Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
AI Agent Skills for Chinese Knowledge Workers: iMandalArt, FIRE, planning, and publishing workflows for Claude Code, Codex, and LLM agents.
| Date | Stars |
|---|---|
| 2026-07-31 | 253 |
| 2026-08-11 | 256 |
| 2026-08-20 | 257 |
| 2026-08-21 | 258 |
| 2026-08-29 | 259 |
| 2026-10-12 | 258 |
| 2026-10-15 | 259 |
| 2026-10-21 | 259 |
| 2026-11-04 | 259 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# AI Agent Skills for Chinese Knowledge Workers > Three Kings 2.2: compress with iMandalArt, address with BIRD, and publish with an A4 eight-page booklet. iMandalArt, FIRE semantic analysis, planning, and publishing workflows for Claude Code, Codex, and mainstream LLM agents. [](assets/hermes-all-skills-map.png) This repository is TWHSI's public agent-skill system for Chinese knowledge workers. It turns repeatable writing, planning, note-making, and publishing workflows into skills that can be used by Claude Code, Codex, ChatGPT, Gemini, Hermes, and other LLM agents. The source of truth lives in `skills/*/SKILL.md`; [`skill-tree.json`](skill-tree.json) records the Three Kings relationship, and the website turns the skills into generated LLM manifests, a searchable index, install commands, revisions, and update timestamps. ## What This Repository Is `twhsi/skills` is an installable, shareable, LLM-readable skill registry. It turns long-running workflows for weekly review, iMandalArt, FIRE analysis, card-based notes, EPUB publishing, HyperCard returns, and desktop work into public procedures that agents can repeat and humans can inspect. The point is not to make humans behave like faster machines. The point is to let AI spend tokens on repetitive structure, while humans keep judgment, relationships, pace, and the quieter question: > Which action brings real happiness and peace? The flagship workflow is **Skills 三大天王 2.2**: [`imandalart`](skills/imandalart/) compresses a source, [`thebrain-bird-address`](skills/thebrain-bird-address/) gives every knowledge object an address and Route, and [`a4-eight-page-booklet`](skills/a4-eight-page-booklet/) returns the structure to a verified paper book. Live site: [https://www.twhsi.com/](https://www.twhsi.com/) Live Keyword Graph: [https://keyword-graph-view.twhsi.chatgpt.site/](https://keyword-graph-view.twhsi.chatgpt.site/) Agent manifest: [https://www.twhsi.com/agent.json](https://www.twhsi.com/agent.json) Skill index: [https://www.twhsi.com/skills.json](https://www.twhsi.com/skills.json) LLM context: [https://www.twhsi.com/llms.txt](https://www.twhsi.com/llms.txt) ## What It Does - Convert source material into iMandalArt 2.2 hard-line 9-grid cards. - Apply FIRE semantic analysis for card-box thinking, retrieval, and writing structure. - Turn permanent notes into BIRD 2.1 Book Addresses, structured Knowledge Indexes, Routes, verified Deep Links, Semantic Roles, and TheBrain manuscript scaffolds. - Compress answers with `concise-key-points`: reduce default length by 70% while retaining at least 95% of essential information. - Compile source material into a verified A4 one-sheet eight-page booklet, synchronized reading PDF, print imposition, and editable DOCX. - Generate agent-readable metadata through `agent.json`, `skills.json`, and `llms.txt`. - Route daily planning, weekly planning, booklet, EPUB, Markdown, and knowledge-management workflows. - Extract eight keywords and render a distributed weighted graph with definitions, evidence, and blacklist control. - Package Chinese-first workflows so LLM agents can operate on them consistently. ## Copyable Demo ```text Input: manuscript, notes, PDF, or long conversation Skills: imandalart 2.2 -> thebrain-bird-address 2.2 -> a4-eight-page-booklet 2.2 Output: eight-angle index -> BIRD addresses and Routes -> reading PDF + print sheet + DOCX ``` ## Skills 三大天王 2.2 ```text 素材 -> iMandalArt 2.2：一個中心、八個正交視角 -> BIRD 拆書分析 2.2：Book Address、W+T+K+A、Route、Deep Link -> A4 八頁小書 2.2：八頁閱讀版、折頁列印版、可編輯 DOCX、驗證報告 ``` | Skill | Responsibility | Best use | |---|---|---| | [`iMandalArt 2.2`](skills/imandalart/) | 壓縮王：把混雜素材壓成中心與八個不重複視角。 | 每日計畫、章節總覽、64＋8＋1、手機九宮卡。 | | [`BIRD 拆書分析 2.2`](skills/thebrain-bird-address/) | 地址王：把主張變成可定位、可檢索、可跨章連結的知識節點。 | 拆書、TheBrain、Excel、Roam、Obsidian、書稿 Route。 | | [`A4 八頁小書 2.2`](skills/a4-eight-page-booklet/) | 出版王：把九宮概覽與七條 Routes 變成可讀、可印、可編輯的小書。 | A
Excerpt of 15,311 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:fe39b046e9b06d91, llm:topics: agent-skills, ai-agent, claude-code, codex, knowledge-management, mandalart, prompt-engineering; description: 'AI Agent Skills for Chinese Knowledge Workers: iMandalArt, FIRE, planning, and publishing workflows for Claude Code, Codex, and LLM agents.'
matched fp:fe39b046e9b06d91, llm:topics: agent-skills, ai-agent, claude-code, codex, knowledge-management, mandalart, prompt-engineering; description: 'AI Agent Skills for Chinese Knowledge Workers: iMandalArt, FIRE, planning, and publishing workflows for Claude Code, Codex, and LLM agents.'
matched fp:fe39b046e9b06d91, llm:topics: agent-skills, ai-agent, claude-code, codex, knowledge-management, mandalart, prompt-engineering; description: 'AI Agent Skills for Chinese Knowledge Workers: iMandalArt, FIRE, planning, and publishing workflows for Claude Code, Codex, and LLM agents.'
matched fp:fe39b046e9b06d91, llm:topics: agent-skills, ai-agent, claude-code, codex, knowledge-management, mandalart, prompt-engineering; description: 'AI Agent Skills for Chinese Knowledge Workers: iMandalArt, FIRE, planning, and publishing workflows for Claude Code, Codex, and LLM agents.'