Skip to content
Agentmart
Submit a tool

code-review

Skill by Haofei

IndexedMIT
Write a review

Chalk Labs

Need help deploying code-review?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/haofei-code-review

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

The publisher has not written a description yet.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions: not checked yet.

What's inside

Skill name
code-review
Description
None
License
MIT
Instructions
50 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • missing YAML frontmatter
  • name: missing
  • description: missing

Files (2)

  • SKILL.md
  • air-skill.yaml

SKILL.md (first lines)

# Code Review

Use this skill when reviewing a pull request, merge request, diff, patch, or changed files.

## Objective

Find concrete risks in the proposed change. Prioritize defects that could cause incorrect behavior, production incidents, security issues, data loss, broken compatibility, missing verification, or maintainability problems that would block safe merge.

## Review Method

1. Establish the change intent from the title, description, task, branch names, and touched files.
2. Inspect the diff, not just the surrounding code.
3. For each risky change, reason from current behavior to new behavior and identify the failing scenario.
4. Check whether tests cover the changed behavior and edge cases.
5. Prefer source-grounded findings over broad advice.

## Output Format

Lead with findings. If there are no actionable findings, say that clearly.

For each finding include:

- Severity: `P0`, `P1`, `P2`, or `P3`
- Location: file and line when available
- Problem: what is wrong
- Impact: what can fail or regress
- Suggested fix: concise, practical remediation

After findings, include:

- Open questions or assumptions
- Test/verification gaps
- Brief summary of the change

## Severity Guide

- `P0`: must fix immediately; security breach, data loss, major outage, or unusable release
- `P1`: high-confidence correctness/security issue that should block merge
- `P2`: real bug or missing verification that is worth fixing before merge
- `P3`: low-risk maintainability, clarity, or follow-up issue

## Review Rules

- Do not nitpick style unless it can hide a bug or meaningfully harm maintainability.
- Do not propose unrelated refactors.
- Do not claim a bug without a plausible failing path.
- Do not post comments to remote systems unless explicitly asked.
- If the diff is incomplete, state the limits of the review and review what is available.
- If line numbers are unavailable, reference the file/function/changed block.

From Haofei/air, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
May 18, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get code-review running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying code-review?

CallGet help
Cite this page

code-review skill. Agent Mart. https://agentmart.dev/skills/haofei-code-review (last updated 2026-10-24)