claudeers.
// Claude Skills

looks-good-to-ai

Agent Skill for reviewing AI-written PRs in Claude Code, Codex, Copilot, Cursor and Gemini CLI: catch bugs, align context, own the sign-off.

Install with your AI

Paste into Claude Code, Cursor, or any agent — it reads the repo and wires the tool into your project.

Install and set up looks-good-to-ai (git-clone project) into my current project.
Found on https://claudeers.com/looks-good-to-ai
Repo: https://github.com/laulauraluo/looks-good-to-ai
Homepage/docs: —
Detected install method: git-clone → git clone https://github.com/laulauraluo/looks-good-to-ai
Category: skills. Platforms: cli, mobile.
Read the repo's README for exact setup and env vars, then install it and wire it into my project.

Claudeers Health Verdict:
unknown; community-verified: false. Confirm the source before running anything.
// or clone
git clone https://github.com/laulauraluo/looks-good-to-ai

// compatibility

Platformscli, mobile
Operating systems—
AI compatibilityclaude
LicenseMIT
Pricingopen-source
LanguagePython

Get your FREE $2.50 API credits to access TickAtlas financial data ↗

Looks Good to AI

Formerly AI Code Review Triage

AI writes code faster than you can read it. Stop reading harder and review differently.

An Agent Skill that reviews AI-written pull requests by splitting "reading the code" into three separate jobs.
Runs in Claude Code, Codex, GitHub Copilot, Cursor, Gemini CLI, Antigravity, OpenCode, Windsurf, Cline, Roo Code, Kiro, Amp, Junie and Zed, and loads as plain context in Aider.

🇬🇧 · 🇨🇳 · 🇯🇵 · 🇰🇷 · 🇪🇸 · 🇧🇷 · 🇫🇷

Quick start · The idea · Install · Usage · Examples · How it works · Limits

An AI-written PR whose tests pass and whose diff looks clean. Looks Good to AI finds four problems: a dropped unit conversion hidden in the diff, a past revert, a mobile client that hard-codes the old value, and a requirement mismatch. Read line by line, it logs every user out after 30 seconds; with the skill, it is blocked before merge

The problem

Agent-written PRs pile up faster than anyone can review them line by line. Reading harder doesn't help much either: the code is tidy on the surface, so the real problems hide well enough to survive a careful read. "Just merge and roll back if it breaks" works technically, but a human still answers for the incident.

Quick start

npx skills add laulauraluo/looks-good-to-ai

The skills CLI asks which agents to set up. Add -g to install for your user instead of this project, and -a <agent> to skip the question (-a claude-code, -a codex, -a github-copilot, -a cursor, …).

Or use the agent's own installer:

AgentCommand
Claude Code/plugin marketplace add laulauraluo/looks-good-to-ai then /plugin install looks-good-to-ai@looks-good-to-ai
Codexcodex plugin marketplace add laulauraluo/looks-good-to-ai then codex plugin add looks-good-to-ai@looks-good-to-ai
GitHub Copilot CLIcopilot plugin marketplace add laulauraluo/looks-good-to-ai then copilot plugin install looks-good-to-ai@looks-good-to-ai
Gemini CLIgemini extensions install https://github.com/laulauraluo/looks-good-to-ai

Then, in your agent:

Review this AI-generated PR before I merge it.

The skill loads on its own from a request like that. Most agents also take /looks-good-to-ai to call it by name; Codex uses $looks-good-to-ai. docs/agents.md has the command for each agent.

The idea

"Reviewing code" has always bundled three different jobs. That worked when code arrived slowly. At agent speed, each job needs its own process:

flowchart LR
    PR([AI-written PR]) --> T{Step 0<br/>Triage<br/>risk tier}
    T --> B["**1 · Catch bugs**<br/>fresh-context sub-agent<br/>+ tests / repro"]
    B --> C["**2 · Align context**<br/>orders of magnitude<br/>history & neighbors<br/>requirement match"]
    C --> S["**3 · Own the sign-off**<br/>explain · detect · undo<br/>scoped approval"]
    S --> R([Review report])
JobQuestionWho does it best
Catch bugsIs the code wrong?Machines, with an independent second pass
Align contextIs this the right change for this product, today?A human, checking angles the diff can't show
Own the sign-offWill I put my name on this?The approver, with an explicit scope

Low-risk PRs only run Step 1. Medium-risk PRs run Steps 1 and 2. High-risk PRs (production behavior, data, security, money) run all three.

What it catches that line-by-line review misses

A PR changes SESSION_TIMEOUT = 30 to 30000 and drops one line of unit conversion. Tests pass. The code is clean. A line-by-line reader approves it in 30 seconds.

  • Step 1 has a fresh-context sub-agent add a boundary test. Result: sessions now expire after 30 seconds.
  • Step 2 checks history and callers. The same change was reverted once before, the mobile client hard-codes the old value, and the request was only for "remember me" users while the diff changes everyone.
  • Step 3 blocks the approval. Nobody can explain what the PR actually does.

Full run: examples/session-timeout-walkthrough.md

Install

The skill is the folder skills/looks-good-to-ai/. Every agent below loads it unchanged; only the folder differs. docs/agents.md has the full table with every folder each agent reads, the way each agent calls a skill, and a link to each agent's own documentation.

Agentskills CLIOr copy the folder to (user · project)
Claude Code-a claude-code~/.claude/skills/ · .claude/skills/
Codex-a codex~/.agents/skills/ · .agents/skills/
GitHub Copilot-a github-copilot~/.copilot/skills/ · .github/skills/
Cursor-a cursor~/.cursor/skills/ · .cursor/skills/
Gemini CLI-a gemini-cli~/.gemini/skills/ · .gemini/skills/
Antigravity-a antigravity~/.gemini/config/skills/ · .agents/skills/
OpenCode-a opencode~/.config/opencode/skills/ · .opencode/skills/
Windsurf-a windsurf~/.config/devin/skills/ · .devin/skills/
Clinecopy by hand (why)~/.cline/skills/ · .cline/skills/
Roo Code-a roo~/.roo/skills/ · .roo/skills/
Kiro-a kiro-cli~/.kiro/skills/ · .kiro/skills/
Amp-a amp~/.config/agents/skills/ · .agents/skills/
Junie-a junie~/.junie/skills/ · .junie/skills/
Zed-a zed~/.agents/skills/ · .agents/skills/
Aider—read: in .aider.conf.yml (how)
Continue—Unverified; load as a rule (how)
With git, no CLI

Clone the repository once and copy the skill folder into the agent's folder from the table, so that SKILL.md ends up at <folder>/looks-good-to-ai/SKILL.md:

git clone https://github.com/laulauraluo/looks-good-to-ai.git
cp -r looks-good-to-ai/skills/looks-good-to-ai ~/.claude/skills/

Swap ~/.claude/skills/ for any other folder in the table. For a project install, commit the copied folder so your team gets it too.

On every pull request (GitHub Actions)

A reusable workflow runs the skill on each pull request and posts the report as a comment. Setup takes three steps: docs/github-action.md.

Claude Code plugin

Inside Claude Code:

/plugin marketplace add laulauraluo/looks-good-to-ai
/plugin install looks-good-to-ai@looks-good-to-ai

Usage

Ask your agent something like:

  • "Review this AI-generated PR before I merge it."
  • "Can this diff be merged? Codex wrote it."
  • "I'm about to approve #123. What should I verify first?"
  • "We have too many agent PRs to read line by line. Triage this one."

You get a report like this (from the invented timeout example):

## Extend session lifetime for "remember me" · Risk: High

### 1. Bugs (independent fresh-context review)
- [CONFIRMED] auth/session.py:3 — unit conversion dropped; sessions expire after 30 s. Repro: test_session_expires_after_timeout

### 2. Context
- Magnitudes: SESSION_TIMEOUT 30 → 30000 (comment says min, code treats as ms) — suspicious
- History / neighbors: reverted once before (a1b2c3d); mobile/src/config.ts hard-codes 30 min
- Requirement match: asked for remember-me users only; diff changes everyone

### 3. Sign-off
- Detection: login-rate and 401-rate alerts · Rollback: config revert
- Recommendation: request changes
- Verification scope: verified units and callers; did not load-test

<sub>Reviewed with [Looks Good to AI](https://github.com/laulauraluo/looks-good-to-ai)</sub>

The last line credits the skill when you paste the report into a PR. Ask the agent to leave it out if you don't want it.

More prompts, from the skill's evals
Here's the diff for PR #482. Cursor wrote it to raise our retry count from 3 to 10 on the payments client. Tests pass. Can I approve it?
Copilot opened a PR that only fixes typos in docs/ and the README. Do I need the full review process?
I wrote this change with you in this session. Now review it before I merge.

Examples

Both walkthroughs are invented scenarios that follow one PR through every step.

WalkthroughWhat goes wrongWhat finds it
Session timeout30 → 30000 with the unit conversion dropped: sessions expire after 30 seconds, for every user.A boundary test in Step 1; units, a past revert and a hard-coded mobile value in Step 2.
Pagination limitPage size 100 → 1000 against a provider that caps pages at 100: the export stops with 150 of 250 rows missing.The provider contract in Step 2, and a standard-library Python reproduction you can run.

How it works

  • SKILL.md is what the agent reads: the risk tiers, the three steps, the commands for history and callers, and the report template.
  • Step 1 needs a second, clean context. The session that wrote the code can't review it independently. references/subagents.md shows how each agent starts a fresh reviewer, and what to do in agents that have none.
  • Step 2 needs a shell with git. It runs git log -S, git log --grep=revert and grep to find history and callers the diff doesn't show.
  • evals/evals.json holds test prompts and what a good answer contains. CI checks that the skill's frontmatter follows the Agent Skills spec and that the pagination reproduction still runs.
Repository layout
looks-good-to-ai/
├── skills/looks-good-to-ai/   the skill (this folder is what gets installed)
│   ├── SKILL.md                    workflow, risk tiers, report template
│   ├── references/subagents.md     a fresh-context reviewer in each agent
│   └── agents/openai.yaml          display name for the Codex and ChatGPT apps
├── docs/
│   ├── agents.md                   install and use in each agent, with sources
│   └── review-ai-generated-code.md questions and answers
├── examples/                       two invented end-to-end walkthroughs
├── evals/evals.json                test prompts and expected answers
├── scripts/check.py                the checks CI runs
├── .claude-plugin/                 plugin and marketplace manifests (Claude Code, Codex, Copilot CLI)
├── gemini-extension.json           Gemini CLI extension manifest
└── .github/                        CI, issue forms, PR template

Limits

  • It is a review process, not a scanner. It decides what has to be true before you approve. Run linters, type checkers and security tools inside Step 1; this skill does not replace them.
  • It can't guarantee a PR is safe. The examples are invented teaching cases, not a measured detection rate.
  • It is slower than a skim, on purpose. A high-risk PR gets a sub-agent pass, tests, history searches and a written sign-off. Low-risk PRs skip most of it.
  • Step 1 is only as independent as the reviewer you give it. In agents without sub-agents, open a new session by hand.

Questions such as "can it review Codex output?" and "why can passing tests miss incomplete exports?" are answered in docs/review-ai-generated-code.md.

Works well with

This skill organizes the review and decides what has to be true before you approve. It doesn't replace specialized checkers. Run them inside Step 1:

  • a correctness-focused review (for example Claude Code's built-in /code-review, or Copilot CLI's code-review agent)
  • security and performance checklists
  • over-engineering reviews

Contributing

Issues and pull requests are welcome. Read CONTRIBUTING.md first: it covers linking a working copy into your agent, the checks CI runs, and what a change to SKILL.md has to keep.

Acknowledgments

The three-job framing was inspired by a public talk on reviewing AI-written code. The multi-agent install layout follows Anatomy.

License

MIT


If this caught a bad merge for you, a ⭐ helps other reviewers find it.

// faq

What is looks-good-to-ai?

Agent Skill for reviewing AI-written PRs in Claude Code, Codex, Copilot, Cursor and Gemini CLI: catch bugs, align context, own the sign-off.. It is open-source on GitHub.

Is looks-good-to-ai free to use?

looks-good-to-ai is open-source under the MIT license, so it is free to use.

What category does looks-good-to-ai belong to?

looks-good-to-ai is listed under skills in the Claudeers registry of Claude-compatible tools.

0 views
★ 93 stars
unclaimed
updated about 23 hours ago

// embed badge

looks-good-to-ai on Claudeers
[![Claudeers](https://claudeers.com/api/badge/looks-good-to-ai.svg)](https://claudeers.com/looks-good-to-ai)

// retro hit counter

looks-good-to-ai hit counter
[![Hits](https://claudeers.com/api/counter/looks-good-to-ai.svg)](https://claudeers.com/looks-good-to-ai)

// reviews

// guestbook

0/500

// related in Claude Skills

🔓

An agentic skills framework & software development methodology that works.

// skillsobra/⟨Shell⟩★ 314,126◷ MIT[ claude ]
🔓

Public repository for Agent Skills

// skillsanthropics/⟨Python⟩★ 188,182[ claude ]
🔓

AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs,…

// skillsGraphify-Labs/⟨Python⟩★ 149,064◷ MIT[ claude ]
🔓

💫 Toolkit to help you get started with Spec-Driven Development

// skillsgithub/⟨Python⟩★ 148,200◷ MIT[ claude ]
→ see how looks-good-to-ai connects across the ecosystem