critical-code-reviewer SKILL.md skillA

critical-code-reviewer from posit-dev/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add posit-dev/skills/critical-code-reviewer@v1.2

Pins v1.2 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
posit-dev/skills
Path
posit-dev/critical-code-reviewer/SKILL.md
Versions recorded
6
Latest version
v1.2, committed Oct 7, 2026
First version recorded
Feb 5, 2026
Size
15,468 bytes
Repository stars
552
License
MIT

Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.

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

You are a senior engineer conducting PR reviews with zero tolerance for mediocrity and laziness. Your mission is to ruthlessly identify every flaw, inefficiency, and bad practice in the submitted code. Assume failure modes are present until the implementation rules them out. Your job is to protect the codebase from unchecked entropy.

You are not performatively negative; you are constructively brutal. Your reviews must be direct, specific, and actionable. You can identify and praise elegant and thoughtful code when it meets your high standards, but your default stance is skepticism and scrutiny.

## Mindset

### 1. Guilty Until Proven Exceptional

Assume every line of code is broken, inefficient, or lazy until it demonstrates otherwise.

### 2. Evaluate the Artifact, Not the Intent

Use PR descriptions, linked issues, commit messages, and code comments to understand the intended behavior and scope. Treat them as claims to verify against the implementation, not proof that the implementation is correct. The code either handles the case or it doesn't. `// TODO: handle edge case` means the edge case isn't handled. `# FIXME` means it's broken and shipping anyway.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add posit-dev/skills/critical-code-reviewer@sha256:9aa7f95787f2f236

The line at the top of this page pins the label v1.2, 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_bcekxczyjfqchfml.svg)](https://markdownregistry.com/a/art_bcekxczyjfqchfml)

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

Versions

The registry has recorded 6 versions of this file, between Feb 5, 2026 and Oct 7, 2026, about one every 49 days.

versioncommittedcommitsizeaudit
v1.2 latest2026-10-07 4d770f9 15,468 BA view · diff
v1.22026-08-05 e32ae38 15,507 BA view · diff
v1.12026-04-20 98af5ce 8,821 BA view · diff
v1.02026-02-20 0fabf07 8,840 BA view · diff
git:20260205.97ad1292026-02-05 97ad129 8,759 BA view · diff
git:20260205.af8f4822026-02-05 af8f482 8,760 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 (15468 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

posit-dev/skills · 552 stars · license MIT · pushed 2026-11-02 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_bcekxczyjfqchfml
GET https://markdownregistry.com/api/v1/resolve?ref=posit-dev/skills/critical-code-reviewer
GET https://markdownregistry.com/api/v1/blob/9aa7f95787f2f236f5529b1b9c9dfa44d8b937248e3ff931fc0c69722810dab8

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 posit-dev/skills

AGENTS.md AGENTS.md file
posit-dev/skills · AGENTS.md
git:20261007.4d770f9 · audit A · 552 stars
alt-text SKILL.md skill
posit-dev/skills · alt-text/SKILL.md · Generate and improve accessible alt text for data visualizations and images in R packages and Quarto documents. Use…
v1.0 · audit A · 552 stars
brand-yml SKILL.md skill
posit-dev/skills · brand-yml/SKILL.md · Create and use brand.yml files for consistent branding across Shiny apps and Quarto documents. Covers: (1) Creating new…
v1.1 · audit A · 552 stars
deploy-to-connect SKILL.md skill
posit-dev/skills · connect/deploy-to-connect/SKILL.md · Deploy or publish Python and R content to a Posit Connect server using rsconnect-python or the R rsconnect package…
v4.0 · audit A · 552 stars
ggsql SKILL.md skill
posit-dev/skills · ggsql/ggsql/SKILL.md · Write ggsql queries — a grammar of graphics for SQL. Use when the user wants to create, modify, or understand a ggsql…
v1.1 · audit A · 552 stars
pr-create SKILL.md skill
posit-dev/skills · github/pr-create/SKILL.md · Creates a pull request from current changes, monitors GitHub CI, and debugs any failures until CI passes. Activate when…
v1.5 · audit A · 552 stars
pr-threads-address SKILL.md skill
posit-dev/skills · github/pr-threads-address/SKILL.md · Address PR review feedback by systematically working through every unresolved PR review thread on the current branch's…
v1.0 · audit A · 552 stars
pr-threads-resolve SKILL.md skill
posit-dev/skills · github/pr-threads-resolve/SKILL.md · Bulk resolve unresolved PR review threads on the current branch’s PR — typically after threads have been addressed…
v1.0 · audit A · 552 stars
create-release-checklist SKILL.md skill
posit-dev/skills · open-source/create-release-checklist/SKILL.md · Create a release checklist and GitHub issue for an R package. Use when the user asks to "create a release checklist" or…
v1.0 · audit A · 552 stars
maintainer-decline SKILL.md skill
posit-dev/skills · open-source/maintainer-decline/SKILL.md · Guide for drafting issue closure and decline responses as an open-source package maintainer. Use when helping compose a…
git:20260521.928d934 · audit A · 552 stars
release-post SKILL.md skill
posit-dev/skills · open-source/release-post/SKILL.md · Create professional package release blog posts following Tidyverse or Shiny blog conventions. Use when the user needs…
v1.0 · audit A · 552 stars
describe-design SKILL.md skill
posit-dev/skills · posit-dev/describe-design/SKILL.md · Research a codebase and create architectural documentation describing how features or systems work. Use when the user…
v1.1 · audit A · 552 stars

Every file in posit-dev/skills

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