Spawn Agentica multi-agent patterns
AI & LLM
LLM integrations, prompt engineering, and AI orchestration
7,390 skills
Background Agent Pings
Analyze Claude Code sessions via Braintrust
Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging
Claude Code CLI commands, flags, headless mode, and automation patterns
Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup",...
Manage Clorch configuration (Braintrust, API keys, features)
Interactive workspace discovery - learn what tools, workflows, agents, and hooks are available
Implementation agent that executes a single task and creates handoff on completion
LLM Tuning Patterns
Research-to-implement pipeline chaining 5 MCP tools with graceful degradation
System health check (MOT) for skills, agents, hooks, and memory
No Polling for Background Agents
MANDATORY - Load this skill first. Routes to bootstrap + domain rules.
Parallel Agent Type Contracts
Parallel Agent Orchestration
AI-powered web search, research, and reasoning via Perplexity
Identify failure modes before they occur using structured risk analysis
Create and manage project-specific Claude Code hooks
Research agent for external documentation, best practices, and library APIs via MCP tools
Process large contexts using RLM (Recursive Language Model) patterns - chunking, filtering, recursive sub-calls
Meta-skill for creating and managing Claude Code skills
Create and configure Claude Code sub-agents with custom prompts, tools, and models
Goal-based workflow orchestration - routes tasks to specialist agents based on user goals