review-pr-judgment SKILL.md skillA

review-pr-judgment from doodledood/manifest-dev is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add doodledood/manifest-dev/review-pr-judgment@git:20261025.752eae1

Pins git:20261025.752eae1 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
doodledood/manifest-dev
Path
claude-plugins/manifest-dev-tools/skills/review-pr-judgment/SKILL.md
Versions recorded
5
Latest version
git:20261025.752eae1, committed Oct 25, 2026
First version recorded
Sep 3, 2026
Size
7,992 bytes
Repository stars
77
License
MIT

Called by review-pr in both of its modes: the whole-PR premise check that asks whether a change earns its keep against the pain it solves, firing only on concrete evidence and returning non-blocking author-facing questions, one per root, with no severity. Not for direct use.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# review-pr-judgment

The reviewer-fleet dimensions find defects inside a change whose intent is taken as given — they judge implementation against explicit requirements and weigh the author's rationale as evidence. The judgment pass adds the one thing they structurally cannot: it asks whether the change **earns its keep** — whether it should exist, in this shape, at this footprint, given the pain it claims to solve.

**The single question:** *Does this change — its existence, its approach, and its footprint — earn its keep against the pain it solves, and is anything the pain requires missing?*

It runs as a **wide-context pass**. **Receives:** the PR description, the PR conversation, the codebase direction, the **full PR-head diff** (`base..head`, the whole PR), and, in manifest mode, the manifest's Intent as the stated pain. It is **non-blocking**: every finding is a question the author answers, never a gate. The caller decides where this runs and gates fresh generation to once per PR; this skill only judges and returns.

## Altitude — whole-PR only
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add doodledood/manifest-dev/review-pr-judgment@sha256:b8471e606ac6d14e

The line at the top of this page pins the label git:20261025.752eae1, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_p5plb5jsw337evsw.svg)](https://markdownregistry.com/a/art_p5plb5jsw337evsw)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Sep 3, 2026 and Oct 25, 2026, about one every 13 days.

versioncommittedcommitsizeaudit
git:20261025.752eae1 latest2026-10-25 752eae1 7,992 BA view · diff
git:20261024.0f76d8e2026-10-24 0f76d8e 8,010 BA view · diff
git:20260926.22b28872026-09-26 22b2887 8,065 BA view · diff
git:20260905.7f3e60f2026-09-05 7f3e60f 7,965 BA view · diff
git:20260903.fce7e902026-09-03 fce7e90 8,088 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7992 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

doodledood/manifest-dev · 77 stars · license MIT · pushed 2026-11-03 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_p5plb5jsw337evsw
GET https://markdownregistry.com/api/v1/resolve?ref=doodledood/manifest-dev/review-pr-judgment
GET https://markdownregistry.com/api/v1/blob/b8471e606ac6d14e6238c9153ff8b2728304a4bd52f723ee6e33d158f7cbbf24

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from doodledood/manifest-dev

harden-task-file SKILL.md skill
doodledood/manifest-dev · .claude/skills/harden-task-file/SKILL.md · Harden a manifest-dev task guidance file for one-shot quality — either /define''s quality-gate/Default set or…
git:20260727.0d4eb6e · audit A · 77 stars
learn-from-session SKILL.md skill
doodledood/manifest-dev · .claude/skills/learn-from-session/SKILL.md · Analyze Claude Code sessions to learn what went right/wrong and suggest high-confidence improvements to skills. Use…
git:20260705.5879381 · audit A · 77 stars
sync-claude-code-plugins SKILL.md skill
doodledood/manifest-dev · .claude/skills/sync-claude-code-plugins/SKILL.md · Sync the prompt-engineering plugin from a local clone of claude-code-plugins into .claude/ so the repo is…
git:20260904.63307b7 · audit A · 77 stars
sync-tools SKILL.md skill
doodledood/manifest-dev · .claude/skills/sync-tools/SKILL.md · Regenerate the Codex distribution copy of the plugin skills, and the copies of the shipped verify tool, and check them…
git:20261021.a5511e4 · audit A · 77 stars
AGENTS.md AGENTS.md file
doodledood/manifest-dev · AGENTS.md
git:20260519.0a93ea2 · audit B · 77 stars
CLAUDE.md CLAUDE.md file
doodledood/manifest-dev · CLAUDE.md
git:20261102.c204d29 · audit A · 77 stars
example SKILL.md skill
doodledood/manifest-dev · claude-plugins/PLUGIN_TEMPLATE/skills/example/SKILL.md · Analyzes the current project structure and tech stack. Use when asked to explore, understand, or summarize a project…
git:20260515.229b90c · audit A · 77 stars
babysit-pr SKILL.md skill
doodledood/manifest-dev · claude-plugins/manifest-dev-tools/skills/babysit-pr/SKILL.md · Author-side PR lifecycle babysitter and companion to review-pr. Use when the user wants to tend an existing GitHub PR…
git:20261025.752eae1 · audit A · 77 stars
eli5 SKILL.md skill
doodledood/manifest-dev · claude-plugins/manifest-dev-tools/skills/eli5/SKILL.md · Explain a topic like I'm a 5 year old. Use when the user types /eli5 <topic> or asks for a dead-simple picture…
git:20260916.6062505 · audit A · 77 stars
handoff SKILL.md skill
doodledood/manifest-dev · claude-plugins/manifest-dev-tools/skills/handoff/SKILL.md · Produce a self-contained context payload that lets a fresh agent continue without re-deriving what this session…
git:20261025.752eae1 · audit A · 77 stars
prompt-engineering SKILL.md skill
doodledood/manifest-dev · claude-plugins/manifest-dev-tools/skills/prompt-engineering/SKILL.md · Create, update, review, or discuss an LLM prompt — a system prompt, a skill, or an agent. Use when writing or improving…
git:20261031.1cf2a1f · audit A · 77 stars
review-pr-holistic SKILL.md skill
doodledood/manifest-dev · claude-plugins/manifest-dev-tools/skills/review-pr-holistic/SKILL.md · Called by review-pr after its reviewer fleet and judgment pass return: consolidates their findings against the PR''s…
git:20261025.752eae1 · audit A · 77 stars

Every file in doodledood/manifest-dev

Browse by kind, by grade A, or by owner.