voidfulvoidful/academic-skills/CLAUDE.md

academic-skills

CLAUDE.md126 starsChanged 8 months agoMITView on GitHub

本倉庫提供完整的學術研究 Skill 套件，涵蓋從論文閱讀到撰寫、審稿的完整研究流程。本套件符合 Agent Skills 開放標準，同時支援 Claude Code、ChatGPT/Codex CLI、Gemini CLI。

In this repository8 other files it gives its agents.
- experiment-designSkill
- idea-generationSkill
- paper-readingSkill
- paper-reviewSkill
- paper-writingSkill
- professor-fit-analyzerSkill
- proof-writerSkill
- academic-researchSkill

The file

Create a free account to mount

Files

CLAUDE.md

Academic Research Skills — 調度器

本倉庫提供完整的學術研究 Skill 套件，涵蓋從論文閱讀到撰寫、審稿的完整研究流程。

本套件符合 Agent Skills 開放標準，同時支援 Claude Code、ChatGPT/Codex CLI、Gemini CLI。

Skill 路由

指令	Skill	說明
`/read-paper`	`paper-reading/SKILL.md`	太奶角色論文導讀（繁中）
`/brainstorm`	`idea-generation/SKILL.md`	發散→搜索→收斂三階段構思
`/experiment`	`experiment-design/SKILL.md`	實驗設計與規劃
`/prove`	`proof-writer/SKILL.md`	理論推導與數學證明
`/write-paper`	`paper-writing/SKILL.md`	論文撰寫（頂會標準）
`/review`	`paper-review/SKILL.md`	4步驟學術審稿
`/prof-fit`	`professor-fit-analyser/SKILL.md`	教授適配度分析

Skill Pipeline

professor-fit-analyser ─┐
                        ↓
paper-reading ──→ idea-generation ──→ experiment-design
      │                                       │
      ↓                                       ↓
paper-review ←── paper-writing ←──── proof-writer
      │                 ↑
      └─────────────────┘  (revision cycle)

語言慣例

預設語言: 繁體中文（分析、解釋、討論）
英文場景: LaTeX 生成、正式審稿輸出（Step 4）、數學符號與定理名稱
學術詞彙: 參考 shared/chinese-academic-glossary.md 確保一致性

品質標準

每個 SKILL.md 必須包含符合 agentskills.io 標準的 YAML frontmatter（name, description 為必填；license, compatibility, metadata 為選填）
每個 SKILL.md 建議 200–500 行
Reference 檔案提供詳細指引，SKILL.md 透過相對路徑引用
所有模板使用 Markdown 或 LaTeX 格式

Cross-Reference 規則

Skill 之間可透過相對路徑互相引用：../paper-writing/SKILL.md
共享資源放在 shared/ 目錄
每個 Skill 的 references/ 僅存放該 Skill 專屬的參考資料

使用方式

將本倉庫 clone 到工作目錄
在 Claude Code 中開啟該目錄
使用上方指令表中的 / 指令啟動對應 Skill
依照 Skill Pipeline 完成完整研究流程

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free