agentleFS
Sign inStart free
SrejonKhanSrejonKhan/agent-skills/skills/test_runner/SKILL.md

test_runner

Skill3 starsChanged 2 months agoMITView on GitHub

Executes the project's test suite, analyzes failures, and provides fix recommendations.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 8 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to execute tests and understand _why_ they might be failing.

    line 8
  2. Very specific:

    Use run_command to execute tests.

    line 17
  3. Very specific:

    Use view_file to read failure logs or source code if tests fail.

    line 18
  4. Very specific:

    Command: Run the appropriate test command for the environment (e.g., npm test, pytest, python -m unittest).

    line 24
  5. Distinctive:

    Scope: Run all tests by default, or target a specific file if requested.

    line 25
  6. Distinctive:

    Pass: If all green, celebrate! 🟢

    line 29
  7. Distinctive:

    Fail: If red 🔴, analyze the output:

    line 30
  8. Distinctive:

    If tests failed, provide a summary of the failure.

    line 37
  9. Distinctive:

    Ensure that the testing process didn't leave behind artifacts (temp files, database entries) unless intended for debugging.

    line 42
  10. Distinctive:

    When running or debugging End-to-End (E2E) tests:

    line 46
  11. Distinctive:

    Isolation: Ensure tests run in complete isolation (dedicated test accounts/data).

    line 48

≈ “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

Test Runner

Use this skill to execute tests and understand why they might be failing.

Inputs

  • Test Command: (Optional) Override defaults (e.g., npm test -- -t "search").
  • Scope: Specific file or all tests.

Tooling Strategy

  • Use run_command to execute tests.
  • Use view_file to read failure logs or source code if tests fail.

Workflow

1. Execution

  • Command: Run the appropriate test command for the environment (e.g., npm test, pytest, python -m unittest).
  • Scope: Run all tests by default, or target a specific file if requested.

2. Analysis

  • Pass: If all green, celebrate! 🟢
  • Fail: If red 🔴, analyze the output:
    • StackTrace: Where exactly did it blow up?
    • Assertion: What was expected vs. what was received?
    • Diff: Visual comparison of the data mismatch.

3. Recommendation

  • If tests failed, provide a summary of the failure.
  • Suggest potential fixes or point to the line of code causing the regression.

4. Integrity

  • Ensure that the testing process didn't leave behind artifacts (temp files, database entries) unless intended for debugging.

E2E Testing Patterns (Advanced)

When running or debugging End-to-End (E2E) tests:

  • Isolation: Ensure tests run in complete isolation (dedicated test accounts/data). Do not run destructive tests against production.
  • Flakiness: Debug flaky tests by checking for race conditions, unstable DOM selectors, or implicit waits rather than explicit waits.
  • Tracing: Utilize artifacts (screenshots, video recordings, network traces) captured during CI/CD failures to reconstruct the test state.
  • Critical Journeys: Focus E2E tests on critical user journeys rather than exhaustive edge-case testing (which belongs in unit tests).

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