agentsclimarketplace
Sign in

Test issue

Skill amurshak/hephaestus/.agents/skills/test-issue

Test the current implementation. Issue number (optional): <argument> Use for /test-issue requests.From its SKILL.md

Install
npx -y skills add amurshak/hephaestus --skill test-issue

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

  • 1 stars1 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

1.9 KB, as published. Nobody here has run it

<!-- requires: tester --> <!-- chains: none --> <!-- generated from .ai/workflows/test-issue.md; do not edit directly -->

Codex: this skill is the /test-issue adapter. Use Codex role agents from .codex/agents/ when the runtime exposes them; otherwise perform the work directly and keep the same structured output.

Codex does not substitute $ARGUMENTS — read it as the arguments given in the user's request.

Test the current implementation. Issue number (optional): $ARGUMENTS

Always delegate to role agent(s) — test output is verbose and should not pollute the main context window.

Steps:

  1. Detect repo: Run git remote get-url origin to identify the target repo for gh commands.

  2. Identify changed files: Run git diff --name-only and git diff --cached --name-only to see what's affected.

  3. Launch tester role agent(s):

    • Check CLAUDE.md to determine the correct test and lint commands for this project
    • Launch one or more tester role agents based on changed areas (parallelize if there are independent test suites)
    • Each tester runs in its own context and returns only a structured summary

  4. Verify acceptance criteria: If an issue number was provided in $ARGUMENTS, run gh issue view <#> --repo <detected-repo> and check each acceptance criterion against the implementation. Report pass/fail per criterion.

  5. Report results (concise — the role agents already absorbed the verbose output):

    • Tests: pass count, fail count, any error output
    • Lint: clean or list of violations
    • ACs: pass/fail per criterion

If anything fails, identify the root cause and suggest a fix. Do not just report the failure.

Next steps

  • If all tests pass: run /ship to create a PR, or /finish <#> if already merged
  • If tests fail: fix the failures and re-run /test-issue

Keep looking

Skills are one crate of 627,801. 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.