agentleFS
Sign inStart free
tadoEngtadoEng/web-starter/.claude/skills/feature/SKILL.md

feature

Skill2 starsChanged 3 months agoMITView on GitHub

Build a complete product feature end to end — backend, contract, frontend, tests, evidence. Use for whole-capability requests like "add invitations", "build expense approval", "let managers export a report", where the work crosses the database, the API and the UI.

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 60 edited versions we read keep these.

  • 3

    Distinctive

    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
  1. Very specific:

    If the answers change docs/PRODUCT.md, update it in this change.

    line 29
  2. Distinctive:

    Only if the schema changes.

    line 43
  3. Distinctive:

    Run it before handing over, particularly the boundary checks.

    line 69
  4. Distinctive:

    Do what was asked. If you spot something adjacent worth fixing, mention it — don't fold it in.

    line 80

“Common” is measured: kept by at least 6 in 10 of the 60 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Build a feature

Orchestrates the specialist skills; does not repeat them. Each step below hands off to the skill that owns it — follow that skill's rules there, then come back.

1. Product check — before any code

Answer these. If you can't, ask rather than guess:

  • Who does this serve, and what can they do that they couldn't before?
  • What is the success state — what's true when it works?
  • Who must NOT be able to do it? This is the authorization spec, and it is the step most often skipped. Write it as a table of role → allowed.
  • What is explicitly out of scope for this pass?

If the request is broad or vague — "build project management", "add a dashboard" — stop and run the product-shaping skill first. It produces the bounded brief this skill builds against. Excellent code for the wrong product is the most expensive failure available here, and it is cheapest to prevent at this exact moment.

If the answers change docs/PRODUCT.md, update it in this change.

2. Plan the slice

State the plan before implementing: tables touched, endpoints added, pages added, and the authorization rule for each mutation. Keep it to a few lines. If the plan requires an architectural boundary to move — a queue, a cache, a second datastore, logic in the frontend — stop here and propose it per AGENTS.md.

Build one thin vertical slice first, end to end, before adding breadth. A feature that is 80% backend and 0% visible is not 80% done.

3. Data — db-migration skill

Only if the schema changes. Model → autogenerate → read the migration → apply → test.

4. API — api-endpoint skill

Schemas → route → service → authorization → tests for all four authz cases → regenerate the client. The regenerated frontend/src/generated/ diff belongs in this change.

5. UI — frontend-page, or frontend-craft for anything visual

  • Routine wiring (one more screen following an established pattern) → frontend-page: route → generated-client query hook → components → five async states → tests.
  • A new surface, a redesign, a dashboard, or anything where the layout is the work → frontend-craft. It owns hierarchy, composition, responsive decisions and rendered evidence. Wiring a page correctly and having it look generic are two different failures.

6. Evidence

  • ./scripts/seed-demo-data first — an empty database renders an empty UI and proves nothing about long titles, null fields, status variety or pagination.
  • ./scripts/verify.sh green — report the real output.
  • Exercise the feature in a real browser. Attach a desktop screenshot and a mobile (375px) screenshot, plus one error or empty state.
  • State plainly what you did not cover.

7. Self-review — review skill

Run it before handing over, particularly the boundary checks. Reviewing your own work with the checklist catches more than re-reading the diff does.

Order matters

Backend → contract → frontend, in that order. Building UI against a shape you intend to add later means hand-writing the type you were told never to hand-write, and it is the single most common way this architecture rots.

Scope discipline

Do what was asked. If you spot something adjacent worth fixing, mention it — don't fold it in. A feature PR that also reformats three files is a PR nobody can review properly.

Download now (ZIP)

  • Other versions67 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 67

    1. crbnos/carbon★ 2.8ksame name
    2. aeonfun/aeon★ 785same name
    3. aaronjmars/aeon★ 776same name
    4. astashov/liftosaur★ 747same name
    5. me2resh/apexyard★ 532same name
    6. yicheng47/runner★ 436same name
    7. bradtraversy/coding-with-ai-course-resources★ 344same name
    8. garagon/nanostack★ 206same name
    9. DeL-TaiseiOzaki/claude-code-orchestra★ 199same name
    10. vide/matedroid★ 82same name

    57 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use bug, bugfix and 10 more.

    Other files people use alongside this one.

    Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
    • marcusbelzSkill

      bug

      Document a bug as a single file under docs/bugs/. Use to report new bugs or update the status of existing ones.

      Also in 6 projects that use this

    • team-attentionSkill

      bugfix

      Root cause based one-shot bug fix. debugger diagnosis → requirements.md generation → /execute. /bugfix "error description" Full investigation pipeline: debugger + gap-analyzer + standard verify. QA suggestion after successful fix.

      Also in 6 projects that use this

    • codebycoreySkill

      adopt

      Adopt an existing plan from conversation context into delta-spec format. Use when importing a plan, adopting planning that already happened, capturing plan mode output, or bringing in prior design work.

      Also in 4 projects that use this

    • marylinSkill

      recover

      Recover work from a crashed or interrupted session. Use when Claude crashed mid-task, after an unexpected exit, when you see 'stale sessions detected', or when you lost context and need to figure out what was happening.

      Also in 3 projects that use this

    • AWSSkill

      map

      Map verified service capabilities against customer-provided control framework and threat model. Produces mapping-results.json, controls-catalog.md, and framework-mapping.md. Supports pluggable frameworks: CCMv4, NIST 800-53, CIS Benchmarks, ISO 27001, etc. Split into 4 focused sub-skills for better accuracy; this skill orchestrates them.

      Also in 4 projects that use this

    • corygabrielsenSkill

      spike

      Implement N approaches as separate branches, then compare side-by-side. Removes "implementation effort" as a variable from the decision.

      Also in 4 projects that use this

  • In this repository9 other files it gives its agents.

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free