queries
- Quick decision flowchart covers request types including new feature, bug fix, code review, testing, context length, docu
Adoption & trust: 513 installs on skills.sh; 17.5k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You know Claude Code has many slash commands and agents but waste time guessing whether to run /plan, /tdd, /compact, or call code-reviewer.
Who is it for?
Claude Code daily drivers who want a cheat sheet mindset without memorizing every command mapping.
Skip if: Developers on editors without Claude Code slash commands who only need language-specific coding help.
When should I use this skill?
User is unsure which command or tool to use, needs agent/skill fit for the task, asks about /plan, /tdd, /compact, /loop usage, or wants a command cheat sheet or decision flowchart.
What do I get? / Deliverables
You get a scenario-matched recommendation—command, agent, or skill—from the decision flowchart so the next step in your session is the intended Claude Code workflow.
- Recommended Claude Code slash command for the scenario
- Recommended specialist agent or related skill when applicable
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
A new feature request arrives and you route to /plan and the planner agent instead of coding blind.
You choose between /e2e and the tdd-guide agent based on whether the task is coverage or red-green iteration.
Before merge you follow the flowchart to /code-review or the code-reviewer agent rather than a generic summarize.
A failing CI build triggers build-error-resolver per the bug-fix branch of the chart.
Early spec work uses /plan recommendations so implementation later stays aligned.
How it compares
Use as meta routing guidance instead of raw model improvisation when Claude Code offers a documented command or agent for the job.
Common Questions / FAQ
Who is command-guide for?
Solo and indie builders using Claude Code who want fast recommendations for commands, agents, and skills matched to the current request.
When should I use command-guide?
Use it at the start of Build implementation when choosing /plan versus /tdd, during Ship when deciding on /code-review or security-reviewer, when context overflows and you need /compact, during Launch prep for /docs, or anytime you ask which agent fits a looping or testing task.
Is command-guide safe to install?
It is documentation-style routing with no inherent shell execution; confirm trust via the Security Audits panel on this Prism page like any third-party skill.
SKILL.md
READMESKILL.md - Command Guide
# Claude Code Command Selection Guide This skill helps you choose the most appropriate command, agent, or skill for different scenarios. ## Quick Decision Flowchart ```mermaid graph 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] ``` ## 1. Built-in Slash Commands ### Session Management Commands | Command | Use Case | Example | |---------|----------|---------| | `/compact` | Context too long (>150K tokens), slow response, task phase transition | `/compact` or auto-trigger | | `/clear` | Start fresh conversation, clear history | `/clear` | | `/loop` | Periodic task execution, automated looping work | `/loop 5m check build status` | | `/help` | View help, learn commands | `/help` | | `/fast` | Need faster response (Opus 4.6 only) | `/fast` | | `/model` | Switch model | `/model sonnet` | ### Development Workflow Commands | Command | Use Case | Activation Timing | |---------|----------|-------------------| | `/plan` | Start new feature, architecture refactor, complex tasks | **Enter Plan Mode** | | `/tdd` | Write tests, TDD development workflow | When test guidance needed | | `/e2e` | E2E testing, critical user flow verification | When browser testing needed | | `/code-review` | Code quality review | After writing code | | `/build-fix` | Build failure, type errors | When build fails | | `/learn` | Extract patterns from session, learning | Before session ends | | `/skill-create` | Create new skill from git history | When repeating patterns found | ### Documentation & Query Commands | Command | Use Case | Example | |---------|----------|---------| | `/docs` | Update project documentation | `/docs` | | `/update-codemaps` | Update code maps | `/update-codemaps` | | `/remember` | Save memory to memory system | `/remember user prefers concise output` | | `/tasks` | View task list | `/tasks` | --- ## 2. Agents Selection ### Development Workflow Agents | Agent | Trigger Condition | Purpose | |-------|-------------------|---------| | `planner` | Complex feature request, architectural decision | Create implementation plan | | `architect` | System design, tech stack selection | Architecture analysis and decisions | | `tdd-guide` | New feature, bug fix | TDD workflow guidance | | `code-reviewer` | **Invoke immediately after writing code** | Code quality review | | `security-reviewer` | Handling auth, API, sensitive data | Security vulnerability detection | ### Problem Solving Agents | Agent | Trigger Condition | Purpose | |-------|-------------------|---------| | `build-error-resolver` | **Invoke immediately when build fails** | Fix build/type errors | | `e2e-runner` | Critical user flows, before PR | E2E test execution | | `refactor-cleaner` | Code maintenance, dead code clean