code-review-skills

Name: code-review-skills
Author: akkie76

by akkie76

Verified

Evidence-based code review skills for Codex and Claude Code

82stars

0forks

Python

Added 9/28/2026

Installation

# Add to your Claude Code skills
git clone https://github.com/akkie76/code-review-skills

Getting Started

Guides for using ai agents skills like code-review-skills.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

Security ReportVerified

Last scanned: 9/29/2026

{
  "issues": [],
  "status": "PASSED",
  "scannedAt": "2026-09-29T10:25:55.958Z",
  "npmAuditRan": true,
  "pipAuditRan": true,
  "promptInjectionRan": true
}

Compare with similar skills

See how code-review-skills compares with popular alternatives.

code-review-skills vs hermes agent

See comparison

code-review-skills vs ecc

See comparison

code-review-skills vs everything claude code

README.md

Frequently Asked Questions

What is code-review-skills?

code-review-skills is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by akkie76. Evidence-based code review skills for Codex and Claude Code. It has 82 GitHub stars.

Is code-review-skills safe to use?

Yes. code-review-skills passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install code-review-skills?

Clone the repository with "git clone https://github.com/akkie76/code-review-skills" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is code-review-skills written in?

code-review-skills is primarily written in Python. It is open-source under akkie76 on GitHub, so you can review or fork the full source.

Are there alternatives to code-review-skills?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh code-review-skills against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

ECC

by affaan-m

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

274,491

baoer_signal_grep fireworks-design

⚠️ Third-Party Software Notice

This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.

Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.

Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.

Read the Terms of Service

Code Review Skills

日本語

Code Review Skills is an evidence-driven code-review workflow for AI coding agents. It helps Codex and Claude Code find actionable defects while avoiding style-only comments and unsupported speculation.

This Skill is based on ideas from コードレビューの教科書 and independently adapts them for AI coding agents. It does not reproduce or replace the book.

Beta: The review methodology and packaging are under evaluation. Expect changes before the first stable release.

What it does

Establishes the requested review scope and repository-specific rules.
Traces changed behavior beyond the modified lines.
Checks correctness, interfaces, design, security, reliability, tests, and documentation according to risk.
Optionally decomposes complex reviews across independent sub-agents when the environment supports delegation, followed by a required integration pass.
Requires a concrete trigger and impact for every finding.
Prefixes each comment with its action level and viewpoint, such as MUST(Functionality): or BETTER(Simplicity):.
Produces prioritized findings in English or Japanese.

The skill reviews code; it does not modify the reviewed code unless the user separately asks for changes.

See the review comment convention for action levels, viewpoints, and communication rules.

Install

Clone this repository and copy the complete package directory for your agent. Copying only SKILL.md omits required references.

Codex

For all local projects:

mkdir -p ~/.codex/skills
cp -R dist/codex/evidence-code-review ~/.codex/skills/

For one repository, copy the package to .agents/skills/evidence-code-review/ inside that repository instead. Start a new Codex task after installation, then ask it to use evidence-code-review to review a diff, commit, branch, pull request, or working tree.

Claude Code

For all local projects:

mkdir -p ~/.claude/skills
cp -R dist/claude-code/evidence-code-review ~/.claude/skills/

For one repository, copy the package to .claude/skills/evidence-code-review/ inside that repository instead. Invoke it with /evidence-code-review or ask Claude Code to use the evidence-code-review skill. Automatic selection can vary with context; when you need the Skill to run, invoke /evidence-code-review explicitly.

The installed package records its version in a skill-version comment near the top of SKILL.md. This repository's current version is in VERSION. See the versioning and compatibility policy for the documented output contract and release-version rules.

Review a skill before installing it. A skill supplies instructions to an agent and should be treated like other executable development configuration. See the installation guide for project installation, Windows commands, verification, updates, removal, and troubleshooting.

Development

The files under src/core/ are the canonical, vendor-neutral methodology. Files under dist/ are generated and must not be edited directly.

make build  # regenerate every agent package
make check  # validate frontmatter, links, and generated freshness
make test   # also validate behavioral evaluation fixtures

make build uses only the Python standard library and does not require network access. See the evaluation guide for manual testing with each agent.

Project technology guidance

Language, framework, SDK, and tool requirements vary by project. Store the information needed for accurate reviews in the reviewed repository's AGENTS.md, CLAUDE.md, or a project document referenced by those files. Do not edit the installed Skill; updates may replace it.

Relevant material can include version constraints, lifecycle or concurrency rules, architecture conventions, and verification commands. If no guidance is supplied, the reviewer uses repository evidence and avoids assuming technology-specific guarantees.

Project policy

This project currently follows a maintainer-led beta process. Evidence-backed Issues about defects, review accuracy, agent compatibility, and documentation are welcome. Pull requests require prior agreement. See SUPPORT.md for the scope and evidence expected, and SECURITY.md for private vulnerability reporting guidance.

The repository contains independently authored material. Its source and publication boundaries are described in docs/CONTENT_POLICY.md.

License

The original material in this repository is licensed under the MIT License.