Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Pick the next shell whose dependencies are satisfied and carry it through planning: expand, refine, self-improve, halt. Use when the user asks to "pick next shell", "next shell", "continue project", "what's next", "next implementation step", or "continue with the plan".
Bidirectional planning for ambiguous or design-heavy tasks. Use when the user requests help breaking down a problem or formulating a plan, and also when an existing plan has too many gaps or needs refinement; converge top-down framing with bottom-up inventory and explicit questions.
Cancel an implementation plan. Moves the plan to archive/ with CANCELLED status. Use when a plan is superseded, abandoned, or no longer needed.
Plan/Code workflow for moderate to complex tasks. Defines when to use Plan vs Code mode. Applied automatically for non-trivial implementations.
Comprehensive project planning standards for plans/ directory including folder structure (ideas.md, backlog/, in-progress/, done/), naming convention (YYYY-MM-DD__identifier/), file organization (README.md for small plans, multi-file for large), and Gherkin acceptance criteria. Essential for creating structured, executable project plans.
Extracts work units from plan artifacts and creates sequenced GitHub issues. Use when (1) decomposing plan.md into actionable issues, (2) creating issues with validation checklists, (3) linking issue dependencies, or (4) executing after /plan command completion.
Design an implementation approach for a single ticket.
Explore the codebase and produce an implementation plan for a GitHub issue