Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture)
MCP Script Rules
Parallel Agent Orchestration
Migration workflow - research β analyze β plan β implement β review
Wiring Verification
Graceful Degradation with Helpful Messages
External research workflow for docs, web, APIs - NOT codebase exploration
Resume work from handoff document with context analysis and validation
Planning agent that creates implementation plans and handoffs from conversation context
Release preparation workflow - security audit β E2E tests β review β changelog β docs
Full 5-layer analysis of a specific function. Use when debugging or deeply understanding code.
Meta-skill for creating and managing Claude Code skills
Token-efficient code analysis via 5-layer stack (AST, Call Graph, CFG, DFG, PDG). 95% token savings.
Implement technical plans from thoughts/shared/plans with verification
Friendly onboarding when users ask about capabilities
Create and use Claude Code slash commands - quick prompts, bash execution, file references
AST-based code search and refactoring via ast-grep MCP
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".
Agentica server + Claude proxy setup - architecture, startup sequence, debugging
Parallel Agent Type Contracts