agentsclimarketplace

Run tests

Skill tmj-90/gaffer/runner/skills/run-tests

Use when a ticket or acceptance criterion needs the test suite run and its result evidenced, or after making a change to confirm nothing broke. Invoke for "tests must pass", "verify the suite is green", or before submitting any code change for review.From its SKILL.md

Install
npx -y skills add tmj-90/gaffer --skill run-tests

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.7 KB, 349 tokens by cl100k_base, as published. Nobody here has run it

Run the test suite

Run the repo's existing test command, report the real result, and evidence it. Do not introduce a new runner — use what the project already uses.

Steps

  1. Find the test command from the context packet's verification commands (e.g. pnpm test, npm test, pytest, go test ./..., mvn test). If the packet is silent, detect it from the manifest (package.json scripts, pyproject.toml, go.mod, pom.xml). Use the project script, not the underlying tool directly.
  2. Run the full suite (or the scoped subset the ticket names). Capture the exact command and the pass/fail summary, including counts (passed/failed/skipped).
  3. If tests fail, read the failures. Fix only what the ticket scopes; if a failure is unrelated and pre-existing, note it — do not paper over it or delete the test.
  4. Re-run until green (or until you confirm a failure is out of scope and blocking).
  5. Evidence: the exact command and its passing summary. Then use the record-evidence skill to record test_output against the AC and submit for review.

Rules

  • Report the true result — never claim "tests pass" without a run in this session.
  • Don't skip or delete failing tests to go green; fix the cause or mark blocked.
  • Don't add a new test framework; match the repo's runner.
  • Run on a branch (the create-branch skill), never a protected branch.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,758. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.