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".
Environment Triage
Migration workflow - research β analyze β plan β implement β review
Search past reasoning for relevant decisions and approaches
Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity
Reference guide for Agentica multi-agent infrastructure APIs
Parallel Agent Orchestration
Identify failure modes before they occur using structured risk analysis
Guide for integrating Agentica SDK with Claude Code CLI proxy
Never Use TaskOutput
Maps questions to the optimal tldr command. Use this to pick the right layer
Token-efficient code analysis via 5-layer stack (AST, Call Graph, CFG, DFG, PDG). 95% token savings.
Deep interview process to transform vague ideas into detailed specs. Works for technical and non-technical users.
TDD workflow for migrations - orchestrate agents, zero main context growth
Implement technical plans from thoughts/shared/plans with verification
Generate comprehensive PR descriptions following repository templates
Friendly onboarding when users ask about capabilities
Document codebase as-is with thoughts directory for historical context
Show full session token usage, costs, TLDR savings, and hook activity
Create and configure Claude Code sub-agents with custom prompts, tools, and models