From ai-review
Requests human code review of git changes via ai-review desktop app and air CLI before committing or merging. Determines relevant diff, opens interactive viewer, returns JSON feedback with inline comments.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ai-review:human-reviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You have finished writing code and need the human to review it before proceeding. Use the `air` CLI tool to open an interactive code review session, then address every piece of feedback.
You have finished writing code and need the human to review it before proceeding. Use the air CLI tool to open an interactive code review session, then address every piece of feedback.
Determine what to review. Check these in priority order to pick the right air invocation:
a. Uncommitted changes exist (staged or unstaged, check via git status --porcelain):
Run air --wait --json with no branch/commit flags. This reviews the working directory diff.
b. All changes committed, on a gg stack branch — the current branch matches the user/name pattern (no -- in the name part) 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.
c. All changes committed, on a feature branch (not main/master):
Determine the base branch (main or master, whichever exists). Find the merge-base commit and use --commit:
air --wait --json --commit $(git merge-base <base-branch> HEAD)
d. All changes committed, on main/master itself:
Identify the first commit you made during this session. If you can determine the exact commit (e.g., you created it earlier in this conversation), use that hash directly. Otherwise, fall back to the first unpushed commit: run git log origin/main..HEAD --oneline --reverse (or origin/master) and take the first commit hash. Run:
air --wait --json --commit <first-relevant-commit-hash>
e. None of the above: Run air --wait --json with no flags (empty diff — the app handles it).
The air command opens the ai-review desktop app showing the relevant diff. The human will review the code, add comments, and submit. The command blocks until submission and prints structured JSON feedback to stdout.
Parse the feedback. The output is a JSON object with the following shape:
{
"format": "ai-review.feedback/v1",
"context": {
"mode": "unstaged|staged|commit|range|branch",
"commitRef": "...",
"selectedCommit": { "hash": "...", "short_hash": "...", "message": "...", ... } | null,
"selectedBranch": { "name": "...", "short_hash": "...", ... } | null
},
"comments": [
{
"id": "...",
"file": "src/App.tsx",
"startLine": 10,
"endLine": 12,
"side": "old|new",
"text": "...",
"createdAt": "..."
}
]
}
Parse the JSON and iterate over the comments array. Each comment has a file, startLine/endLine, side ("old" = deleted code, "new" = added/current code), and text.
Address every comment. For each review comment:
Summarize. After all changes are made, provide a concise summary listing each comment and what you did to address it.
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.Provides 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.
npx claudepluginhub mrmans0n/ai-review --plugin ai-review