win4r — 26 Open-Source AI Agent Skills

win4r is the author of 26 open-source AI agent skills and MCP servers spanning agent-tool, codex-skill, claude-skill, mcp-server, with a combined 7,521+ GitHub stars. On AgentSkillsHub each is quality-scored (avg 58/100) and security-graded where a README exists (19 of 26) — 17 verified safe.

Top skills by win4r

• AISuperDomain — Aila(AI超元域): The premier AI integration tool for Windows, macOS, and Android. Ask once, get answers from 10+ AIs like ChatGPT, Gemini, Claud (2.0k★ · quality 62/100 · security: safe)
• memory-lancedb-pro — Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder Rerank, Multi-Scope Isolation, Management CLI (1.8k★ · quality 74/100 · security: safe)
• ClawTeam-OpenClaw — ClawTeam fork fully adapted for OpenClaw — multi-agent swarm coordination with OpenClaw as the default agent (1.5k★ · quality 72/100 · security: safe)
• openclaw-a2a-gateway — OpenClaw plugin implementing the A2A (Agent-to-Agent) protocol v0.3.0 — bidirectional agent communication gateway (551★ · quality 73/100 · security: safe)
• lossless-claw-enhanced — Fork of Martian-Engineering/lossless-claw with CJK-aware token estimation (541★ · quality 73/100 · security: safe)
• team-tasks — Multi-agent pipeline coordination: Linear, DAG, and Debate modes for AI agent orchestration (447★ · quality 73/100 · security: safe)
• MuseAI-Skills — muse.ai (Muse AI) skills and runtime snapshot: 68 skills, workflow guides, connector manifests. muse.ai 技能与运行环境文件；非官方存档 / Unofficial archive (295★ · quality 58/100 · security: safe)
• agent-skills-code-review-router — (125★ · quality 61/100 · security: safe)

View win4r on GitHub · Explore audited agent skills