autonomous-dev-kit

Use when completing tasks, implementing major features, or before merging to verify work meets requirements - runs review in a forked code-reviewer agent

Activate autonomous loop mode for persistent development sessions. **CRITICAL:** Always activate this AFTER completing spec and implementation plan, BEFORE beginning implementation. This is what makes autonomous builds actually autonomous—the Stop hook enforces completion criteria.

Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes

Apply systematic root cause analysis and debugging methodologies to diagnose and fix bugs, test failures, and unexpected behavior. Use when encountering production issues, investigating test failures, diagnosing performance problems, tracing error sources through call stacks, analyzing logs and stack traces, reproducing inconsistent bugs, debugging race conditions, investigating memory leaks, or applying scientific method to problem-solving before proposing fixes.

Activate orchestrator mode. You coordinate specialists, you don't implement. MAXIMIZE parallelism with task-builder. MAXIMIZE quality with code-reviewer, codex, gemini. Speed + Quality through delegation, not through doing work yourself.

Execute ONE task in parallel with other task-builders. ALWAYS SPAWN MULTIPLE for independent tasks. ORCHESTRATOR: You coordinate, you don't implement. Spawn N task-builders for N unblocked tasks. Maximum parallelism = maximum speed = maximum quality (each task gets focused attention).

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge

This skill should be used when the user asks to "use Claude Code", "Claude Code best practices", "run Claude headless", "claude -p", "plan mode", "configure Claude Code", or "optimize Claude Code workflows".

This skill should be used when the user asks to "use Codex CLI", "codex exec", "get a Codex second opinion", or "run a Codex review" as a separate agent.

This skill should be used when the user asks to "use Gemini", "get a Gemini review", "delegate to Gemini CLI", or "run Gemini headless" for a second opinion.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Coordinate multiple Claude Code sessions working on the same project via shared task list. Creates task DAG, assigns work to parallel agents, monitors progress. Use for large implementations that benefit from true parallelism.

This skill should be used when the user asks to write/debug GLSL shaders, create custom materials/effects, implement procedural noise/SDFs, port Shadertoy/Unity/HLSL shaders, optimize shader performance, or build post-processing effects in Three.js/WebGL.

This skill should be used when the user asks to build Three.js scenes in React, use React Three Fiber/Drei, optimize R3F performance, integrate physics/animations/shaders, manage 3D assets in React, or mentions "R3F", "react-three-fiber", or "Drei".

This skill should be used when the user asks to "build a Three.js app", "optimize Three.js performance", "set up a 3D asset pipeline", "add postprocessing/particles/physics", or needs production-grade Three.js architecture and rendering guidance.

Run accessibility checks on interactive UI components. Use after implementing UI, before code review. Forked to a11y-reviewer agent. Creates TodoWrite items for each check. Covers WCAG AA compliance: labels, keyboard nav, focus, color contrast, motion, and content.

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - runs in a forked review-triager agent for rigorous verification

Validate a specification before implementation. Use when you've drafted a spec and need to verify it's complete, precise, and unambiguous. Runs in a forked spec-reviewer agent. Creates TodoWrite items for each check. Run this before proceeding to implementation planning.