agentleFS
Sign inStart free
Codagent-AICodagent-AI/agent-skills/skills/review-spec/SKILL.md

review-spec

Skill31 starsChanged 6 months agoMITView on GitHub

Reviews proposal, specification, design, and task artifacts for internal consistency, testability, traceability, and cross-artifact alignment. Use when asked to review a spec, review artifacts, check design documents, check a change for consistency, or verify artifact quality before implementation.

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 17 edited versions we read keep these.

  • 3

    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:

    Read all relevant markdown artifacts and infer their roles from path and content.

    line 11
  2. Distinctive:

    Every finding must cite the exact path and section.

    line 24
  3. Distinctive:

    Do not critique product intent or architecture, search for missing behavior or failure-mode decisions, review implementation code, invent …

    line 27

“Common” is measured: kept by at least 6 in 10 of the 17 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

Review Spec

Review the supplied planning artifacts for internal coherence, structural testability, traceability, and cross-artifact consistency. Accept product and design choices as written; consequential gaps, alternatives, and weak decisions belong to an approach review.

Read all relevant markdown artifacts and infer their roles from path and content. Missing artifact types are not findings.

Check applicable concerns:

  • contradictions, scope drift, dropped commitments, or terminology drift across artifacts;
  • behavioral requirements without a concrete testable scenario, scenarios that do not express their requirement, or unresolved placeholders;
  • tasks that are not self-contained, lack exact source citations, alter source acceptance criteria, over-prescribe implementation, retain placeholders, or separate ordinary infrastructure, tests, or docs from the behavior they support; and
  • contradictions or unresolved references within an artifact.

Every finding must cite the exact path and section. Recommend the smallest consistency-preserving fix when more than one is possible.

Do not critique product intent or architecture, search for missing behavior or failure-mode decisions, review implementation code, invent missing artifacts, or rewrite the artifacts.

## Findings

### [high|medium|low] <title>
- Artifact: <path and section>
- Issue: <consistency, testability, traceability, or coherence defect>
- Fix: <smallest safe correction>

## Assessment
<Artifact readiness, or "No findings.">

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