// Use when the user asks about agent pipelines, how to use /code /docs /startup commands, how to create custom pipelines, or needs help troubleshooting agent workflows - explains the agent orchestrator system and guides pipeline creation
Use when the user wants to create a custom agent pipeline, add a new pipeline to an existing agent, or design a multi-stage workflow that chains skills together - guides through pipeline JSON creation with validation
Use when a super-agent (coding-agent, docs-agent, startup-agent) needs to execute a multi-stage pipeline defined in JSON - resolves template variables, manages sequential/parallel/chain stage execution, enforces quality gates, and passes data between stages via file outputs
Use when the user says /code or asks for end-to-end coding workflows like full-stack builds, quality audits, rapid prototypes, or debug chains - routes to the right pipeline and invokes pipeline-orchestrator to execute it
Use when the user says /docs or asks for end-to-end documentation workflows like API docs, project scaffolding, content pipelines, or release documentation - routes to the right pipeline and invokes pipeline-orchestrator to execute it
Use when the user says /startup or asks for end-to-end startup workflows like MVP builds, go-to-market launches, pitch decks, or product analytics - routes to the right pipeline and invokes pipeline-orchestrator to execute it
Create detailed technical plans and implementation roadmaps by analyzing project architecture and designing solutions that integrate seamlessly with existing patterns. Use when designing features, planning integrations, making architectural decisions. Triggers: 'plan', 'design', 'architecture', 'approach', 'how should I', 'best way', 'integrate', '계획', '설계', '아키텍처', '접근법', '어떻게 해야', '가장 좋은 방법', '통합', '마이그레이션', working with multi-module features, system boundaries, complex migrations.
| name | agent-help |
| description | Use when the user asks about agent pipelines, how to use /code /docs /startup commands, how to create custom pipelines, or needs help troubleshooting agent workflows - explains the agent orchestrator system and guides pipeline creation |
I'm using the agent-help skill to explain the agent pipeline system.
| Command | Agent | What It Does |
|---|---|---|
/code | Coding Agent | Full-stack builds, quality audits, prototypes, debugging |
/code full-stack | Coding Agent | brainstorm → plan → parallel build → review → finish |
/code quality | Coding Agent | code-review → bugs → security → tests → perf → verify |
/code prototype | Coding Agent | api → db → FastAPI → React → Docker |
/code debug | Coding Agent | debug → root-cause → fix → test → verify |
/docs | Docs Agent | API docs, project scaffolding, content, releases |
/docs api | Docs Agent | documenter → code-docs → examples → OpenAPI |
/docs project | Docs Agent | CLAUDE.md → ARCHITECTURE → DEVLOG → DOMAIN |
/docs content | Docs Agent | research → parallel(Medium, LinkedIn, newsletter) → polish |
/docs release | Docs Agent | PRs → commits → changelog → release-notes |
/startup | Startup Agent | MVPs, go-to-market, pitch decks, analytics |
/startup mvp | Startup Agent | brainstorm → Hormozi → plan → parallel build → deploy |
/startup gtm | Startup Agent | research → pitch → parallel(5 channels) → email |
/startup pitch | Startup Agent | Hormozi → coach → PPTX → outreach email |
/startup analytics | Startup Agent | metrics → pipeline → D3.js → PPTX report |
/code, /docs, or /startup (optionally with a pipeline name)Read the full guide: agents/GUIDE.md
agents/<agent>/references/pipelines/<name>.jsonskill, skill-chain, or parallel typesapproval, quality, verification) between stagesoutputs and inputs for data passingFor the complete guide with architecture diagrams, JSON schema, examples, and custom pipeline tutorial, read agents/GUIDE.md.