Skill Claude CodeCodex
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Skill Claude CodeCodex
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Agent Claude Code
Use this agent when you need to locate specific functions, classes, or logic within the codebase. Examples: Context: User needs to find authentication-related code in the project. user: "Where is the user authentication logic implemented?" assistant: "I'll use the code-searcher agent to locate authentication-related…
Agent Claude Code
Execute TZ='Africa/Cairo' date command and return ONLY the raw output. No formatting, headers, explanations, or parallel agents.
Agent Claude Code
Analyzes git changes, groups them logically, and creates Conventional Commits for each group. Use proactively after code changes to ensure atomic, meaningful commits.
Command Claude Code
Interactive design refinement using Socratic method.
Command Claude Code
Create atomic git commits with Conventional Commits format using the git-commiter subagent.
Command Claude Code
Adds conciseness to the output.
Command Claude Code
Removes AI generated slop from the generated code.
Command Claude Code
Automatically fix a GitHub PR reviews by analyzing the codebase changes and the PR Reviews and implementing changes.
Command Claude Code
Automatically fix a GitHub issue by analyzing the codebase and implementing changes.
Settings file Claude Code
Agent settings declaring 6 hook events (PreToolUse, PostToolUse, UserPromptSubmit, SessionStart) and 1 allowed tools.
Agent
Analyzes git changes, groups them logically, and creates Conventional Commits for each group. Ensures atomic, meaningful commits and can be invoked by other agents.
Agent
Explores codebase and writes structured analysis documents. Spawned by map-codebase with a focus area (tech, arch, quality, concerns). Writes documents directly to reduce orchestrator context load.
Agent
Investigates bugs using scientific method, manages debug sessions, handles checkpoints. Spawned by /gsd-debug orchestrator.
Agent
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.
Agent
Verifies cross-phase integration and E2E flows. Checks that phases connect properly and user workflows complete end-to-end.
Agent
Fills Nyquist validation gaps by generating tests and verifying coverage for phase requirements.
Agent
Researches how to implement a phase before planning. Produces RESEARCH.md consumed by gsd-planner. Spawned by /gsd-plan-phase orchestrator.
Agent
Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality. Spawned by /gsd-plan-phase orchestrator.
Agent
Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification. Spawned by /gsd-plan-phase orchestrator.
Agent
Researches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by /gsd-new-project or /gsd-new-milestone orchestrators.
Agent
Synthesizes research outputs from parallel researcher agents into SUMMARY.md. Spawned by /gsd-new-project after 4 researcher agents complete.
Agent
Creates project roadmaps with phase breakdown, requirement mapping, success criteria derivation, and coverage validation. Spawned by /gsd-new-project orchestrator.
Agent
Verifies phase goal achievement through goal-backward analysis. Checks codebase delivers what phase promised, not just that tasks completed. Creates VERIFICATION.md report.