Agent
Maps implementation and tests to task acceptance criteria, identifies remaining gaps, and provides a clear done/partial/not-done status for each requirement.
Agent
Maps implementation and tests to task acceptance criteria, identifies remaining gaps, and provides a clear done/partial/not-done status for each requirement.
Agent
Investigates external APIs, libraries, and framework behavior, then produces concise implementation guidance with constraints, examples, and risks for the coding agent.
Agent
Converts bug reports, logs, and stack traces into reproducible steps, suspected root causes, and a minimal investigation plan before implementation begins.
Agent
Performs a strict, checklist-driven review of recent changes for correctness, edge cases, regressions, maintainability, and project standard compliance.
Agent
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.
Agent
Updates developer-facing documentation, README notes, migration guidance, and changelog entries to match recent code changes without inventing undocumented behavior.
Agent
Implements a scoped plan step with minimal diffs, preserving existing behavior outside the requested change. Focuses on one plan step at a time.
Agent
Research agent for CV, robotics, and technical questions.
Agent
Translates a task into a minimal, executable implementation plan with scoped steps, risks, and a test strategy. Produces plans before coding starts.
Agent
Writes and improves tests for new behavior and bug fixes, prioritizing regression coverage, edge cases, and reproducibility. Focuses on tests first for bugs.
Skill Claude CodeCodex
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Skill Claude CodeCodex
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Use when asked to "simplify code", "clean up code", "refactor for clarity", "improve readability", or review recently modified code for elegance. Focuses on project-specific best practices.
Skill Claude CodeCodex
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies.
Skill Claude CodeCodex
Use when you have a written implementation plan to execute in a separate session with review checkpoints.
Skill Claude CodeCodex
Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review, or audit code on the current branch.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
Interview user in-depth to create a detailed spec.
Skill Claude CodeCodex
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.
Skill Claude CodeCodex
Use when completing tasks, implementing major features, or before merging to verify work meets requirements.
Skill Claude CodeCodex
Use when executing implementation plans with independent tasks in the current session.
Skill Claude CodeCodex
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
Skill Claude CodeCodex
Use when implementing any feature or bugfix, before writing implementation code.
Skill Claude CodeCodex
Use when starting any conversation - routes work through the correct worker agents before any task action, requiring explicit worker selection and visible compliance.
Skill Claude CodeCodex
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always.