review-commits
Open existing commits in the ai-review desktop app for review. Use when you need to review, understand, or get feedback on specific commits, a commit range, or a branch diff — not your own recent work, but existing history.
Best use case
review-commits is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Open existing commits in the ai-review desktop app for review. Use when you need to review, understand, or get feedback on specific commits, a commit range, or a branch diff — not your own recent work, but existing history.
Teams using review-commits should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/review-commits/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How review-commits Compares
| Feature / Agent | review-commits | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Open existing commits in the ai-review desktop app for review. Use when you need to review, understand, or get feedback on specific commits, a commit range, or a branch diff — not your own recent work, but existing history.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
Open specific commits or a commit range in ai-review so the human can review existing changes. Useful for understanding history, reviewing someone else's work, or getting context on past changes.
## Steps
1. **Determine what to review.** Based on what was requested, pick the right `air` invocation:
a. **A specific commit:**
```
air --wait --json --commit <commit-hash>
```
b. **A range of commits** (e.g., "last 3 commits", "commits since Tuesday"):
Determine the range. For the last N commits, find the Nth parent: `git rev-parse HEAD~N`. Run:
```
air --wait --json --commits <start-hash>..<end-hash>
```
c. **A branch diff** (e.g., "what changed on feature-x"):
```
air --wait --json --branch <base-branch>
```
d. **The current gg stack** — when on a branch matching the `user/name` pattern (no `--` in name) and `.git/gg/config.json` exists:
Read the gg base branch from config (parse `defaults.base`, fall back to `main`). Run:
```
air --wait --json --commits <gg-base>..HEAD
```
This shows the full stack diff, matching what ai-review displays when opening a gg stack.
The `air --wait --json` command opens the ai-review desktop app and blocks until the human submits. The output is structured JSON.
2. **Handle the response.**
- **If the human submitted comments:** Parse the JSON feedback. The output has the shape:
```json
{
"format": "ai-review.feedback/v1",
"context": { "mode": "...", ... },
"comments": [
{ "id": "...", "file": "...", "startLine": 10, "endLine": 12, "side": "old|new", "text": "...", "createdAt": "..." }
]
}
```
Present the comments to the user. If the comments suggest code changes and the commits are on the current branch, offer to make the changes.
- **If the human submitted with no comments:** (empty `comments` array) Acknowledge and move on.
## Notes
- If `air` is not found, tell the user to install via `brew install --cask mrmans0n/tap/ai-review` (macOS) or build from source at https://github.com/mrmans0n/ai-review.
- If the specified commit or range doesn't exist, inform the user and suggest alternatives (e.g., `git log --oneline -10`).Related Skills
human-review
Request human code review via the ai-review desktop app. Use when code changes are complete and ready for a final human review before committing or merging. Opens an interactive diff viewer where the human can leave inline comments, then returns their feedback.
show-changes
Present completed work to the human for optional review via the ai-review desktop app. Use when you've finished a task and want the human to see what you did — they can optionally leave feedback.
browse-diff
Open the ai-review desktop app to visually browse a diff. Use when the user wants to see changes in a visual diff viewer without a review feedback loop — just for viewing.
performing-serverless-function-security-review
Performing security reviews of serverless functions across AWS Lambda, Azure Functions, and GCP Cloud Functions to identify overly permissive execution roles, insecure environment variables, injection vulnerabilities, and missing runtime protections.
performing-privileged-account-access-review
Conduct systematic reviews of privileged accounts to validate access rights, identify excessive permissions, and enforce least privilege across PAM infrastructure.
performing-oauth-scope-minimization-review
Performs OAuth 2.0 scope minimization review to identify over-permissioned third-party application integrations, excessive API scopes, unused token grants, and risky OAuth consent patterns across identity providers and SaaS platforms. Activates for requests involving OAuth scope audit, API permission review, third-party app risk assessment, or consent grant minimization.
performing-entitlement-review-with-sailpoint-iiq
Performs entitlement review and access certification campaigns using SailPoint IdentityIQ including manager certifications, targeted entitlement reviews, role-based access validation, SOD violation remediation, and automated revocation workflows. Activates for requests involving access reviews, entitlement certifications, SailPoint IIQ governance, or periodic user access recertification.
performing-access-review-and-certification
Conduct systematic access reviews and certifications to ensure users have appropriate access rights aligned with their roles. This skill covers review campaign design, reviewer selection, risk-based p
fix-review
Review security fixes and patches for completeness and correctness.
differential-review
Security-focused code review of diffs and pull requests using Trail of Bits expertise.
code-review
Automated code review for pull requests using specialized review patterns. Analyzes code for quality, security, performance, and best practices. Use when reviewing code changes, PRs, or doing code audits.
self-review
手元のコードをreviewerエージェントでセルフレビューし、指摘に基づいて自動修正するループ