agentleFS
antjeantje/product-school-claude-code-for-pms/.claude/skills/review-checklist/SKILL.md

review-checklist

Skill0 starsChanged 54 days agoMITView on GitHub

Checks a product brief or one-pager for the six things a brief must cover before it goes any further. Use when asked to review, check or run review-checklist on a brief, a one-pager, or a folder of them. Reports one line per criterion and quotes the text behind every flag.

8 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions8 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 8

    1. nearai/ironclaw★ 13ksame name
    2. clidey/whodb★ 5.1ksame name
    3. microsoft/GHCP-Lab★ 45same name
    4. vospr/context-engineering-template★ 9same name
    5. matejformanek/postgres-claude★ 1same name
    6. SohrabZ/buzz-agent-teams★ 1same name
    7. markbaindesign/bain-studio★ 0same name
    8. qrqr2100/ship-gate-kit★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 5

    Distinctive

    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:

    Check a brief against six criteria and report what is missing.

    line 8
  2. Distinctive:

    Check each one against the brief's own text.

    line 18
  3. Distinctive:

    Does not apply to numbers the brief is *proposing*, like a threshold or a target.

    line 42
  4. Distinctive:

    Do not fix the brief. Report only.

    line 72
  5. Distinctive:

    Do not flag style, length or tone.

    line 73
  6. Very specific:

    If a criterion genuinely does not apply, say n/a rather than passing it.

    line 74

“Common” is measured: kept by at least 6 in 10 of the 8 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-checklist

Check a brief against six criteria and report what is missing. Same check every time, whoever runs it.

What to point it at

A single file, or a folder. For a folder, check every .md and .txt file in it, one after another, and total the flags at the end.

The six criteria

Check each one against the brief's own text. Pass or flag, nothing in between.

  1. Names who owns it. A named person or team who is responsible for the work getting done. Flag if the brief only says who has to decide things, or parks it for "whoever picks it up", or leaves the owner blank.
  2. Says how we'll know it worked. Something observable that would move if the work succeeded, and would not move if it failed. Flag if the brief describes what gets built but never what changes as a result. Also flag a measure that could move for another reason: fewer complaints, for instance, also happens when the people affected stop complaining.
  3. The scope at the end matches the scope at the start. Compare what the opening says is being built with what the rest of the brief says. Flag if items get added along the way, or if something the opening endorses is never placed in or out of scope.
  4. Explains the problem before it proposes a fix. Flag if the solution appears before the reader knows what is wrong.
  5. Every number used as evidence says where it came from. A number that supports the argument needs a source the reader could reopen: a file, a ticket, a named report, or one line pointing to where the evidence lives. Does not apply to numbers the brief is proposing, like a threshold or a target. Flag if evidence numbers appear with no way to check them.
  6. Anything not yet known is written as a question, not as a fact. That includes results from a model, a simulation or a forecast: the assumption they depend on belongs beside them. Flag an assumption, estimate, modelled result or prediction stated as if it were observed. This is how an unchecked guess ends up in someone else's decision.

How to report

For each brief, this exact shape:

<filename>
  owner named ................... yes | NO: flagged
  success measure ............... yes | NO: flagged
  scope stays bounded ........... yes | NO: flagged
  problem stated before fix ..... yes | NO: flagged
  evidence numbers sourced ...... yes | n/a | NO: flagged
  unknowns written as unknowns .. yes | NO: flagged
  -> N flags: <one line per flag, quoting the words that caused it>

Then one closing line: <n> briefs checked, <n> flagged, <n> flags total.

Rules

  • Quote the brief. Every flag names the exact words that caused it, so the author can find it in seconds.
  • Do not fix the brief. Report only. The author decides what to change.
  • Do not flag style, length or tone. Only the six criteria.
  • If a criterion genuinely does not apply, say n/a rather than passing it.

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.