agentleFS
sourjyasourjya/kiro-rails/.claude/skills/spec-verify/SKILL.md

spec-verify

Skill9 starsChanged 4 months agoMITView on GitHub

Verify a completed implementation against its spec. Checks all acceptance criteria, runs tests, validates coverage. Use after spec-implement is done.

9 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use grill-me and handoff.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • GoogleSkill

    grill-me

    A relentless interview to sharpen a plan or design.

    Also in 3 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 4

    Distinctive

    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:

    Verify that a completed implementation satisfies its spec.

    line 8
  2. Distinctive:

    After checking, append a verification section to the spec folder:

    line 45
  3. Distinctive:

    Check tests exist: - don't just trust that code works.

    line 72
  4. Distinctive:

    Flag scope creep: - if implementation added things not in the spec, note it

    line 73

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “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

Spec Verify Workflow

Verify that a completed implementation satisfies its spec.

Steps

  1. Read the spec - load requirements.md and design.md
  2. Run verification checks against each requirement
  3. Generate a verification report
  4. Flag any gaps for remediation

Verification Checklist

For each requirement in requirements.md:

Functional Verification

  • Every acceptance criterion has a passing test
  • Edge cases identified in design.md are handled
  • Error paths are tested (not just happy path)

Non-Functional Verification

  • Performance requirements met (if specified)
  • Security requirements met (no secrets, proper auth, input validation)
  • Accessibility requirements met (if frontend)

Code Quality

  • Tests pass (npm test / pytest / equivalent)
  • Type checking passes (if applicable)
  • No lint errors
  • No hardcoded values that should be configurable

Documentation

  • Code comments explain WHY, not WHAT
  • API changes documented
  • ADR written if architectural decisions were made
  • Changelog entry added

Verification Report

After checking, append a verification section to the spec folder:

<!-- Append to tasks.md -->

## Verification Results

**Date:** YYYY-MM-DD
**Status:** ✅ PASSED | ⚠️ PARTIAL | ❌ FAILED

### Requirements Coverage
| Requirement | Status | Notes |
|-------------|--------|-------|
| REQ-1 | ✅ | All criteria met |
| REQ-2 | ⚠️ | Missing edge case test |

### Gaps Found
- Gap 1: ...
- Gap 2: ...

### Recommendation
Ready for archive / Needs remediation on: ...

Rules

  1. Be strict - a requirement is only "met" if ALL its acceptance criteria pass
  2. Check tests exist - don't just trust that code works; verify tests cover it
  3. Flag scope creep - if implementation added things not in the spec, note it
  4. Recommend next step - either spec-archive (if passed) or remediation tasks

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.