/open-code-review

name: open-code-review
description: >
  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.
license: Apache-2.0
compatibility: >
  Requires the `ocr` CLI installed (via `npm install -g
  @alibaba-group/open-code-review` or GitHub release binary). Requires a
  configured LLM (Anthropic or OpenAI-compatible) before first run.
metadata:
  author: alibaba
  homepage: https://github.com/alibaba/open-code-review
  version: "1.0.0"

Open Code Review

A skill for invoking [open-code-review](https://github.com/alibaba/open-code-review) (`ocr`) — an open-source AI code review CLI that reads Git diffs and generates structured, line-level review comments.

Prerequisites check

Before starting a review, verify the environment:

# 1. Check the CLI is installed
which ocr || echo "NOT INSTALLED"

# 2. Verify LLM connectivity
ocr llm test

If `ocr` is not installed, install it first:

npm install -g @alibaba-group/open-code-review

If `ocr llm test` fails, the user must configure an LLM. Guide them with one of these options:

**Option A — Environment variables (highest priority, recommended for CI):**

export OCR_LLM_URL=https://api.anthropic.com/v1/messages
export OCR_LLM_TOKEN=<api-key>
export OCR_LLM_MODEL=claude-opus-4-6
export OCR_USE_ANTHROPIC=true

**Option B — Persistent config:**

ocr config set llm.url https://api.anthropic.com/v1/messages
ocr config set llm.auth_token <api-key>
ocr config set llm.model claude-opus-4-6
ocr config set llm.use_anthropic true

Stop here and ask the user to provide credentials — never invent or hardcode API keys.

Workflow

Step 1: Gather Business Context

Analyze the review target (commits, branch, or changes) to extract concise business context. Pass this context via `--background` to improve review quality.

Step 2: Run Code Review

Run the OCR command with appropriate flags. **Always pass business context via `--background`** when available:

ocr review --audience agent --background "business context here" [user-args]

**Argument handling:**

• **Background context** (RECOMMENDED): use `--background "context"` or `-b "context"` to provide business context for better review quality
• **Default** (no user arguments): reviews staged, unstaged, and untracked changes (workspace mode)
• **Specific commit**: use `--commit` or `-c` to review a single commit against its parent
• **Branch comparison**: use `--from <ref>` and `--to <ref>` to review diff between two refs
• **Timeout**: default timeout is 10 minutes per file; adjust with `--timeout <minutes>`
• **Concurrency**: default concurrency is 8 file workers; reduce with `--concurrency <n>` if rate limits are hit
• **Preview mode**: use `--preview` or `-p` to preview which files will be reviewed without running the LLM
• **Installation**: if `ocr` command is not found, install it by running `npm i -g @alibaba-group/open-code-review`

**Common invocation patterns:**

| User says | Command to run | |-----------|---------------| | "review my changes" / "review the working copy" | `ocr review --audience agent -b "context"` | | "review this PR" / "review feature branch" | `ocr review --audience agent -b "context" --from main --to <branch>` | | "review commit abc123" | `ocr review --audience agent -b "context" --commit abc123` | | "what would be reviewed?" (dry-run) | `ocr review --preview` |

**Output mode:**

• Always use `--audience agent` to suppress progress UI and emit only the final summary

Step 3: Classify and Report

For each comment from the review output, classify by priority and report all issues to the user:

• **High**: Obvious bugs, security issues, clear mistakes, or well-founded suggestions with precise fix proposals
• **Medium**: Reasonable concerns but context-dependent, style/performance suggestions, or fixes that require manual implementation
• **Low**: Likely false positives, lacking sufficient context, nitpicks, or meaningless suggestions

Report all comments grouped by priority level.

Step 4: Fix

Before applying fixes, check whether the user requested automatic fixes:

• If the user explicitly requested "review and fix" or similar, proceed with automatic fixes
• If the user only requested "review" without fix intent, ask for permission before applying any changes

When fixing issues and suggestions:

• Focus on High and Medium priority items
• Apply fixes directly to the code when safe and well-defined
• For complex fixes requiring manual intervention, clearly describe what needs to be done
• Always verify fixes with the user before committing

Output Format

Each comment contains:

• `path`: File path
• `content`: Review comment text
• `start_line` / `end_line`: Line range (both 0 means positioning failed)
• `suggestion_code`: Optional fix suggestion
• `existing_code`: Optional original code snippet
• `thinking`: Optional LLM reasoning process

After filtering comments by priority, present results using this template:

## Code Review Results

**Files reviewed**: N
**Issues found**: X high priority / Y medium priority

### High Priority

- **`path/to/file.java:42`** — Brief description
  > Recommendation: How to fix

### Medium Priority

- **`path/to/file.ts:88`** — Brief description
  > Recommendation: How to fix (if applicable)

If the review found no issues after filtering, simply state: "Review complete — no issues found in N files."

**Priority classification:**

• **High**: Obvious bugs, security issues, clear mistakes, or well-found