elara-labs/code-context-engine
Claude re-reads your code every session. Make it stop. Save 70%+ on tokens. Local MCP server with AST indexing, hybrid search, and cross-session memory.
Claude re-reads your code every session. Make it stop. Save 70%+ on tokens. Local MCP server with AST indexing, hybrid search, and cross-session memory.
npx add-skill elara-labs/code-context-engineClaude re-reads your code every session. Make it stop. Save 70%+ on tokens. Local MCP server with AST indexing, hybrid search, and cross-session memory.
奔奔王国（Benben Kingdom）游戏玩家专用攻略助手。读取本地 markdown 文件目录，构建 JSON 索引文件，基于关键词/BM25 检索回答关于奔奔王国的问题。**只要用户消息里出现"奔奔"或"奔奔王国"就必须触发本 skill**，不论是问攻略、问英雄搭配、问兑换建议、问活动玩法，还是想把一篇新的公众号文章/网页/本地 md 加入知识库。
Optimize LLM system quality by using this outer-loop meta-harness to automate the search, evaluation, and mutation of agent benchmarking code.
Karpathy-style LLM Wiki as a Claude Code skill — persistent markdown knowledge base with ingest/query/lint/compile ops
A demonstration of dynamic tool calling with AI Agent using Ollama. Showcases how LLMs can invoke external Python functions in real time to augment their reasoning with live, actionable data.
My Agent Skills Repository
Agent skill repository discovered by 10x-chat research.