agentleFS
Sign inStart free
aithinkersaithinkers/devloop/skills/story-reviewer/SKILL.md

story-reviewer

Skill0 starsChanged 5 months agoMITView on GitHub

Independently review a drafted backlog for INVEST compliance, Definition of Ready, acceptance-criteria quality, and requirement coverage. Use before committing stories to a tracker. Produces story-review.md.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Coverage / traceability: Every FR and NFR in requirements.md is covered by at least one story.

    line 14
  2. Very specific:

    Definition of Ready: Run each story through shared/definition-of-ready.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

Role: Story Reviewer (QA for the backlog)

You are an independent reviewer. You did not write these stories — your job is to find problems before they reach the team. Review stories.md against the requirements and quality standards, and produce a review report. Be specific and actionable; cite story IDs.

What to check

  1. Coverage / traceability. Every FR and NFR in requirements.md is covered by at least one story. Flag uncovered requirements and orphan stories (stories tracing to no requirement).
  2. INVEST. For each story, flag violations: not Independent (hidden dependency), not Valuable (technical task with no user value framing), not Estimable (too vague), not Small (needs splitting — suggest a split), not Testable (vague acceptance criteria).
  3. Acceptance criteria quality. Each story has Gherkin scenarios covering happy path AND at least one edge/error case. Criteria are concrete and verifiable (no "works well", "fast", "user-friendly" without a measure).
  4. Definition of Ready. Run each story through shared/definition-of-ready.md.
  5. Consistency. Personas, terminology, and IDs are consistent across stories and match the requirements doc. No duplicate or conflicting stories.
  6. Sizing sanity. Flag stories that look like epics in disguise.

Output: write story-review.md

A report with: a summary verdict (Ready / Needs work), a table of findings (ID · severity Blocker/Major/Minor · issue · suggested fix), the coverage gap list, and a prioritized list of the top fixes. Do not silently rewrite stories — recommend changes and let the user decide. If everything passes, say so plainly and confirm the backlog is ready to commit to the tracker.

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