Skip to content
mcp/skillhub

Agent Skill

Open Code Review skill

open-code-reviewalibaba/open-code-reviewskills/open-code-review/SKILL.md

Performs AI-powered code review on Git changes using the `ocr` CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply fixes when requested. With appropriate review rules, can detect various types of issues including bugs, security vulnerabilities, performance problems, and code quality concerns.

48kApache-2.0

always on

97 tokname + description

once used

2,760 tokSKILL.md body

bundled files

0

repo stars

48kGitHub

Install the Open Code Review skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/alibaba/open-code-review --skill open-code-review

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/alibaba/open-code-review.git /tmp/open-code-review
mkdir -p ~/.claude/skills
cp -R /tmp/open-code-review/skills/open-code-review ~/.claude/skills/open-code-review

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

WhenWhat loadsCost
Every sessionName and description97 tok
When the agent uses itThe SKILL.md instructions2,760 tok
Only if openedNo bundled files—

Until it is used, open-code-review costs about 14× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 4 skills from alibaba/open-code-review would load 330 tokens of descriptions. Skills vs MCP study

Checks

Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

  • Open Code Review
  • Workflow
  • Step 1: Gather Business Context
  • Step 2: Run Code Review
  • Step 3: Report
  • Step 4: Fix
  • Output Format
  • Custom Review Rules
  • Advanced Review Options
  • Gotchas
  • Validation
  • Troubleshooting
  • References

More skills from alibaba/open-code-review

All skills in this repo
  1. open-code-reviewalibaba/open-code-review

    Performs AI-powered code review on Git changes using the `ocr` CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply fixes when requested. With appropriate review rules, can detect various types of issues including bugs, security vulnerabilities, performance problems, and code quality concerns.

    48k97 tok idle · 2,810 in use
  2. open-code-review-delegatealibaba/open-code-review

    Delegation mode for open-code-review (OCR). Instead of OCR calling an LLM endpoint, this skill instructs the host agent to perform the code review itself, using OCR only for deterministic engineering: file selection and rule resolution. Use when the host agent should drive the review with its own LLM capabilities.

    48k68 tok idle · 2,005 in use
  3. open-code-review-delegatealibaba/open-code-review

    Delegation mode for open-code-review (OCR). Instead of OCR calling an LLM endpoint, this skill instructs the host agent to perform the code review itself, using OCR only for deterministic engineering: file selection and rule resolution. Use when the host agent should drive the review with its own LLM capabilities.

    48k68 tok idle · 1,951 in use