agentleFS
Sign inStart free
wedabrowedabro/bro-skills/.agents/skills/speckit.tester/SKILL.md

speckit.tester

Skill3 starsChanged 45 days agoMITView on GitHub

Test Runner & Coverage - Design and run evidence-backed tests for requirements, regressions, and failure paths.

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read source, spec, plan, tasks, existing tests, test config, and constitution.

    line 10
  2. Very specific:

    Write .agents/memory/test-report.md with commands, environment, results, coverage scope, failures, and untested risks.

    line 11
  3. Distinctive:

    Prefer existing test conventions and the smallest meaningful unit, integration, contract, browser, or property test.

    line 15
  4. Distinctive:

    Run configured tests in Docker when required.

    line 17
  5. Distinctive:

    Never weaken assertions or delete a failing test to obtain green results.

    line 19
  6. Distinctive:

    Every applicable requirement has passing evidence or a named blocker.

    line 22
  7. Distinctive:

    Do not claim 100% coverage from a partial suite.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Mission

Prove implementation behavior against spec criteria and risk, with meaningful coverage rather than a vanity percentage.

Inputs and Outputs

  • Read source, spec, plan, tasks, existing tests, test config, and constitution.
  • Write .agents/memory/test-report.md with commands, environment, results, coverage scope, failures, and untested risks.

Protocol

  1. Map each scenario, requirement, changed path, side effect, permission boundary, and failure mode to a test or explicit N/A reason.
  2. Prefer existing test conventions and the smallest meaningful unit, integration, contract, browser, or property test; avoid mocks that remove the behavior under test.
  3. Cover happy, invalid, boundary, empty, timeout/retry, authorization, idempotency, concurrency, and recovery paths as applicable.
  4. Run configured tests in Docker when required; record exact command, exit code, duration, and relevant logs. Run focused tests first, then the full gate.
  5. Report pass/fail separately from line/branch coverage. Explain exclusions and distinguish untested code from unreachable code.
  6. Never weaken assertions or delete a failing test to obtain green results.

Completion Gate

Every applicable requirement has passing evidence or a named blocker; failed and untested areas are listed with next action.

Guard Rails

Do not claim 100% coverage from a partial suite. Do not change production code while acting as tester unless the user explicitly switches to implementation.

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