dotfiles

Use when the user asks to commit, write a commit message, generate a conventional commit, or invokes /conventional-commit. Also use when staged changes need a commitlint-compliant message, when the user asks to commit and push (or passes --push), when unstaged or untracked files exist and staging scope must be confirmed, or when agent-attribution trailers must be avoided on commits. Handles git commit and git push flags when the user passes them.

Use when the user asks to create, open, or raise a GitHub pull request, submit changes for review. Also when staged, committed, or unpushed work needs a PR via gh CLI and required PR metadata is missing (base branch, draft vs ready, reviewers, labels, linked issues, test plan).

Use when the task is multi-constraint, ambiguous, architectural, or needs a design/algorithm choice before answering. Skip for trivial lookups and one-line edits.

Use when the user explicitly asks to audit, critic, or verify a generated solution or answer (e.g. /verifying-solutions, "audit this", "critic this") — not for routine completion claims or pre-answer design.

Use when staging, formatting, or creating git commits for code changes in a Git repository.

Analyzes error logs, stack traces, and provides systematic debugging strategies and solutions

Drafts professional emails based on context, tone, and purpose with templates and suggestions

Explain mode. Analyzes the codebase to answer questions and provide insights

Interactive Explore mode. Interactively explains the codebase through guided discovery

Performs a comprehensive security audit of code changes, dependencies, and potential vulnerabilities

Identifies and suggests cleanup opportunities including unused code, dependencies, and optimization possibilities

Find relevant documentation and output GitHub URLs

Generates TSDoc comments for a given JavaScript or TypeScript code snippet

Analyzes the current project directory recursively and generate a comprehensive GEMINI.md file

Automatically generates comprehensive test cases for functions, classes, or modules with edge cases and best practices

Intelligently organizes files in directories based on content type, date, and purpose with safe automation

Analyzes tasks and priorities to create organized, actionable task lists with time estimates and urgency levels

Organizes and renames photos based on their visual content, date, and location metadata

Generates comprehensive reports from data files and folders, with analysis and visualizations

Performs a code review on the specified code, providing feedback and suggestions

Reviews a pull request based on issue number

Summarizes meeting notes, transcripts, or discussions into actionable insights and follow-up items

Fetches and summarizes the latest release notes for specified Google Cloud products

Generates a Git commit message based on staged, modified, or untracked changes

Systematic multi-source research across web, GitHub, community discussions, and official docs. Use when asked to research best practices, trends, patterns, or find information on any topic. Invoke with a topic to research.

Manage and install active agentic skills. Use when the user asks to search, install, list, or enable/disable skills.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Systematically compares package.json dependency entries to actual repo usage via imports, requires, configs, and scripts. Use when auditing dead dependencies, cleaning package.json, answering “is X still used?”, before removing packages, or reducing install size and supply-chain surface.