agentleFS
Sign inStart free
ndisisndndisisnd/msg/.claude/skills/plan-review/SKILL.md

plan-review

Skill6 starsChanged 4 months agoMITView on GitHub

Staff PM contract certifier. Reads an existing PRD and runs a fixed seven-check certification, each check tied to a named downstream consumer. Picks the product check or the eng check from the PRD's content, auto-fixes every Critical and Major, logs Minors without asking, and stops only for a product decision. Writes one AHA learning per auto-fixed Critical/Major so the next plan-pm draft self-heals, logs findings to reports/review-prd-[n]-[slug].md, and ends with one result block. Use it when the user says "certify the PRD", "review the PRD", "check the PRD before plan-em", or invokes /plan-review.

43 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use plan-execute, pr-comment and 10 more.

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.
  • longranger2Skill

    plan-execute

    Use when the user says "/plan-execute", "plan execute", "implement plan", or "execute plan" and provides a finalized plan file path to carry out. Claude orchestrates, Codex writes code, Claude reviews, and Codex fixes issues until the quality bar is met.

    Also in 3 projects that use this

  • BenjaminGSkill

    pr-comment

    This skill should be used when reviewing someone else's pull request and you want drafted review comments posted to GitHub — either gate / gate-wf findings (tier-marked) or pr-challenge's reviewer questions (unmarked) — each drafted through humanizer and posted as a standalone inline comment at its file:line, after one confirmation. Triggers on "post these as review comments", "comment the gate findings on the PR", "draft and post my review", "leave review comments", after a gate / gate-wf run or a pr-challenge pass on a PR you're reviewing.

    Also in 3 projects that use this

  • MicrosoftSkill

    spec-review

    Independent, multi-model review of a design or spec **before** any code is written, for the microsoft/winappcli repo. Activate when a contributor asks to "review this spec", "review my design", "review this design doc", "validate this approach", "should we build this", "spec review", "design review", or "feature review". Fans out parallel sub-agents — each doing its OWN research against the real codebase and ecosystem rather than trusting the spec — covering necessity & scope, approach & alternatives, feasibility vs reality, risks & unknowns, DX & user impact, and a different-model-family cross-check. Emits a decision-oriented recommendation (proceed / proceed-with-changes / reconsider) to stdout. This is the PRE-CODE companion to the pr-review skill (which reviews code already written); use spec-review at the design/spec stage, not on an implemented diff. Does NOT write code or edit the spec.

    Also in 3 projects that use this

  • AnthropicSkill

    office-hours

    Set up and run Claude Code office hours, including the calendar event when the champion's own calendar connector allows it. Use when a champion wants a regular time for teammates to bring problems.

    Also in 3 projects that use this

  • AWSSkill

    retro

    Conduct a retrospective on a coding session.

    Also in 5 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 5 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 35 edited versions we read keep these.

  • 1

    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:

    Never interview the user. The only question is one batched product-decision pause.

    line 35
  2. Very specific:

    Follow refs/protocol-review.md end to end — Steps 1–3 (resolve and select → certify → fix, record, stamp, report).

    line 58

“Common” is measured: kept by at least 6 in 10 of the 35 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

plan-review

Usage

Invoke: /plan-review [prd-path] — a manual step the user can run at any time.

  • Natural language: "certify the PRD", "review the PRD", "run the contract certifier", "check the PRD before plan-em"
  • Context: a path to an existing PRD .md file, or a run right after plan-pm or plan-em saved one
  • plan-pm and plan-em run it at the end of their run when their auto-review switch is on, and plan-em runs it before engineering when the PRD has no stamp.

The skill picks the product check (checks 1, 2, 3, 6) or the eng check (checks 2, 4, 5, 6, 7) by itself. refs/certification.md owns the checks, the severity rubric and the findings-table schema. Scripts handle PRDs written before v5.4.

Posture

A certifier, not an adversarial reviewer: run the selected check's subset and nothing else — no check without a consumer. Never interview the user. The only question is one batched product-decision pause.

Inputs

NameFormatRequiredSource
PRD file path.md file matching features/prd-*/prd-*.mdYes (asked if missing)User message, or the skill that ran it
devkit/ filesAHA.md, OPEN-QUESTIONS.md, PLATFORMS.mdNoEach is used when present and skipped silently when absent. No devkit/ at all ⇒ setup runs by itself first (/msg --init, then this command — ../shared/refs/setup-first.md)

Outputs

NameDestination
Findings ledger<prd-dir>/reports/review-prd-[n]-[slug].md, written by script-ledger.py once, after the fixes
Revised PRDRESOLVED_PATH — every Critical/Major fix, and the normalised Open questions table
Certification stampPRD frontmatter, via script-prd-stamp.sh --certify — written only when no Critical stays open
Self-healing learningsdevkit/AHA.md, one [tune:<category>] entry per auto-fixed Critical/Major
Result blockInline, at the end of the run (refs/protocol-review.md Step 3)

The stamp is the gate, the report is the evidence. script-cert-status.sh and plan-em read the stamp and the open Criticals in the report.

Step-by-step protocol

Follow refs/protocol-review.md end to end — Steps 1–3 (resolve and select → certify → fix, record, stamp, report).

Closing message: end every run with the closing message per ../shared/refs/closing-message.md, after the result block. When plan-em runs this skill inline, plan-em's digest carries the result and plan-em closes the run.

Harness incidents: log unexpected script failures, tool errors, retries and missed writes to devkit/DOCTOR.md per ../shared/refs/doctor-logging.md.

References

  • refs/protocol-review.md — the three-step protocol
  • refs/certification.md — the seven checks, consumers, severity rubric, findings-table schema, AHA categories
  • .claude/scripts/ — script-cert-preflight.sh (path + check type), script-cert-mech.py (checks 4, 5, 6 structure), script-ledger.py (the ledger), script-prd-stamp.sh --certify (the stamp), script-aha.sh · script-openq.sh (devkit writers)

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