Loading...
Loading...
Found 55 Skills
GANG orchestrator skill. You are the orch, orchestrating the GANG closed loop — split features / assign peers / collect verdicts / update the board / perform integration validation / report to humans.
A curated collection of research papers and resources on agentic reasoning for Large Language Models, organized by planning, tool use, search, self-evolution, and multi-agent systems.
Implementation guidance for creating individual agents in the Arcanea system with proper structure, capabilities, and integration.
Multi-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships.
Use when wiring an external agent framework (LangGraph, CrewAI, PydanticAI, Mastra, ADK, LlamaIndex, Agno, Strands, Microsoft Agent Framework, or others) into a CopilotKit application via the AG-UI protocol.
Initialize a Harness Engineering framework in the current project. Use when user says 'harness', 'init harness', 'initialize framework', 'setup harness engineering', '/harness', or wants to set up a Plan-Build-Verify development workflow with specialized agents (planner, generator, evaluator). Creates CLAUDE.md, agent definitions, command templates, hooks, and documentation structure for autonomous AI-driven development.
INVOKE THIS SKILL when using the langgraph CLI to scaffold, develop, build, or deploy LangGraph applications. Covers langgraph new, dev, build, up, deploy, and langgraph.json configuration.
This skill should be used when the user asks to "develop a concept", "explore a new idea", "brainstorm a system concept", "do concept development", "create a concept document", "run Phase A", "define the problem and architecture", or mentions concept exploration, feasibility studies, concept of operations, system concept, architecture exploration, solution landscape, or NASA Phase A.
Framework for collective skill evolution in multi-user LLM agent ecosystems — automatically distills session experience into reusable SKILL.md files and shares them across agent clusters.
Adaptive multi-agent framework for automated data science tasks with planning, execution, and validation
LangGraph-based agent framework for consistent tool calling with automatic tool loops. Use when you need reliable multi-step task execution with OpenAI-compatible providers (Z.AI/GLM-5, OpenRouter, Groq, DeepSeek, Ollama).
A minimal teaching framework for understanding AI Agent architecture with core loop, fake LLM interface, and skill discovery system