Code Review
AI-powered code review for diffs and individual files using LLM analysis
Install
npx skills add initializ/forge --skill code-reviewgit clone --depth 1 https://github.com/initializ/forge.git /tmp/forge
mkdir -p ~/.claude/skills
cp -r /tmp/forge/forge-skills/local/embedded/code-review ~/.claude/skills/code-reviewPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Code Review Skill AI-powered code review that analyzes diffs and individual files for bugs, security issues, style violations, and improvement opportunities. Supports both local git diffs and GitHub pull requests. ## Authentication Set at least one LLM API key: ```bash # Option A: Anthropic export ANTHROPIC_API_KEY="sk-ant-..." # Option B: OpenAI or any OpenAI-compatible provider (Together, OpenRouter, Groq, ...) export OPENAI_API_KEY="sk-..." export OPENAI_BASE_URL="https://api.together.ai/v1" # only when not using openai.com # Optional: override the model (defaults: claude-sonnet-4-20250514 / gpt-4o) export REVIEW_MODEL="moonshotai/Kimi-K2.6" # Optional: force a specific provider when both keys are set export REVIEW_PROVIDER="openai" # or "anthropic" ``` **Provider selection** (auto-detected when `REVIEW_PROVIDER` is unset): 1. If `REVIEW_PROVIDER` is set, it wins. 2. Else if `REVIEW_MODEL` starts with `claude-` or `anthropic/`, use Anthropic. 3. Else if only one API key is set, use that provider. 4. Else (both keys, no model hint): use OpenAI. This precedence fixes the common deployment where both `ANTHROPIC_API_KEY` and `OPENAI_API_KEY` live in `.forge/secrets.enc` (one is stale or for a different skill). Pre-fix the skill always preferred Anthropic and returned 401 against the stale key. For GitHub PR review, also set: ```bash export GH_TOKEN="ghp_..." ``` The token needs **read-only** access: | Scope (classic PAT) | Fine-grained permission | Why |
Details
- Skill name
code-review- Repository
- initializ/forge
- Path
forge-skills/local/embedded/code-review/SKILL.md- License
- Apache-2.0
- Repo updated
- 17 November 2026
FAQ
What does the Code Review skill do?
AI-powered code review for diffs and individual files using LLM analysis
How do I install the Code Review skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add initializ/forge --skill code-review. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Code Review popular?
It lives in initializ/forge, which has 230 GitHub stars and 17 forks.
Related skills
Code Agent
230initializ/forge
General-purpose coding agent that reads, writes, and edits code, and searches codebases.
Code Plan
230initializ/forge
Turn a task description and repository into a structured implementation plan (files to create, files to modify, tests to add, risks).
Code Review Github
230initializ/forge
GitHub PR workflow orchestration for code review — list PRs, post comments, apply labels, and guarded auto-merge
Gh Aw Operations
206thomast1906/github-copilot-agent-skills
Comprehensive skills for creating, compiling, debugging, and managing GitHub Agentic Workflows (gh-aw) with best practices and common patterns
Github
230initializ/forge
Create issues, PRs, clone repos, and manage git workflows
Apm Package Author
206thomast1906/github-copilot-agent-skills
Create, maintain, and troubleshoot APM (Agent Package Manager) manifests for distributing GitHub Copilot skills, agents, and MCP servers. USE FOR: creating apm.yml root manifests; creating packages/* sub-manifests; bundling MCP server config into a package; installing packages from a GitHub repo; troubleshooting APM install errors (missing .vscode/mcp.json, Codex CLI warnings, cached installs). DO NOT USE FOR: general GitHub Copilot customization questions; creating SKILL.md files (use skill-creator); writing MCP server code.
Browse the most popular Claude skills, all git & code review skills, or write your own with the skills generator.