Coding agents can generate a lot of plausible code faster than humans can audit it. A reviewer skill gives the next agent a repeatable standard instead of asking it to improvise what "review this" means.
Free · open source · SKILL.mdFindings firstBuilt into Critique Chat
critique-review
Code review skill for agents that need standards.
A deeper reviewer protocol for Codex, Claude Code, Cursor, Windsurf, Cline, and other agents that understand skills. It teaches the agent to classify risk, load the right review lens for the codebase in front of it, verify claims before reporting them, and publish a merge-ready artifact without burying the bug under summary text. It is free, open source, and preloaded inside Critique Chat for repository review conversations.
Why we made it
Agents need standards, not vibes.
critique-review started as the review discipline we wanted every Critique agent to carry by default: concise enough to load, strict enough to stop rubber-stamp reviews, and portable enough to hand to any coding assistant outside our product.
Generic review prompts often collapse into style notes, praise, or broad warnings. critique-review forces the useful shape: evidence, file line, failure mode, fix direction, checks, and verdict.
Teams already use Codex, Claude Code, Cursor, Cline, Windsurf, and other agents side by side. A portable Markdown skill lets the review standard travel with the team instead of living in one product.
Why this exists
Less approval theater. More triage and evidence.
Adaptive depth
Small low-risk diffs do not need the same review intensity as auth rewrites, migrations, or agent-permission changes.
Research first
The new protocol pushes the reviewer to trace data flow and surrounding code before escalating an ambiguous pattern into a finding.
Independent pass
When a second agent is used, it gets raw diff context instead of your private chain of thought.
This upgrade
What changed in the deeper version.
The original release made review output sharper. This version makes the reviewer itself sharper: it now triages risk up front, uses codebase-type lenses, and holds findings to a stricter evidence contract.
Adaptive triage
The new version forces the reviewer to classify review mode, change shape, blast radius, and risk before it starts producing findings.
Stack-aware lenses
Backend, React/frontend, migrations, async jobs, infrastructure, and AI-agent systems now get different review checks instead of one generic pass.
False-positive control
The rubric now pushes research-before-reporting, warns against framework-safe pattern matching, and separates findings from open questions more aggressively.
Stricter artifact contract
Every finding now has to answer what breaks, why this path fails, who is impacted, and what direction fixes it.
Comparative position
Smaller than a product. Sharper than a prompt.
This is not trying to replace full PR review platforms. Critique itself runs a much larger review control plane with retrieval, model routing, GitHub checks, and Remedy. This skill is the portable review contract underneath: a free Markdown artifact that improves the behavior of any agent that can read instructions before touching a diff.
General code-review skills
Broad quality frameworks are useful for remembering correctness, readability, architecture, security, and performance. critique-review keeps those axes, then adds adaptive triage, blast-radius thinking, and a stricter merge-oriented artifact shape.
Subagent review prompts
Reviewer-subagent workflows are strong when you need an independent second pass. critique-review bakes in the isolation rule: pass raw diff context and requirements, not the main agent conversation or hidden conclusions.
Product-native reviewers
GitHub Copilot, Cursor Bugbot, CodeRabbit, Greptile, Qodo, and similar tools live where the PR is. critique-review is intentionally lighter: a free portable review protocol any agent can read before it reviews.
Output shape
A review format that is hard to misunderstand.
The skill pushes agents away from vague advice and toward reproducible claims: severity, file line, failure mode, fix direction, checks, and verdict.
**Findings**
- [P1] Missing tenant filter on review runs
File: app/api/review-runs/route.ts:84
Impact: A user could read runs from another workspace.
Why: The new query filters by run id only and dropped the workspace predicate the previous path relied on.
Fix: Keep the organizationId predicate used by the existing helper.
**Checks**
- pnpm exec tsc --noEmit
- pnpm test:unit
**Verdict**
Request changesAgent Skill Marketplace
Publish lenses. Version them. Import anywhere.
Teams can ship Fintech Security, Kafka Migration, or custom critique-review skills on Critique — ranked, versioned, and installable into any workspace, similar to skills.sh. Publishing requires a Critique account; installs work in Chat or via portable npx commands.
Install anywhere
npx skills add https://www.critique.sh/api/skills/marketplace/critique-review/bundle --version 1.0.0Download .md
Single-file Markdown copy
Open raw Markdown
Static public file
View source
Open-source GitHub repo
Skills run with agent permissions. Read the Markdown before installing third-party skills, then pin or vendor the version your team trusts.