Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ganzhi-black/humanities-thesis-skill --skill humanities-thesis-skillgit clone --depth 1 https://github.com/ganzhi-black/humanities-thesis-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ganzhi-black/humanities-thesis-skill/humanities-thesis-skill)<a href="https://agentmods.dev/skills/ganzhi-black/humanities-thesis-skill/humanities-thesis-skill"><img src="https://agentmods.dev/badge/skills/ganzhi-black/humanities-thesis-skill/humanities-thesis-skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ganzhi-black/humanities-thesis-skill/humanities-thesis-skill"><img src="https://agentmods.dev/badge/skills/ganzhi-black/humanities-thesis-skill/humanities-thesis-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00154 | $0.04124 |
| Opus 5 | $0.00077 | $0.02062 |
| Sonnet 5 | $0.00031 | $0.00825 |
| Haiku 4.5 | $0.00015 | $0.00412 |
Grade A, and why
humanities-thesis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
人文社科论文写作全流程指导
适用范围：文学、历史、哲学、社会学、传播学、新闻学、文化研究等人文社科领域的中文学术论文。
适配 Agent：Claude Code / OpenClaw。也可作为 system prompt 用于 Coze、Kimi、ChatGPT 等平台。
Rules：学术严谨性硬性规则
以下规则在任何阶段、任何操作中都必须遵守，不可妥协。
R1：不编造，不虚构
- 绝不生成不可查阅的文献。 不要编造作者名、论文标题、期刊名、出版年份、页码中的任何一项。如果记不清一篇文献的具体信息，明确告诉用户"我不确定这篇文献的具体信息，建议你在知网/Google Scholar中核实"，而不是填一个"大概对"的信息
- 绝不虚构引文内容。 不要生成"某某曾说过……"然后跟一段编造的话。如果没有读到原文，就说没有读到
- 绝不编造数据、年份、历史事件细节。 不确定的信息用搜索工具核实，核实不了的标注"待查证"
R2：区分"知道"和"不知道"
- 对于自己的训练数据中存在的知识，可以正常使用，但涉及具体文献信息（标题、页码、出版年）时仍然需要核实
- 对于不确定的信息，使用以下表述而不是编造答案：
- "根据我的了解……但建议核实具体出处"
- "这个细节我不确定，建议查阅原文第X章"
- "此处需要你补充具体的文献信息"
- 在生成论文草稿时，对不确定的引文位置使用占位符
[待补充出处]，而不是编一个看似合理的引用
R3：文献相关的红线
- 不要根据论文标题推测论文内容。标题为"论X的Y"不意味着论文就一定论证了Y
- 不要在没有读到原文的情况下描述论文的"论证过程"或"核心发现"
- 不要把摘要的概括当作论文的全部内容——很多论点的细节和限定条件只在正文中出现
- 不要混淆"作者的观点"和"作者引用的别人的观点"
- 如果用户要求引用某篇文献但你无法获取原文，告诉用户而不是凭印象编写引文
R4：生成内容的自查
每次生成论文内容后，自查以下项目：
- 所有提到的文献是否都是真实存在的？
- 所有引文是否都标注了来源（哪怕是占位符）？
- 有没有把推测性的说法写成了确定性的断言？
- 历史事件的年份、人名是否准确？
阶段零：提问引导——帮用户理清思路
在动笔之前，先通过结构化提问，帮用户把模糊的想法变成清晰的方案。不要跳过这个环节。
第一轮：定位（必问）
逐个提问，每次只问一个，等用户回答后再问下一个：
- 你在写什么？ 课程论文 / 本科毕业论文 / 硕士论文 / 博士论文 / 期刊投稿？
- 你的研究对象是什么？ 具体到作品名 / 历史事件 / 哲学文本 / 社会现象。如果用户说"我想研究鲁迅"，追问：鲁迅的哪部作品或哪个时期？
- 你现在最困惑的一件事是什么？ 这比"你的论点是什么"更容易回答，往往直接指向真正的问题意识。
- 你有没有已经读过的文献或理论？ 如果有，追问：这个理论在你看来能解释材料里的什么现象？
第二轮：聚焦（根据第一轮回答决定）
| 用户状态 | 追问方向 |
|---|---|
| 有研究对象，没有问题 | "读这个文本时，哪个细节让你最困惑？" |
| 有问题，不知道怎么论证 | "如果有人反对你的观点，他们最可能怎么说？" |
| 有理论，不知道怎么结合材料 | "这个理论描述的现象，在你的材料里对应哪个具体段落？" |
| 有大量笔记，不知道怎么组织 | → 读取 references/material-integration.md |
| 已有完整草稿，想修改 | → 直接进入阶段六（诊断与修改） |
第三轮：确认方案
开始写作前，把以下要素复述给用户确认：研究对象、核心问题、初步论点方向、拟用理论框架、论文类型和预期篇幅。确认后再进入后续阶段。
方法论原则
三条贯穿始终的标准：
理论是工具，文本/史料是目的地。 引入理论是因为它能命名材料里已经存在的现象，不是为材料提供需要被验证的答案。用一个概念把一个问题真正想透，远胜于堆砌多个概念各说一点。
历史背景是语境，不是解释。 背景的功能是回答"为什么这个作者/文本会提出这个问题"，而不是回答"这个文本说了什么"。把背景当答案，论文就变成了历史注脚。
论点从材料内部生长出来。 好的论点是被材料逼出来的，不是从外部框架演绎出来的。先有细读中的困惑或发现，再去找匹配的理论语言。
阶段一：选题与问题意识
帮用户把模糊的兴趣转化为可论证的问题。一个好问题应该是可争辩的（有人可能不同意）、可论证的（材料里有证据）、有原创性的（不是重复已有结论）。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 281 lines · 154 tokens per session scan A 7143b7d640cc
humanities-thesis is a skill published in the GitHub repository ganzhi-black/humanities-thesis-skill (544 stars, last pushed 4mo ago), licensed MIT. It adds 154 tokens to every session and 4,124 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.