Agent
Test-driven development enforcement specialist ensuring 80%+ code coverage. Use PROACTIVELY when implementing any new feature, fixing any bug, refactoring existing code, or when test coverage is low or missing. MUST BE USED on every feature request, bug report, and refactoring task to enforce the write-tests-first…
Command
Review API design for REST conventions and best practices.
Command
Incrementally fix build errors one at a time.
Command
Create a git commit checkpoint of current progress.
Command
Review database schema, queries, and migrations.
Command
Systematic debugging process to isolate and fix issues.
Command
Pre-deployment verification checklist.
Command
Auto-fix lint and formatting issues across the codebase.
Command
Profile and optimize application performance.
Command
Create a detailed implementation plan for a feature or project.
Command
Clean up dead code and refactor for maintainability.
Command
Run code review on recent changes.
Command
Run OWASP-based security audit on the codebase.
Command
Start test-driven development workflow for a feature or fix.
Command
Analyze test coverage and add missing tests to reach 80%.
Command
Find and update outdated documentation.
Hook
Runs before the agent uses a tool for tool == "Bash" && tool_input.command matches "(npm run dev, pnpm( run)? dev, yarn dev, bun run dev)", tool == "Bash" && tool_input.command matches "git push", tool == "Bash" && tool_input.command matches "(npm, pnpm, yarn, bun) (install and add)" tool calls, running an inline…
Hook
Runs after a tool call finishes for tool == "Edit" && tool_input.file_path matches "\\.(ts, tsx, js, jsx)$", tool == "Write" && tool_input.file_path matches "\\.(ts and tsx)$" tool calls, running an inline shell check (2 commands). From VersoXBT/claude-initial-setup.
Skill Claude CodeCodex
Patterns for running independent tasks in parallel using multiple tool calls and Agent invocations. Use when the user has multiple independent operations, asks about fan-out/fan-in, or wants to speed up multi-step workflows.
Skill Claude CodeCodex
Patterns for when and how to use Claude Code subagents via the Agent tool. Use when the user needs to delegate research, run parallel investigations, protect the main context window, or asks about subagent types like Explore or Plan.
Skill Claude CodeCodex
Patterns for using TaskCreate, TaskUpdate, TaskList, and TaskGet to coordinate multi-step work. Use when the user has a complex project with multiple steps, needs progress tracking, dependency management, or multi-agent task assignment.
Skill Claude CodeCodex
Patterns for inter-agent communication including message passing, shared state, event-driven architectures, pub/sub, inbox/outbox, and structured vs freeform messages. Use when the user is building systems where multiple agents need to communicate, share information, coordinate work, or pass data between processing…
Skill Claude CodeCodex
Strategies for managing AI agent context windows including optimization, summarization, retrieval-augmented generation, progressive disclosure, and pruning. Use when the user is hitting context limits, building long-running agents, implementing RAG, optimizing token usage, or designing systems that need to manage…
Skill Claude CodeCodex
Patterns for multi-agent systems including orchestrator, pipeline, consensus, delegation, supervisor, and swarm patterns. Use when the user is building multi-agent workflows, coordinating multiple AI agents, implementing agent delegation or supervision, or designing systems where agents collaborate on complex tasks.