agentleFS
Tngc93Tngc93/product-management-skills/skills/review-spec/SKILL.md

review-spec

Skill0 starsChanged 34 days agoMITView on GitHub

Review a PRD, spec, one-pager or set of stories the way a demanding senior PM, engineer and designer would, and return prioritised, specific feedback with suggested rewrites. Use when the user asks to review, critique, sanity-check, tighten or "poke holes in" a product document, or before a spec goes to engineering or leadership.

18 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use create-spec.

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.
  • srobinsonSkill

    create-spec

    Create a task specification (SPEC.md) through interactive requirements elicitation. Use when helping users define what they want to build before autonomous execution begins.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 17 edited versions we read keep these.

  • 1

    Distinctive

    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:

    Run pm-skills lint <file> (add --type prd, stories, criteria or update if the type is not detected).

    line 14
  2. Very specific:

    Start from pm-skills template review-spec.

    line 24
  3. Distinctive:

    Do not rewrite the whole document unless asked.

    line 29

“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 a product document

Your job is to find what will cause rework, arguments or a failed launch, while it is still cheap to fix. Be direct and specific. Praise only what the author should keep doing.

CLI: node "${CLAUDE_PLUGIN_ROOT}/cli/pm-skills.mjs" (or ../../cli/pm-skills.mjs relative to this file). Below, pm-skills.

1. Run the mechanical checks first

Run pm-skills lint <file> (add --type prd, stories, criteria or update if the type is not detected). Its findings go in your review as-is, grouped, so you can spend your attention on judgment.

2. Read as three people

  • Engineer: Can I estimate this? Which requirement is ambiguous, contradictory or missing an edge case? What dependency or data migration is unmentioned? What will be hard that the doc treats as easy?
  • Designer / user: Is the problem real and evidenced? Is the user's journey clear end to end, including errors and empty states? Who is left out?
  • Executive: Why now? How will we know it worked: is the success metric the right one, with a baseline and a date? What does it cost, and what are we not doing instead? What is the riskiest assumption, and is there a cheap way to test it first?

3. Write the review

Start from pm-skills template review-spec. Rules:

  • Order findings by impact: Blocking (must fix before work starts), Important (fix before launch), Minor (polish).
  • Each finding quotes or points to the exact place, explains the consequence if left as is, and proposes a concrete rewrite or question.
  • Limit to the 10 findings that matter most. A review with 40 comments gets none of them fixed.
  • Do not rewrite the whole document unless asked. Do not change the author's decisions; challenge them with reasons.
  • End with the three questions the author should be able to answer before the next review.

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.