30 分钟从零建出你的第二大脑——WorkBuddy + Obsidian 双工具 × 提示词七件套 × 6 大行业实战场景。
火火火
重庆交通大学人工智能专业硕士 x 万象AI实验室AI知识库共创者 百度文库 AI 漫剧短剧库专家团成员
One goal: use WorkBuddy + Obsidian and a 7-prompt toolkit to run the minimal loop of "build → ingest → query" in 30 minutes. After that, 10 minutes a day keeps the library growing. No coding — everything is "chat + prompts."
What is a second brain / AI knowledge base? It's not a cloud drive or a chatbot — the core logic is Karpathy's LLM Wiki 'compiler' paradigm. Meet WorkBuddy (does the work) and Obsidian (shows the structure).
Build, ingest, query, retrieve, restock, write, maintain — 7 prompts, each with 'when to use → prompt → how to adapt → how to verify.' Copy, paste, run.
Steps 0–5: create folder → send first prompt → drop in materials → query with sources → view structure in Obsidian. Each step has acceptance criteria.
5 daily actions + 2 maintenance actions + 6 industry scenarios (knowledge worker / sales / HR / teacher / finance / content creator) + methodology sources + FAQ + glossary.
4 lessons covering the full path from theory to practice to daily maintenance.
Answer three questions: What is an AI knowledge base? What is it NOT? Why is it worth it? Then meet WorkBuddy and Obsidian — one does the work, one shows the results, both open the same folder.
The arsenal: build, ingest, query, retrieve, restock, write, maintain — 7 prompts, each with "when → prompt → how to adapt → how to verify."
Step 0 prep → Step 1 create folder → Step 2 send first prompt → Step 3 drop in materials + ingest → Step 4 query with sources → Step 5 view in Obsidian. Each step has acceptance criteria.
5 daily actions + 2 maintenance actions + 6 industry scenarios + methodology sources + FAQ + glossary + 3 golden sentences.
Two companion materials are included for hands-on practice:
One sentence: AI does the first 4 steps, you do the last 1 — you state the goal and make judgments; AI does the heavy lifting.
Tools will change; the "materials → ingest → reflow" loop always holds.
