agentleFS
lglucaslglucas/ai-dev-operating-system/.claude/skills/verify-build-works/SKILL.md

verify-build-works

Skill12 starsChanged 47 days agoMITView on GitHub

Smoke-test that the project still builds, the dev server starts, and the main user flow loads after a change. Run after every non-trivial edit, after a rollback (`rollback-safe`), after a fix from `bug-triage-agent`, before a commit, before pushing, and as part of `release-check`. Also when the user says "ainda tá funcionando?", "roda aí pra ver", "testa se não quebrou", "tá de pé?".

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 9 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    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. Very specific:

    After applying a fix from bug-triage-agent.

    line 10
  2. Very specific:

    After a rollback-safe operation.

    line 11
  3. Distinctive:

    Before any commit larger than a single docs change.

    line 12
  4. Distinctive:

    Before pushing to remote.

    line 13
  5. Distinctive:

    Before opening a PR.

    line 14
  6. Distinctive:

    Before tagging a release.

    line 15
  7. Distinctive:

    Stop and report at first failure.

    line 26
  8. Very specific:

    If build fails, hand off to bug-triage-agent.

    line 34
  9. Distinctive:

    If any step fails:

    line 73
  10. Distinctive:

    Don't claim success without running the steps.

    line 89
  11. Very specific:

    Don't suppress errors with || true.

    line 90
  12. Distinctive:

    Don't skip step 3 because "build passed".

    line 91
  13. Distinctive:

    Don't run destructive commands (DB migrations, file deletions) as part of verification.

    line 92

≈ “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.

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

Verify Build Works

When to run this skill

  • After applying a fix from bug-triage-agent.
  • After a rollback-safe operation.
  • Before any commit larger than a single docs change.
  • Before pushing to remote.
  • Before opening a PR.
  • Before tagging a release.

Verification ladder (run all that apply, in order)

Step 1 — Static checks (cheap, fast)

npm run typecheck
npm run lint

Stop and report at first failure. Don't continue if static layer is broken.

Step 2 — Build

npm run build

If build fails, hand off to bug-triage-agent.

Step 3 — Dev server starts

npm run dev

Confirm: process alive after 15s, HTTP 200 on http://localhost:<port>/, no fatal stderr.

Step 4 — Smoke test the golden path

For UI: load homepage + most critical authenticated page. For API: hit GET /health (or main endpoint) → 2xx.

npm run test:smoke   # if exists

Step 5 — Visual sanity (UI only)

  • Open the affected page in a real browser.
  • Confirm change is visible and not regressed.
  • Confirm at least one adjacent feature didn't break.

Output format

🧪 verify-build-works

Step 1 — Static checks:    ✅ typecheck OK, lint OK
Step 2 — Build:            ✅ build succeeded in 14s
Step 3 — Dev server:       ✅ ready on :3000, GET / → 200
Step 4 — Smoke tests:      ⚠️  no test:smoke script — skipped
Step 5 — Visual sanity:    ✅ home renders, login renders

Verdict: SAFE TO COMMIT.

If any step fails:

🧪 verify-build-works — ❌ FAIL at Step 2 (build)

Erro principal: src/features/auth/sign-in.ts(23,7): TS2322 ...

Próximo passo: invoco o bug-triage-agent.

Tone for the vibe coder

Antes de avisar que terminou, eu sempre testo. Se algo está quebrado, eu falo agora — não na frente do primeiro usuário.

Do NOT

  • Don't claim success without running the steps.
  • Don't suppress errors with || true.
  • Don't skip step 3 because "build passed".
  • Don't run destructive commands (DB migrations, file deletions) as part of verification.

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.