Loading...
Loading...
Found 162 Skills
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
Turns a free-form project description into PROJECT_MANIFEST.md and SOFTWARE_FACTORY_MANIFEST.md for a 6-agent software factory pipeline. Agent-agnostic: works in Claude Code, Codex CLI, Gemini CLI.
Fan out a prompt to multiple AI coding agents in parallel and synthesize their responses.
AI agent development workflow for building autonomous agents, multi-agent systems, and agent orchestration with CrewAI, LangGraph, and custom agents.
Semantic search over global agent memory. Use to retrieve previously learned patterns, decisions, gotchas, and workarounds. Prevents stale-context errors across long sessions and multi-agent pipelines.
Use this skill when designing AI agent architectures, implementing tool use, building multi-agent systems, or creating agent memory. Triggers on AI agents, tool calling, agent loops, ReAct pattern, multi-agent orchestration, agent memory, planning strategies, agent evaluation, and any task requiring autonomous AI agent design.
Ouroboros specification-first AI development — the complete system. Socratic interviewing crystallizes vague ideas into immutable specs (Ambiguity ≤ 0.2) before any code is written. Nine Minds agents (socratic-interviewer, ontologist, seed-architect, evaluator, contrarian, hacker, simplifier, researcher, architect) execute the Double Diamond. Ralph mode loops with state persistence until verification passes — the boulder never stops. Use when user says "ralph", "ooo", "ooo interview", "ooo seed", "ooo run", "ooo evaluate", "ooo evolve", "ooo unstuck", "ooo status", "ooo ralph", "stop prompting", "start specifying", "specification first", "socratic interview", "don't stop", "must complete", "keep going", or "the boulder never stops".
Use when a single agent demonstrably cannot handle the task and multi-agent coordination is justified.
Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases.
Automatic agent selection and intelligent task routing. Analyzes user requests and automatically selects the best specialist agent(s) without requiring explicit user mentions.
Build multiple AI agents that work together. Use when you need a supervisor agent that delegates to specialists, agent handoff, parallel research agents, support escalation (L1 to L2), content pipeline (writer + editor + fact-checker), or any multi-agent system. Powered by DSPy for optimizable agents and LangGraph for orchestration.
Friendly onboarding when users ask about capabilities