stevesolun/ctx
Skill, agent, MCP, and harness recommendations for Claude Code/custom LLMs: 102,696-node LLM-wiki graph, 91,432 skills, 10,787 MCPs, 13 harnesses, and capped execution recommendations.
Skill, agent, MCP, and harness recommendations for Claude Code/custom LLMs: 102,696-node LLM-wiki graph, 91,432 skills, 10,787 MCPs, 13 harnesses, and capped execution recommendations.
npx add-skill stevesolun/ctxSkill, agent, MCP, and harness recommendations for Claude Code/custom LLMs: 102,696-node LLM-wiki graph, 91,432 skills, 10,787 MCPs, 13 harnesses, and capped execution recommendations.
A cross-platform natural language router for agent skills. Scans Claude Code, WorkBuddy, OpenCode, Gemini CLI, Codex, Cursor and more. Intent-aware routing with keyword, TF-IDF, and LLM matching.
Enable true asynchronous tool calls in agent frameworks with immediate acknowledgements and non-blocking result callbacks for continuous interaction.
`multi-paper-innovation-comparator` 是一个用于批量阅读和对比多篇论文创新点的 AI agent skill。它适合处理一个论文文件夹中的多篇 PDF、Markdown 或文本论文，逐篇读取未处理过的论文，总结每篇论文的主要工作、创新点、实验结果和工作量，并持续与已读论文进行横向对比，最终生成一个 `summ.md` 文档。
Xmem is a India's First multi-modal, multi-agentic long‑term memory layer for AI agents.
Ralph Wiggum パターン (autonomous AI task loop) の汎用スターター。Claude Code Skill + grill-me + ralph.sh の最小構成。
Codex skill and PowerShell templates for modular Windows guardian maintenance.