Fast file editing via Morph Apply API (10,500 tokens/sec, 98% accuracy)

Comprehensive testing workflow - unit tests ∥ integration tests → E2E tests

Meta-skill workflow orchestrator for bug investigation and resolution. Routes to debug, implement, test, and commit based on scope.

Identify failure modes before they occur using structured risk analysis

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge,...

Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize failure context, then create a fix plan and implement after user approval. Use when a user asks to debug or fix...

System health check (MOT) for skills, agents, hooks, and memory

Implementation agent that executes a single task and creates handoff on completion

Security audit workflow - vulnerability scan → verification

Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.

Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns should become skills".

Troubleshoot Claude Code extensions and behavior. Triggers on: debug, troubleshoot, not working, skill not loading, hook not running, agent not found.

Research-to-implement pipeline chaining 5 MCP tools with graceful degradation

Unified math capabilities - computation, solving, and explanation. I route to the right tool.

Boilerplate templates for Claude Code extensions. Triggers on: create agent, new skill, command template, hook script, extension scaffold.

External research workflow for docs, web, APIs - NOT codebase exploration

Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration

Friendly onboarding when users ask about capabilities

Claude Code hook system for pre/post tool execution. Triggers on: hooks, PreToolUse, PostToolUse, hook script, tool validation, audit logging.

Run Claude Code programmatically without interactive UI. Triggers on: headless, CLI automation, --print, output-format, stream-json, CI/CD, scripting.