agentleFS
Sign inStart free
jon-devlapazjon-devlapaz/agentic-se-skills/.agents/skills/verification-planner/SKILL.md

verification-planner

Skill7 starsChanged 6 months agoMITView on GitHub

Use when planning tests, inspections, analyses, demonstrations, trace matrices, or proof that a built artifact meets specified requirements.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Use this skill to prove specified requirements were met with reproducible evidence.

    line 8
  2. Distinctive:

    Run or specify the narrowest reliable proof first, then broader regression checks.

    line 17
  3. Very specific:

    Start with references/source-grounding.md, then inspect Section 5.3 pages extraction/pages/page_098.md through extraction/pages/page_109.md …

    line 23

≈ “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

Verification Planner

Use this skill to prove specified requirements were met with reproducible evidence.

Workflow

  1. List each requirement and its acceptance criteria.
  2. Select one primary verification method per requirement: test, inspection, analysis, or demonstration.
  3. Define procedure, expected result, responsible verifier, and evidence artifact.
  4. Include negative or edge evidence when failure mode matters.
  5. Build a requirements-to-verification matrix with requirement ID, method, command/procedure, expected result, evidence, and status.
  6. Run or specify the narrowest reliable proof first, then broader regression checks.
  7. State explicitly what verification does not prove about user intent or operational fit.
  8. Hand intended-use questions to validation-planner.

Source grounding

Start with references/source-grounding.md, then inspect Section 5.3 pages extraction/pages/page_098.md through extraction/pages/page_109.md and Appendix D pages extraction/pages/page_211.md through extraction/pages/page_212.md before making verification-specific claims.

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