Review staged changes and create atomic Git commits whose messages match repository conventions. Use when the user asks to commit, write a commit message, or finalize already staged work.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Create a commit that accurately describes one logical staged change.
Treat the staging area as user-controlled input. Do not stage, unstage, or
otherwise alter it unless the user explicitly asks for that operation. Use the
git-staging skill when selective staging is requested.
If nothing is staged, report that fact and ask whether the user wants help staging. If staged and unstaged changes coexist, keep them distinct throughout the review.
git status, git diff --cached --no-ext-diff, and enough recent
history to learn the repository's message style.Follow repository conventions first. Use Conventional Commits only when the history or project rules use them. Keep the subject concise and imperative when that matches local style; add a body when rationale, behavior changes, or migration details would help future readers.
Include issue references, task files, sign-offs, or AI attribution only when relevant or required by the repository or user. Do not fabricate metadata.
Before reporting success, inspect the created commit (for example with
git show --stat --oneline HEAD) and state what remains uncommitted.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Applies local reliability, viewport, tab-safety, stale-ref, widget, and browser-boundary lessons to every agent-browser automation. Use alongside the upstream agent-browser skill whenever navigating, clicking, filling, testing, extracting, taking screenshots, or debugging any website with agent-browser.
The English summary is being prepared. Showing the original description.
Size the agent-browser Chromium window to fill its current screen, leaving a configurable bottom margin for the desktop panel. Use before any agent-browser automation that needs the full screen visible without elements overlapping or scrolling off (e.g. Xero, dense web apps).
The English summary is being prepared. Showing the original description.
Create Claude Code slash commands, OpenCode command files, Pi prompt templates, and Codex custom prompts that delegate to the right subagent or skill. Use when creating new commands, porting commands across agent platforms, or refactoring existing commands to follow platform conventions.
The English summary is being prepared. Showing the original description.
Adds or changes allowed commands in AI agent permission configs for OpenCode and Claude Code. Use when a command needs adding to an agent's allow list, when permission settings for existing commands need changing, when setting up a new AI tool that requires command permissions, or when the user asks to stop being prompted for a particular command.
The English summary is being prepared. Showing the original description.
Creates a Beads issue for a described problem or piece of work without doing the work itself. Use when the user invokes `/bc` or `$bc`, or asks to file, log, or record a bead for something. To also carry out the work, use the `bx` skill instead.
The English summary is being prepared. Showing the original description.
Stores a persistent memory or learning with `bd remember` so it survives across sessions. Use when the user invokes `/bdr` or `$bdr`, or asks to remember, note, or persist an insight in a Beads workspace.
The English summary is being prepared. Showing the original description.