by clayzhang-TW · Claude Skill · ★ 74
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is claude-academic-workflow-zh safe to install? View the security audit →
把機械的事情交給 AI 研究助理 教育研究者的 Claude 學術工作流 一本書，也是一門七週的研究所課程。 從你的第一份筆記，走到一篇通過自審、可以送出去的稿子。 ### 你手上有正在寫論文的學生？ 有一頁是為這個處境寫的：五個十分鐘內看得出來的徵象， 讓你判斷眼前這份稿子背後有沒有發生學習—— 而且要診斷的是「有沒有經過判斷」，不是「有沒有用 AI」。 同一頁還有：這本書不讓工具碰哪些事、鷹架與依賴怎麼分辨， 以及帶學生最常擔心的那幾件事各在哪一節被處理。 → 帶學生的時候 這本書在處理什麼 五件事，你大概都遇過： 文獻是個無底洞。 第一天搜到四十篇，第五天發現有一整條你完全沒注意到的脈絡，下面又有八十篇。最後停下來的理由不是「讀夠了」，是「沒時間了」。 寫到一半失去方向。 筆記做了三十份，每一份都很紮實。然後你打開空白文件，游標閃爍，寫不出第一句。 引用焦慮。 改到第七稿，你已經記不清第三頁那筆引用是哪來的。要查的有六十幾筆，截止日在後天。 沒有人幫你審。 你希望有人在送出去之前看一眼。但指導教授很忙，同儕在趕自己的稿，而你看這份稿子已經看到什麼都看不出來。 格式地獄。 投稿前一晚你在改參考文獻的標點。這件事跟研究品質無關，但它會花掉你三個小時，而且下一篇還要再來一次。 這五件的共同點是流程太長、太碎、太孤獨。你在第八步已經忘記第二步做過什麼決定；每一段之間都有摩擦成本，而那些成本不會出現在任何一份研究計畫的時程表裡。 它不教「AI 有哪些功能」 整本書只有一個判準：如果它做錯了，我看得出來嗎？ 七章各用一種方式回答它。所以書裡花很多篇幅在講它會在哪裡出錯、以及一份看起來完整的產出可以錯得多安靜。第 2 章有一節要求你先讓它騙你一次，親手抓到那一筆之後才准往下讀。 這本書長什麼樣 45 段。⚠️ 先讀〈[怎麼用這本書](docs/HOWTOUS
No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
| Stars | 74 |
| Forks | 8 |
| Category | Claude Skill |
| Quality Score | 50.5785836178916/100 |
| Last Updated | 2026-10-15 |
| Created | 2026-08-19 |
| Platforms | claude-code |
| Est. Tokens | ~16k |
These tools work well together with claude-academic-workflow-zh for enhanced workflows:
Looking for a claude-academic-workflow-zh alternative? If you're comparing claude-academic-workflow-zh with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Shareable Claude Code infrastructure for PhD researchers — skills, agents, hooks, and rules for academic workf
MCP implementation of Claude Code capabilities and more
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
Your own Claude Code UI, sandbox, in-browser VS Code, terminal, multi-provider support (Anthropic, OpenAI, Git
A curated list of research-oriented skills usable in OpenAI Codex, covering writing, literature review, evalua
📜 An MCP server for conversation history search and retrieval in Claude Code
Explore other popular claude skill tools:
claude-academic-workflow-zh is 教育研究者的 Claude 學術工作流. It is categorized as a Claude Skill with 74 GitHub stars.
You can find installation instructions and usage details in the claude-academic-workflow-zh GitHub repository at github.com/clayzhang-TW/claude-academic-workflow-zh. The project has 74 stars and 8 forks, indicating an active community.
The top alternatives to claude-academic-workflow-zh on Agent Skills Hub include claude-research, mcp-claude-code, deepcontext-mcp. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: