agentsclimarketplace

Test runner

Skill YZYY95K/test/skills/test-runner

Auditable AgentTeams multi-agent software delivery with contract-driven Skills.

Install
npx -y skills add YZYY95K/test --skill test-runner

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

3 things to look at

  • 12 days oldThe repository was created 12 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 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.

What its author says it does

Copied from the file, not written here

Apply a candidate only in isolation, execute tests, and compare against a trusted baseline. Use when a validated Patch is ready for verification before security review or PR creation.

SKILL.md

1.5 KB, as published. Nobody here has run it

Test Runner

Produce reproducible TestRunResult evidence; never approve a patch.

Procedure

  1. Validate the candidate digest, repository revision, tier, and test policy.
  2. Establish the baseline from the same trusted revision.
  3. Create an isolated disposable checkout and apply the candidate there only.
  4. Run focused tests for T1/T2 and the full suite for T3+; enforce resource and network policy.
  5. Compare results with baseline and label retries or flaky evidence.
  6. Run python scripts/validate.py output <artifact.json>. Emit test.passed only for zero failures, zero errors, and no regression; otherwise emit test.failed.

Decision rules

  • Timeout, missing baseline, malformed output, or unavailable isolation is error, never passed.
  • Retry infrastructure failure once. Cap isolated flaky reruns at two.
  • Route deterministic code failures to CoderAgent with exact failing evidence.

Boundaries

Do not alter the canonical checkout, source, tests, acceptance criteria, or review status. Never interpolate untrusted input into a shell command.

Read the contract for suite policy and failure routing. Read examples to calibrate pass, error, and boundary outcomes.

Keep looking

Skills are one crate of 328,083. 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.