agentleFS
Sign inStart free
xiaolaixiaolai/vmark/.claude/skills/plan-verify/SKILL.md

plan-verify

Skill851 starsChanged 29 days agoISCView on GitHub

Verify a completed implementation against a plan by running gates and checking acceptance criteria. Use when the user asks to verify work items or confirm completion.

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If unclear, ask for the plan path.

    line 16
  2. Very specific:

    Use repo-specific gates from .claude/commands/feature-workflow.md or plan “Testing Procedures”.

    line 25
  3. Distinctive:

    If tests are not runnable, note the blocker explicitly.

    line 26
  4. Distinctive:

    Always run tests unless the user explicitly forbids it.

    line 50
  5. Distinctive:

    If tests are skipped or fail, mark WI as Blocked.

    line 51
  6. Distinctive:

    Do not claim “verified” without test evidence.

    line 52

≈ “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

Plan Verify

Overview

Runs the plan’s required tests/gates and validates acceptance criteria, producing a pass/fail verification report.

Workflow (Verify)

  1. Locate the plan
    • Prefer dev-docs/plans/<plan>.md.
    • If unclear, ask for the plan path.
  2. Extract verification checklist
    • For each WI, list:
      • Acceptance criteria
      • Required tests
      • Manual checks (if any)
  3. Run gates
    • Use repo-specific gates from .claude/commands/feature-workflow.md or plan “Testing Procedures”.
    • If tests are not runnable, note the blocker explicitly.
  4. Verify acceptance
    • For each WI, mark each acceptance criterion as Pass/Fail/Blocked.
    • Include evidence (test output, file refs, manual steps).
  5. Report results
    • Summarize pass/fail with concrete next actions.

Output Format (required)

  • Verification Summary
    • Total WIs verified
    • Pass/Fail/Blocked counts
  • Gate Results
    • Command → status
    • Failures with key error lines
  • Acceptance Matrix
    • WI‑### → criterion → Pass/Fail/Blocked
  • Manual Checks
    • Steps executed + outcome

Verification Rules

  • Always run tests unless the user explicitly forbids it.
  • If tests are skipped or fail, mark WI as Blocked.
  • Do not claim “verified” without test evidence.
  • Manual checks must include evidence (step list + observed result).

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.

Reviews can't be read right now.

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