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

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

Observe Before Editing

Interactive workspace discovery - learn what tools, workflows, agents, and hooks are available

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".

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

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

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

Security audit workflow - vulnerability scan → verification

OPC Architecture Understanding

Generate comprehensive PR descriptions following repository templates

Complete Claude Code configuration collection - agents, skills, hooks, commands, rules, MCPs. Battle-tested configs from an Anthropic hackathon winner.

Completion Check: Verify Infrastructure Is Wired

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

Workflow orchestrator that chains existing skills for feature development

Analyze repository structure, patterns, conventions, and documentation for understanding a new codebase

Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity

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

This skill provides guidance on using Google's Gemini CLI for long-context code exploration. Use when the user explicitly invokes "/gemini", asks to "use gemini", "run gemini", or when Claude...

Use RepoPrompt CLI for token-efficient codebase exploration