hexmostech/git-lrc/claude
- community
Checking that the SKILL.md file is still in the repository.
Manage LiveReview code review for staged changes in this repo. Run /lrc review to open a browser-based AI review of staged changes before committing. Use /lrc skip to bypass review and write an attestation, or /lrc vouch to manually approve without AI. Check and toggle hook state with /lrc hooks status, hooks disable, hooks enable, hooks install, or hooks uninstall. Invoke when the user explicitly wants to review code, explicitly skip a review, vouch for changes, check if LiveReview is active, turn off hooks, or reinstall the Claude git-commit gate.
Install
npx vskill@latest install hexmostech/git-lrc/claudeSKILL.md
lrc
Run commands from the current repository root. Map $ARGUMENTS to the matching command below. Translate plain natural-language requests to the nearest command before running.
Review commands
| Intent | Command | |
|---|---|---|
| Review staged changes | lrc review --staged | |
| Review staged + block until browser decision | lrc review --staged --blocking-review | |
| Skip review (write attestation, no AI) | lrc review --staged --skip | |
| Vouch for changes manually | lrc review --staged --vouch | |
| Review a specific prior commit | lrc review --commit HEAD | |
| Non-interactive review (agent/CI) | lrc review --no-serve --output json --staged | |
| Non-interactive range review | lrc review --no-serve --output json --range main...feature |
Hooks commands
| Intent | Command | |
|---|---|---|
| Check hook status | lrc hooks status | |
| Check Claude hook status only | lrc hooks status --surface claude | |
| Disable all hooks in this repo | lrc hooks disable | |
| Disable only the Claude gate | lrc hooks disable --surface claude | |
| Re-enable hooks in this repo | lrc hooks enable | |
| Re-enable only the Claude gate | lrc hooks enable --surface claude | |
| Install global Claude hook | lrc hooks install --surface claude | |
| Remove global Claude hook | lrc hooks uninstall --surface claude |
Rules
- Prefer lrc hooks status before mutating hook state when intent is ambiguous.
- Use
lrc review --staged --skiponly when the user explicitly asks to skip or bypass review. Never use skip as a fallback after a hook, wrapper, or review failure. - Use
lrc hooks disableorlrc hooks disable --surface claudeonly when the user explicitly asks to disable hooks. Never disable hooks as a fallback for a failing review flow. - Repo-local disable/enable uses marker files under .git/lrc/: disabled, disabled-git, disabled-claude.
- Global Claude integration lives in ~/.lrc/claude/hooks/ and ~/.claude/settings.json — manage only via lrc hooks install/uninstall.
- Never edit .claude/settings.local.json directly; it is not the control plane when the global install is active.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckinghooks/claude/SKILL.md
Popularity
- Repository stars
- 1,435
- Repository forks
- 190
- 7-day trend score
- 36
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/hexmostech/git-lrc/claude)