From review
Enables interactive git diff reviews: generates clean diffs for editor annotations, applies Claude fixes based on feedback, loops until approved.
How this skill is triggered — by the user, by Claude, or both
Slash command
/review:git-reviewThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Interactive annotation-based code review using editor overlays.
Interactive annotation-based code review using editor overlays.
$EDITOR via tmux popup, kitty overlay, or wezterm split-pane${CLAUDE_PLUGIN_ROOT}/skills/git-review/scripts/git-review.py [base_ref]
HEAD~3)If the script produces output (stdout), the user made annotations. The output is a git diff showing what the user added/changed in the review file.
Read the diff carefully:
Each annotation is in context — the surrounding === file headers and diff content
show which file and code area the annotation refers to.
Enter plan mode (EnterPlanMode) to analyze annotations and design the fix approach:
After plan approval, fix the actual source code in the real repository. Each annotation is a directive — treat it as a code review comment that must be addressed.
After fixing code, run the script again. It regenerates a fresh diff reflecting the fixes and opens the editor. The user can:
When the script produces no output, the review is complete. Inform the user.
| Argument | Description |
|---|---|
| (none) | auto-detect: uncommitted changes if present, otherwise branch vs default branch |
<ref> | diff against specific ref: master, main, HEAD~5, v1.2.0, etc. |
--clean | remove the review tracking repo from /tmp |
--test | run embedded unit tests |
User: "review my changes"
→ run: git-review.py
→ editor opens with cleaned diff
→ user adds "this should validate input" next to a handler
→ user closes editor
→ stdout shows the annotation
→ enter plan mode: "annotation requests input validation in handler.go, plan: add validate() call"
→ user approves plan
→ Claude adds input validation to the handler
→ run: git-review.py (again)
→ editor opens with updated diff (validation now visible)
→ user closes without changes
→ no stdout → review complete
→ "review complete, all annotations addressed"
$EDITOR set (defaults to micro)allow_remote_control yes and listen_on unix:/tmp/kitty-$KITTY_PIDnpx claudepluginhub umputun/cc-thingz --plugin reviewReview diffs and files with inline annotations in a terminal TUI overlay. Works with git, hg, and jj repos. Also answers usage and configuration questions.
Self-review code changes using GitHub-style visual diff viewer (difit). Add comments on specific lines in browser; comments output to Claude for applying edits via git diff.
Open the native, Monaco-powered diff review window so the user can leave inline / file-level / overall comments on the current changes (the AI slop), then address each comment. Use this when the user asks to "review my changes", "review the slop", "review my diff", "open a diff review", "open the review window", "get feedback on my work", "do a PR-style review", "show me what I changed and let me comment", or types `@slop-review` explicitly. Defaults to a PR-style review of all commits + uncommitted changes since the merge-base with the auto-detected base branch (origin/HEAD → origin/main → main → origin/master → master); also supports last-commit, uncommitted, and all-files modes.