pipeline-help
Skill1 starsChanged 59 days agoMITView on GitHub
Interactive guide for the feature development pipeline. Explains the flow, which skill to use, and how to resume after context cleanup. Use when asking about the pipeline, how to start, or what comes next.
In this repository27 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- design-craft/CLAUDE.mdCLAUDE.md
- android-emulatorSkill
- audit-branchSkill
- brainstormSkill
- create-devtoolSkill
- create-featureSkill
- create-infrastructureSkill
- execute-tasksSkill
- finish-featureSkill
- frontend-testingSkill
- generate-feature-docSkill
- generate-prdSkill
- git-commitSkill
- ios-simulatorSkill
- modify-featureSkill
- plan-implementationSkill
- prd-clarifierSkill
- prd-to-uxSkill
- prototypeSkill
- react-clean-architectureSkill
- receiving-code-reviewSkill
- refactoring-uiSkill
- setup-daher-skillsSkill
- systematic-debuggingSkill
- test-mobile-appSkill
- writing-skillsSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
If docs/agents/project-conventions.md is missing, run /setup-daher-skills first.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Pipeline Help
If docs/agents/project-conventions.md is missing, run /setup-daher-skills first. Every other skill stops without the files it seeds.
Conventions live in the project's .claude/rules/ — one source of truth.
brainstorm → generate-prd → prd-clarifier → prd-to-ux → plan-implementation → execute-tasks → finish-feature → generate-feature-doc
│ │
└──────────── prototype (optional) ────────┘| # | Skill | Input | Output | Skip when |
| 1 | /brainstorm | Rough idea | DESIGN.md | The feature is already clear |
| 2 | /generate-prd | Idea / DESIGN | PRD.md | — (entry point for specs) |
| 3 | /prd-clarifier | PRD | Clarifications merged into PRD.md | The PRD is already sharp |
| 4 | /prd-to-ux | PRD | UX-spec.md | — |
| 5 | /plan-implementation | Specs | Implementation plan | — |
| 6 | /execute-tasks | Plan | Code + review gates + docs/agents/runs/<feature>-<date>.json run report | Built outside the pipeline → /audit-branch |
| 7 | /finish-feature | Code | Tests, build, commit / PR / discard | — |
| 8 | /generate-feature-doc | Feature code | Feature README.md | Small features |
Quick Start — pick the entry by blast radius
Score the request on three signals and take the highest tier any of them reaches. State the tier in one line before starting so the user can override it.
| Tier | Files | New contract / dependency | Ambiguity | Entry point |
| Bug | any | none — behavior is wrong, spec is not | none | /systematic-debugging (failing test first, then the fix). No pipeline. |
| Small | 1–4, inside one feature | none, or one internal hook/component | clear once you read the code | /modify-feature for extend/refactor; or /plan-implementation → /execute-tasks → /finish-feature when several files need review gates |
| Standard | 5+, or fewer with a new contract | new endpoint, new screen, new shared piece | one real choice to make | /generate-prd → /prd-to-ux → /plan-implementation → /execute-tasks → /finish-feature |
| Large | cross-feature or shared infra | new external dep, public API, UNVERIFIED contracts | multiple open questions | /brainstorm first, then the full pipeline |
File count alone never promotes past Small — the contract and ambiguity columns do. Tie-breaker: anything touching auth, user input, external HTML/URLs, token storage or env access is at least Standard — the quality gate is where frontend-security.md runs. Inside /execute-tasks the same idea repeats per deliverable (tier S/M/L in PROGRESS.md decides how many reviewers each one gets).
Artifacts
Permanent, next to the feature: PRD.md, UX-spec.md, README.md. Intermediate (deleted after ship): DESIGN.md, *-implementation-plan.md, PROGRESS.md.
Each skill reads the previous artifact, not the conversation. Fresh session between /plan-implementation and /execute-tasks. After two failed corrections on the same problem, start a fresh session. Resume: name the feature and invoke the next skill.
Outside the pipeline
| Need | Skill |
| Extend or restructure a shipped feature | /modify-feature |
| Write tests | /frontend-testing |
| Something is broken | /systematic-debugging |
| Build or audit UI | /refactoring-ui |
| Dev-only debug panel | /create-devtool |
| Review a branch built without the pipeline | /audit-branch |
| Commit / PR | /git-commit, /finish-feature |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.