Script and automate repetitive tasks and workflows.
GitHub Pull Request review operations using gh CLI. Extract PR info, view diffs with line numbers, retrieve and post comments, create inline comments, and reply to comments. Use when reviewing PRs, conducting code reviews, or performing PR operations.
Automatically synchronize README.md with actual project components. Scans .claude directory and updates Agents, Skills, Hooks, Commands sections.
Installs a Git safety guard hook for Claude Code to prevent destructive Git and filesystem commands. Blocks accidental data loss from commands like 'git checkout --', 'git reset --hard', 'git clean -f', 'git push --force', and 'rm -rf'. Use this skill to set up safety rails in a new or existing repository, or globally for the agent.
Generates clear commit messages following conventional commit conventions. Use when creating commits, suggesting commit messages, amending commits, creating fixup commits, or any operation involving git commit messages.
Practical Git hygiene for staging and committing: review diffs, stage intentionally, avoid committing noise/build artifacts/secrets, and recover from accidental staging or committing. Use when a user asks how to commit changes, write a commit workflow checklist, unstage/remove accidental files, or verify `.gitignore` behavior.
Sync modified and new files to chezmoi repository and push to GitHub. Use when Claude Code has modified or created files in a chezmoi-managed directory and needs to re-add them to chezmoi, commit changes, and push to the remote repository. Triggers on requests to sync, commit, or push chezmoi changes after file modifications.
The agent is capable of extraordinary work in this domain. These guidelines unlock that potential—they don't constrain it. Use judgment, adapt to context, and push boundaries when appropriate.. Use when When the user asks to address review comments on an open GitHub PR..
Fetch PR review comments from AI reviewers, verify accuracy, and apply valid fixes. Use when the user wants to process AI code review comments, apply AI reviewer suggestions, or verify and implement automated code review feedback. Works with GitHub PRs and uses web search to verify AI claims before applying changes.
⚠️ MANDATORY - YOU MUST invoke this skill before ANY destructive operation. Safety protocol for destructive git/file operations. Lists affected files, warns about data loss, suggests safe alternatives, requires explicit double confirmation. NEVER run destructive commands without invoking this skill.
Generate git commit messages from staged changes following Conventional Commits specification. Use when user wants to commit staged changes, asks for help writing commit messages, or invokes /commit command. Analyzes git diff, generates English commit message, and asks for user confirmation before committing.
Fetch and analyze GitHub PR review comments, evaluate their validity, and propose solutions. Use when the user asks to handle PR reviews, address reviewer feedback, check PR comments, or respond to code review suggestions.
Manage Git worktrees with ga/gd helpers to create, switch, and clean isolated branches quickly.
Request code review by dispatching reviewer subagent with proper context and git SHAs. WHEN: MUST use after completing major features or before merge. Invoke with "/requesting-code-review" or "request code review", "get review before merge". WHEN NOT: Receiving feedback (use receiving-code-review), design phase, debugging.
Systematic code review workflow for evaluating changes against coding standards. Use when reviewing pull requests, commits, diffs, or code changes. Ensures type-safety, maintainability, readability, and adherence to best practices before code is merged.
Performs interactive rebases with smart commit management and conflict resolution. Use when rebasing branches, cleaning up commit history, resolving conflicts, or when the user mentions "rebase", "interactive rebase", "squash commits", or wants to update their branch with latest changes from main/develop.
Automatically generate conventional commit messages when user has staged changes and mentions committing. Analyzes git diff and status to create properly formatted commit messages following conventional commits specification. Invoke when user mentions "commit", "staged", "committing", or asks for help with commit messages.
Analyze repository structure and generate comprehensive index. Use to understand codebase organization or create repo-index.md.
Use this agent when conducting thorough research on a repository's structure, documentation, and patterns. Specializes in analyzing architecture files, examining GitHub issues, reviewing contribution guidelines, and searching for implementation patterns. Triggers on requests like "analyze repository", "research codebase structure", "find patterns in repo".
Automated privacy review for git repositories. Scans for sensitive data exposure including API keys, passwords, database credentials, and tokens. Use before pushing to public repositories or sharing code. Trigger by running 'python privacy_scan.py' on a git repository.
Generates intelligent GitLab merge request descriptions from git commits with automatic categorization and Jira integration
Retrieve code diff from a GitHub Pull Request via GitHub API. Use this as the first step in a code review pipeline when reviewing GitHub PRs.
