
Manage git branch mixes and run mixdowns using ggmx and ggmxd. Use when the user says things like "add this branch to the mix", "remove a branch from the mix", "show the mix", "mix down the branches", or "run a mixdown".
Update documentation based on lessons learned. Use after completing work to capture learnings and prevent future issues.
Implement a single sub-task from a task list. Use when working on feature development with existing task lists.
Break multi-file changes into atomic commits ordered by dependency. Use for refactors, breaking API changes, or features touching 3+ files.
Create well-formatted commits following conventional commits style with proper atomic commits and descriptive messages
Find Linear issues ready for an AI agent to pick up. Equivalent of `bd ready` for Linear workflows. Use when starting a session to find claimable work, or when asked "what's next" or "find work".
Manage Open Build Service (OBS) projects. Use when working with OBS packages for home:aspiers.
Remove code duplication by extracting shared logic into reusable components. Use when the same logic appears in multiple places.
Review code for quality, security, and maintainability. Use after code changes are completed and ready for review.
Generate a .editorconfig file for a repository
Stage files, hunks, or specific lines in git non-interactively.
Initialize a project with AI agent rules and documentation. Use when setting up a new repository for AI agent collaboration.
Safely delete files / directories without asking for permission
Orchestrate the complete development workflow for implementing sub-tasks from a task list. Use for end-to-end feature implementation with quality controls.
Generate a detailed task list from a PRP. Use after a PRP is created and ready for implementation planning.
Create subagent definitions for Claude Code and OpenCode that delegate to skills. Use when creating new subagents or refactoring existing ones to follow the delegation pattern.
Pipe long running commands through tee(1) to allow watching output and repeated analyses without rerunning
Create Claude Code slash commands and OpenCode command files that delegate to subagents. Use when creating new commands or refactoring existing ones to follow the delegation pattern.
Run linters according to repository guidelines. Use immediately after creating or modifying code, or before committing changes.
Refactor overly large code units into smaller, more focused components. Use when code has grown too large or complex.
Generate a PR description for the current branch. Writes Markdown to .git/magit/posts/new-pullreq for use with magit-forge.
Implement sub-tasks iteratively with user approval between each one. Use when working through a task list with user collaboration.
Decompose an approved implementation plan into self-contained beads issues with zero guesswork. Use when breaking down a plan file into actionable beads tasks.
Decompose an approved implementation plan into self-contained Linear issues with zero guesswork. Use when breaking down a plan into actionable Linear tasks via the MCP server.
Create and maintain Claude Code skills following Anthropic best practices. Use when building new skills, refactoring existing ones, or ensuring skills follow official guidelines for structure, naming, progressive disclosure, and testing.
Generate a Product Requirements Prompt (PRP) from a feature description. Use when starting work on a new feature.
Add or change allowed commands in AI agent permission configs (OpenCode, Claude Code)
Run tests according to repository guidelines. Use after linting passes, before staging changes.