LLM Wiki Chinese Edition
Paste the following prompt into your AI chat to install this skill:
Follow https://skillhub.cn/install/skillhub.md to install @user_dc3a9e2d/llm-obsidian-skill-cn.
About this skill
The problem it solves
Many personal knowledge bases fail not because notes are missing, but because new sources are summarized once and never compiled into durable structure: entities, concepts, and cross-source judgments remain scattered, hard to reuse, compare, or trace back to evidence.
How it works
This skill treats imports and questions as knowledge compilation:
- Source pages: extract provenance, one-sentence summaries, the specific problem the source solves, and reusable points, instead of generic overviews.
- Entity, concept, synthesis, and comparison pages: separate people, products, methods, cross-source claims, and easily confused objects into reusable pages with bidirectional links.
- Query pages and topic maps: archive long-lived Q&A and organize multi-topic reading paths.
- Index and log: use wiki/index.md and wiki/log.md for navigation, staged outcomes, and follow-up directions.
- Quality checks: after imports, refactors, or renames, verify broken links, UTF-8 issues, index coverage, and thin or template-heavy pages.
Boundaries
It fits engineers who want Obsidian or Markdown notes to become a maintained knowledge base. It assumes source material is read-only by default, prefers updating existing pages, and avoids generic templates. For time-sensitive claims, it should cite official sources and distinguish source opinions from externally verified facts.
Use Cases
- When curating a topic folder, compile multiple PDF or article summaries into existing wiki pages.
- When answering project questions, start from the index, cite related wiki pages, and archive a durable query page.
- Before publishing or refactoring a vault, run checks for broken links, UTF-8 issues, index coverage, and thin template pages.
- When concept pages feel vague, rewrite them with definitions, core judgments, and specific relationships to adjacent concepts.
Best For
- Engineers maintaining an Obsidian vault who want scattered notes compiled into linked, durable pages.
- Technical researchers who need product and concept comparisons distilled from multiple sources into reusable judgments.
- Markdown documentation writers who want to avoid duplicate concept pages, generic summaries, and broken bidirectional links.
- Tech leads auditing note quality who need checks for broken links, mojibake, index coverage, and thin pages.
Related Skills
Provides Bazi, Liu Yao, Qimen, Meihua, and date-selection guidance from classical references, with plain-language explanations and actionable suggestions.
Extracts core themes and hierarchical relationships from documents, reports, web pages, and images into editable mind maps.
Parse WeChat favorites exports, classify them with keywords or LLM discovery, and export to Obsidian, Notion, or IMA.
Enter a video URL or local file and automatically download, transcribe, and analyze it into structured outputs such as summaries, quotes, chapters, subtitles, mind maps, and share cards.