agentleFS
alex-voloshin-devalex-voloshin-dev/ai-skills/.agents/skills/qa/SKILL.md

qa

Skill2 starsChanged 6 months agoMITView on GitHub

Quality assurance workflow for validating features, writing or improving tests, reporting bugs, and checking coverage or acceptance criteria.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this workflow for verification and test quality work.

    line 10
  2. Distinctive:

    Check happy path, edge cases, and error paths

    line 38
  3. Distinctive:

    Write a structured report with expected vs actual behavior

    line 45
  4. Distinctive:

    Write or improve tests using the project's existing patterns

    line 50
  5. Distinctive:

    Prefer deterministic tests and narrow scope first

    line 51

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

QA

Use this workflow for verification and test quality work.

1. Determine the QA Task

Classify the request as one of:

  • Feature verification
  • Bug report
  • Test creation
  • Test improvement
  • Exploratory testing
  • Coverage review

2. Gather Context

Read:

  1. TESTING.md if present
  2. Root AGENTS.md
  3. Relevant scoped AGENTS.md
  4. Feature brief, bug report, or changed code in scope
  5. Existing tests for the target area

3. Execute the Task

Feature Verification

  • Map acceptance criteria to observable behavior
  • Check happy path, edge cases, and error paths
  • Record pass, fail, or partial status with evidence

Bug Report

  • Reproduce the issue
  • Capture logs, errors, and minimal repro
  • Write a structured report with expected vs actual behavior

Test Creation or Improvement

  • Identify coverage gaps
  • Write or improve tests using the project's existing patterns
  • Prefer deterministic tests and narrow scope first

Exploratory Testing

  • Identify risky or recently changed areas
  • Explore happy path, invalid input, state transitions, and regressions
  • Record issues with severity and reproduction steps

Coverage Review

  • Review current coverage signals
  • Identify important untested logic
  • Recommend the next highest-value tests

4. Apply the Quality Gate

Check:

  • Existing tests still pass
  • New tests are deterministic
  • Acceptance criteria are covered where relevant
  • Bug reports include evidence and reproduction steps

5. Report

Summarize:

  • What was tested
  • Issues found
  • Tests added or improved
  • Coverage impact if relevant
  • Recommended next steps

Integration

  • Companion skills: test-strategy, run-tests, test-local
  • Common follow-up: bugfix, feature-dev, pre-commit

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.