← all publishers

hanlinlibham

@hanlinlibham source repo

Report this profile Claim this profile

• 2 skills
• 0 followers
• 13 hours ago last updated

1. ▌
   Auto Wiki 2 · hanlinlibham bundle

   Knowledge compiler: teaches the agent to incrementally compile source files into a persistent wiki, enabling cross-session knowledge accumulation. Runtime dependencies: Python 3.8+ (stdlib + pydantic). Optional enhancements: WebSearch (active search), external MCP validators (logic validation). Five modes, auto-routed by user intent: recall → User wants questions answered from accumulated knowledge. Trigger words: recall, knowledge mode, open the wiki, answer with the wiki, according to the wiki, based on what we've accumulated, check the wiki, does the wiki have, we researched this before, from our earlier notes. ingest → User provided new material to compile into the wiki. Trigger words: ingest, compile, compile this, digest this, study this, archive this, add this in, accumulate, research this, organize this for me, add to the knowledge base. query → User asked a specific question and wants an answer from the wiki (one-shot). Trigger words: query, answer from the wiki, what does the wiki say, look it up. l
   0
   installs
2. ▌
   Auto Wiki · hanlinlibham bundle

   把源材料增量编译为持久化 Markdown + SQLite wiki，实现跨会话知识积累。用于建立或使用个人/领域知识库、Obsidian wiki，以及取材、编译、查询和治理已有 wiki。八模式按意图路由： survey（我已经有笔记了、勘察存量、冷启动、看看我现有的资料）→ 只读结构扫已有目录，反推 init 提案与种子草案，不建库不写盘； init（初始化、从零建库、搭建 Obsidian）→ 访谈真实工作流并创建首个领域； source（取材、找资料、按清单搜）→ fan-out 搜集，收口 Inbox/raw，不碰正典； recall（打开 wiki、基于积累、之前研究过）→ 持续加载已有知识； ingest（整理、消化、归档、加入知识库）→ 比较新旧后编译材料； query（根据 wiki 回答、查查看）→ 单次查询； lint（检查健康、矛盾、断链、重复）→ 治理知识库； deep-dive（查漏补缺、上强度）→ lint 找缺口，经确认后搜索并 ingest。 无 wiki 且用户要建库时走 init；有新材料走 ingest；人给索引并要求找资料走 source；只提 wiki/既有领域知识走 recall。不确定则询问。
   0
   installs