From ai-review
Opens specific commits, ranges, or branch diffs in ai-review desktop app for human review and feedback. Use to understand git history or review others' existing work.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ai-review:review-commitsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
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.
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.
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.
Handle the response.
If the human submitted comments: Parse the JSON feedback. The output has the shape:
{
"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.
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.git log --oneline -10).npx claudepluginhub mrmans0n/ai-review --plugin ai-reviewProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.