agentleFS
Sign inStart free
Hey-DigaHey-Diga/dotclaude/skills/fix-ci/SKILL.md

fix-ci

Skill17 starsChanged 9 months agoMITView on GitHub

Run Prisma generate, lint (auto-fix), typecheck, and tests; iterate until clean, summarize results. Use when CI is failing or before pushing to verify the repo is clean.

39 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use get-pr-comments, merge and 5 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.
  • jaydubya818Skill

    get-pr-comments

    Use when pull-request feedback needs to be fetched and summarized for action.

    Also in 3 projects that use this

  • MicrosoftSkill

    merge

    Merge changes from the topic branch to the merge base branch. Use when the user wants to merge their session's work back to the base branch.

    Also in 3 projects that use this

  • SentrySkill

    security-review

    Finds exploitable application security vulnerabilities in code changes. Use for Warden security scans, appsec review, OWASP-style checks, authentication or authorization bugs, injection, XSS, SSRF, path traversal, secrets, unsafe crypto, webhook verification, open redirects, or sensitive data exposure.

    Also in 4 projects that use this

  • NVIDIASkill

    testing

    Run Python and Rust tests for physicsnemo-curator using uv + pytest with coverage reporting via pytest-cov, and cargo-nextest for Rust tests. Includes benchmark workflows with pytest-benchmark and criterion.

    Also in 3 projects that use this

  • AWSSkill

    ship

    Finalize dev work on an issue branch — update docs, push, and open a PR.

    Also in 3 projects that use this

  • GoogleSkill

    tdd

    Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 6 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 37 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Follow this sequence. After each step, if it fails, apply minimal, safe fixes and re-run the step before moving on.

    line 21
  2. Very specific:

    If that script is missing or fails, run npx prisma generate.

    line 25
  3. Distinctive:

    If Prisma schema errors appear, propose the smallest viable fix.

    line 26
  4. Very specific:

    If it fails due to auto-fixable issues, run npm run lint:fix and then re-run npm run lint.

    line 30
  5. Distinctive:

    If non-auto-fixable issues remain, make small edits to resolve them (naming, imports, formatting, obvious dead code).

    line 31
  6. Very specific:

    Run npm run typecheck (equivalent to tsc --noEmit).

    line 34
  7. Distinctive:

    If failures are straightforward (e.g., updated types, trivial assertions, missing imports), patch them minimally.

    line 39
  8. Very specific:

    Use the pre-approved commands above.

    line 43
  9. Distinctive:

    Keep edits minimal and in-place.

    line 44
  10. Distinctive:

    After making any edits, re-run the affected step to confirm green.

    line 45

“Common” is measured: kept by at least 6 in 10 of the 37 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

You are running in a Next.js + TypeScript project.

Goal

Get the repo into a clean state by:

  1. ensuring Prisma types are generated,
  2. fixing lint issues automatically where possible,
  3. passing typecheck,
  4. passing tests.

Then produce a short status report (OK/FAIL for each step) plus any follow-ups I should do.

What to do

Follow this sequence. After each step, if it fails, apply minimal, safe fixes and re-run the step before moving on.

  1. Generate Prisma client/types
    • First try: run npm run db:generate.
    • If that script is missing or fails, run npx prisma generate.
    • If Prisma schema errors appear, propose the smallest viable fix. If you change files, explain why.
  2. Lint
    • Run npm run lint.
    • If it fails due to auto-fixable issues, run npm run lint:fix and then re-run npm run lint.
    • If non-auto-fixable issues remain, make small edits to resolve them (naming, imports, formatting, obvious dead code). Keep changes tightly scoped.
  3. Typecheck
    • Run npm run typecheck (equivalent to tsc --noEmit).
    • Resolve clear, local TS errors (missing/incorrect types, unused vars, obvious nullability). Avoid broad any unless strictly necessary and documented.
  4. Tests
    • Run npm test.
    • If failures are straightforward (e.g., updated types, trivial assertions, missing imports), patch them minimally. Do not rewrite test intent.

Constraints & notes

  • Use the pre-approved commands above. Prefer the npm run scripts provided by the project.
  • Keep edits minimal and in-place. Changes should not modify current functionality.
  • After making any edits, re-run the affected step to confirm green.
  • At the end, print a concise checklist and include a short "Next actions" section if anything still fails: Prisma generate: [OK|FAIL] (brief note) Lint: [OK|FAIL] (counts, key rules fixed) Typecheck: [OK|FAIL] (top 1–2 culprits) Tests: [OK|FAIL] (failing suites & test names)

Runbook (you may run these as needed)

  • Prisma:
    • npm run db:generate
    • npx prisma generate
  • Lint:
    • npm run lint
    • npm run lint:fix
  • Types:
    • npm run typecheck
  • Tests:
    • npm test

Download now (ZIP)

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