critical-review SKILL.md skillA

critical-review from kimon1230/claude_extensions is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add kimon1230/claude_extensions/critical-review@git:20261017.4295233

Pins git:20261017.4295233 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
kimon1230/claude_extensions
Path
skills/critical-review/SKILL.md
Versions recorded
5
Latest version
git:20261017.4295233, committed Oct 17, 2026
First version recorded
Mar 28, 2026
Size
5,856 bytes
Repository stars
4
License
MIT

Delivers structured, adversarial feedback on a plan or design document, surfacing risks and gaps before implementation. Use when the user wants a plan or document reviewed.

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

# Critical Review

This skill must only be invoked from the main session, never from a subagent.

1. **Identify the target document:**
   a. If the user specified a file path or plan name, use that.
   b. Else determine the project name: check `origin` git remote (parse last path component, strip `.git`) → git root basename → working directory basename. If ambiguous, ask the user.
   c. List files in `~/.claude/plans/<project-name>/`, sorted by modification time (most recent first). If the directory does not exist or contains no `.md` files, tell the user: "No plan files found in `~/.claude/plans/<project-name>/`. Please specify a file path to review." and stop.
   d. Confirm with the user: "I'll review `<filename>`. Correct?"

2. **Round 1 — Spawn 4 parallel subagents** (all four on the **latest, most capable model** — omit the `model` override so each inherits the session model rather than pinning a version-specific name; plan adjudication is precision work where a weaker model's false positives cost more verification time than the savings, so don't downgrade to a cheaper tier; `CLAUDE_CODE_SUBAGENT_MODEL` overrides if set):
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add kimon1230/claude_extensions/critical-review@sha256:179d39f04fbf2620

The line at the top of this page pins the label git:20261017.4295233, 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_lqyall77nillaqrd.svg)](https://markdownregistry.com/a/art_lqyall77nillaqrd)

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

Versions

The registry has recorded 5 versions of this file, between Mar 28, 2026 and Oct 17, 2026, about one every 51 days.

versioncommittedcommitsizeaudit
git:20261017.4295233 latest2026-10-17 4295233 5,856 BA view · diff
git:20260613.52a9e602026-06-13 52a9e60 5,766 BA view · diff
git:20260612.980fadd2026-06-12 980fadd 5,507 BA view · diff
git:20260528.a8e05a22026-05-28 a8e05a2 5,483 BA view · diff
git:20260328.45cd5d22026-03-28 45cd5d2 5,178 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 (5856 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

kimon1230/claude_extensions · 4 stars · license MIT · pushed 2026-10-18 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_lqyall77nillaqrd
GET https://markdownregistry.com/api/v1/resolve?ref=kimon1230/claude_extensions/critical-review
GET https://markdownregistry.com/api/v1/blob/179d39f04fbf2620ccc4f4c637780e5ffe11905e42104fe4d2f6daa622f31fbc

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 kimon1230/claude_extensions

CLAUDE.md CLAUDE.md file
kimon1230/claude_extensions · CLAUDE.md
git:20261018.71d0efa · audit A · 4 stars
code-review SKILL.md skill
kimon1230/claude_extensions · skills/code-review/SKILL.md · Reviews code for design, correctness, performance, and test quality. Use when the user wants a code review of files, a…
git:20261017.4295233 · audit A · 4 stars
implement-batch SKILL.md skill
kimon1230/claude_extensions · skills/implement-batch/SKILL.md · Implements the next batch of an existing plan, orchestrating subagents with test and lint validation. Use when the user…
git:20261017.4295233 · audit A · 4 stars
save SKILL.md skill
kimon1230/claude_extensions · skills/save/SKILL.md · Checkpoints session progress to status tracking files. Use to save state mid-session, after a major task, before…
git:20261017.4295233 · audit A · 4 stars
security-audit SKILL.md skill
kimon1230/claude_extensions · skills/security-audit/SKILL.md · Audits code for security vulnerabilities — injection, auth and access control, crypto, secrets, SSRF, and insecure…
git:20261017.4295233 · audit A · 4 stars

Every file in kimon1230/claude_extensions

Other files named critical-review

critical-review SKILL.md skill
yeisonrestrepo/code-conductor · skills/critical-review/SKILL.md · 4-phase adversarial review protocol: pre-flight analysis, adversarial execution check, self-correction loop, and…
git:20260922.8fd811c · audit A · 17 stars

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