Agent Skills Hub

memcontext-autopilot

An automated memory middleware for AI agents, implementing a Retrieve-Respond-Save loop to maintain long-term persistent context across conversations.

simplemem-skill

Persistent, semantic long-term memory for AI agents. Save, query, and retrieve cross-session dialogues, decisions, and multimodal context using semantic compression.

evidence-first-debugging

Enforces a strict evidence-based debugging workflow using structured observation, hypothesis testing, and causality validation to eliminate speculation in technical investigations.

skill-reinforcement

An automated meta-learning skill that improves agent workflows by capturing patterns, failures, and shortcuts after each task execution.

context-management

Proactive context window management for AI agents via intelligent token monitoring, snapshot creation, and selective state rehydration to maintain continuity during long sessions.

langchain-architecture

Architect production-grade LLM applications using LangChain 1.x and LangGraph. Implement stateful AI agents, multi-step workflows, and custom memory systems for complex conversational and automation tasks.

cascade-orchestrator

Advanced workflow orchestration for AI agents, featuring multi-model routing, Codex sandbox iteration, parallel swarm execution, and persistent memory across complex pipelines.

context-fundamentals

Foundational guidelines for context engineering: optimizing token budgets, attention mechanics, and system architecture for AI agents.

moollm

A microworld operating system for LLM-based agent living memory, transforming filesystems into navigable rooms and code into habitable worlds.

state-snapshot

Capture a complete debuggee state snapshot, including all committed memory regions and processor registers, for offline analysis and forensic investigation.

novelty-check

Verify research idea novelty against recent literature. Use when user says '查新', 'novelty check', or needs to confirm if a method is original.

doc-sync

Synchronizes and maintains CLAUDE.md and README.md documentation hierarchy across a repository to ensure consistent, just-in-time context for AI agents.