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.From its SKILL.md
npx -y skills add mrmans0n/ai-review --skill human-reviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 6 stars6 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
3.8 KB, as published. Nobody here has run it
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.
Steps
-
Determine what to review. Check these in priority order to pick the right
airinvocation:a. Uncommitted changes exist (staged or unstaged, check via
git status --porcelain): Runair --wait --jsonwith 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/namepattern (no--in the name part) and.git/gg/config.jsonexists: Read the gg base branch from config (parsedefaults.base, fall back tomain). Run:air --wait --json --commits <gg-base>..HEADThis 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 (
mainormaster, 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(ororigin/master) and take the first commit hash. Run:air --wait --json --commit <first-relevant-commit-hash>e. None of the above: Run
air --wait --jsonwith no flags (empty diff — the app handles it).The
aircommand 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
commentsarray. Each comment has afile,startLine/endLine,side("old"= deleted code,"new"= added/current code), andtext. -
Address every comment. For each review comment:
- Read the referenced file and lines
- Make the requested change
- If a comment is unclear, use your best judgment based on the surrounding code context
-
Summarize. After all changes are made, provide a concise summary listing each comment and what you did to address it.
Notes
- If
airis not found, tell the user to install viabrew install --cask mrmans0n/tap/ai-review(macOS) or build from source at https://github.com/mrmans0n/ai-review. - If the diff is empty (current branch is identical to base), inform the user there are no changes to review.
- Do NOT commit after making changes — let the user decide when to commit.