AI & Agents Agent Skills

Byzantine fault-tolerant consensus and distributed coordination.

Advanced Hive Mind collective intelligence system for queen-led multi-agent coordination with consensus mechanisms and persistent memory

Disable the AIWG context hook without uninstalling AIWG or deleting hook files

Designing intervention points where humans review, approve, or redirect agent work.

Install context files from registry. Use when user runs /install-context, says "install context", "setup context", or when context is…

Install plugin hooks into project .claude/ for persistent use without plugin loaded

Run tasks in a loop until goals are met — use for iterative refinement, polling, or convergence

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that…

Switch to Knowledge Work mode for research and writing — use when task is non-code focused

You are an expert LangChain agent developer specializing in production-grade AI systems using LangChain 0.1+ and LangGraph.

LangChain ReAct agent implementation with tool binding for reasoning and action loops

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that…

LangGraph StateGraph builder with state schema design.

Design patterns for the Langroid multi-agent LLM framework.

Create a new Lattice skill — atom, molecule, or refiner — following all framework conventions.

Claude Code Hero Level 11: The Oracle Well -- connect an MCP server and gain a new tool

Claude Code Hero Level 4: The Warden's Keys -- configure permission rules in .claude/settings.json

Claude Code Hero Level 5: The Enchanted Inscription -- create a path-scoped rule in .claude/rules/

Synchronizes local Claude skills to GitHub with automatic Org-mode to Markdown conversion and documentation validation.

Get reliable JSON, enums, and typed objects from LLMs using response_format, tool_use, and schema-constrained decoding across OpenAI…

Agent skill for load-balancer - invoke with $agent-load-balancer