Continual Learning & Self-improving skills system for Claude Code - learn from corrections, never repeat mistakes

A production-ready, modular Unity framework with UE-inspired Gameplay Ability System, zero-GC infrastructure, and hot-update support. Battle-tested, DI-friendly, and cross-platform optimized. 一个高性能、高拓展性、高度优化、支持热更新、功能强大的 Unity 启动模板。具有类虚幻引擎的 GameplayFramework 与 GAS 设计，高度兼容各类控制反转（IoC/DI）框架。

🐙 A curated set of Codex and OpenClaw skills for workflow automation, technical debugging, and agent-assisted development patterns.

Complete game production workflow for Claude Code — 27 skills from concept to shipped build. Design review, prototype planning, game feel diagnosis, playability assessment, QA with fix loop, and release. Built on gstack methodology.

This Unity project implement the Gameplay Ability System and provides a demo of an ARPG.

Open-source Android device automation framework — control real phones via ADB with Python skills, a Vue dashboard, and LLM-powered tooling

EDAgent is a skill-based LLM agent designed to assist EDA research workflows, routing user requests to appropriate skills for code analysis, debugging, experiment setup, and research automation.

Autonomous AI Desktop Agent for Linux – Multi-LLM, Desktop Control via VNC, WhatsApp Integration, RAG Knowledge Base, OpenClaw Skill Ecosystem

Operable AI agent system: plan, execute, verify, and close work with project-scoped memory and auditable contracts.

Multi-agent AI marketing team with 118 skills, 22 LLM providers, shared memory, and 7 chat channels

skill system DEMO based on event-condition-action rescursion

SEO-GEO Skill System for Claude Code & Claude.ai — 5 connected skills: Collector → Auditor (/90) → Implementer → Monitor. Technical SEO, Core Web Vitals, E-E-A-T, Entity SEO, AI visibility (ChatGPT, Perplexity, Claude), competitive analysis. English by default.

Agent Operating System running locally in the browser: a persistent, tool-driven AI that reasons in an agentic loop, executes skills, manages memory/state, and evolves over time with optional sync and strict governance.

Codex meta-skill that detects repeated workflow bottlenecks and proposes new skills only when evidence-based thresholds are met.

OpenClaw Self-Evolving Skill System Extended | Async Review +96% Faster | AI Agent Skills | Chinese/English Docs

📚 Enable AI agents to autonomously learn new technologies from official web sources and create reusable skills for research and development.

AXI: A next-generation Cybernetic Intelligence Assistant. High-performance voice control, HUD-inspired interface, and autonomous learning powered by a custom-built NLP engine with 1,400+ intents.

SkillEngine — framework-agnostic skills engine for LLM agents. Claude Code-like experience on any model.

🧠 Enhance AI learning with the Claude Reflect System, an innovative self-learning tool that adapts from your corrections for improved performance.

🦞 OpenClaw AI Agent Workspace — Complete configuration, memory system, skill modules & training plans. Powered by Ollama + Qdrant + FastAPI. OpenAI-compatible, supports local LLMs and cloud APIs.