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 xuedai-mayi/humanities-report-writing-suite --skill humanities-report-writergit clone --depth 1 https://github.com/xuedai-mayi/humanities-report-writing-suiteWrote 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/xuedai-mayi/humanities-report-writing-suite/humanities-report-writer)<a href="https://agentmods.dev/skills/xuedai-mayi/humanities-report-writing-suite/humanities-report-writer"><img src="https://agentmods.dev/badge/skills/xuedai-mayi/humanities-report-writing-suite/humanities-report-writer/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/xuedai-mayi/humanities-report-writing-suite/humanities-report-writer"><img src="https://agentmods.dev/badge/skills/xuedai-mayi/humanities-report-writing-suite/humanities-report-writer.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 | $0.00132 | $0.01512 |
| Opus 5 | $0.00066 | $0.00756 |
| Sonnet 5 | $0.00026 | $0.00302 |
| Haiku 4.5 | $0.00013 | $0.00151 |
Grade A, and why
humanities-report-writer 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
人文社科报告写作统筹
交付标准
把用户提供的材料写成事实可靠、研究问题明确、证据与结论对应、可以在指定场景使用的正式报告。用户提供的任务书、学校模板、篇幅、格式和公开范围始终优先。
依赖路由
这不是可选建议。满足条件时必须加载对应 Skill:
- 任何中文自然语言的生成、改写、润色或审阅,必须加载
humanizer。在较大写作任务中,把它作为终稿前的最后一步,使用 embedded mode,内部完成初稿、审查和终稿,只交付终稿。 - 用户要求上网搜索、学习优秀范例、核验时效性信息、补政策背景、查文献或给出可点击来源时,必须加载
source-grounded-research。 - 用户要求 Word、
.docx、可直接提交的排版稿,或提供 Word 模板时,必须加载word-report-delivery。
如果当前环境缺少必需依赖,不得用几条摘要规则冒充完整 Skill。明确指出缺少的名称,请用户安装本套装中的对应文件夹,再继续需要该能力的交付。
新手交互
- 用户只需给出材料和用途,不要求用户先设计目录、选择研究方法或写提示词。
- 能从材料中找到的答案由 AI 自己查找,不把整理工作退回给用户。
- 只问会实质改变成稿的问题。通常在审读材料后一次集中问完,不使用专业术语考用户。
- 用户回答“不知道”或“按默认”时,采用稳妥的通用做法继续,但不得补造姓名、数字、日期、活动、引文、文献或来源。
- 只有出现会改变核心结论的事实冲突时,才进行第二轮确认。
工作流程
1. 确定任务边界
优先从用户说明、任务书和模板中识别用途、读者、研究对象、时间范围、篇幅、截止时间、署名要求、公开范围和交付格式。信息足够时直接工作,不为凑流程提问。
2. 完整审读材料
递归查看用户授权范围内的文件,形成文件清单。识别正式稿、重复稿、临时文件、原始数据、统计结果、访谈记录、活动记录和主口径文件。无法打开或内容损坏的文件必须列明,不得假装已经阅读。
原始材料默认只读。除非用户明确要求覆盖,成品另存到清楚命名的交付目录。
3. 建立证据底表
写作前使用 assets/事实底表模板.csv,或在内部建立等价表格。每项事实至少记录来源文件、页码或位置、证据状态和允许写法。详细规则见 references/intake-and-evidence.md。
4. 选择研究结构
根据研究问题、材料类型和交付场景选择结构。不要让不熟悉研究方法的用户在一组术语中盲选。只在需要时读取 references/report-structures.md 中对应部分。
5. 完成必要检索
任务包含外部检索时,加载 source-grounded-research。范例只用于学习结构、论证节奏和版式,不复制句段。正文中的外部事实、政策和文献必须可追溯。
6. 起草正文
先写研究问题、核心判断和章节关系,再扩写正文。分析段落通常包含主张、证据和解释:本段判断是什么,材料如何支持,证据能够说明到什么范围。
结果部分回答材料显示了什么,讨论部分解释可能原因、与已有认识的关系及结论边界。社会实践报告还要说明调研发现如何影响行动设计,以及实际反馈能支持什么结论,不能写成活动日记或宣传稿合集。
7. 事实与论证核查
逐项回查姓名、机构、时间、地点、样本量、比例、统计结果、成果数量、引语、图片和参考文献。检查是否把相关写成因果、把少数案例写成普遍规律、把计划或分工写成已经完成的成果。
详细终检使用 references/final-audit.md。
8. 中文自然化
加载完整 humanizer,使用 embedded mode 处理整篇中文文本。保留事实、数字、日期、姓名、引语、引用、专业术语和结论边界。不得为了显得自然而加入原材料没有的细节或观点。
9. 生成成品
用户要求 Word 时,加载 word-report-delivery,应用用户模板或随包模板并完成视觉核验。只有实际生成、验证并检查文件后,才能声称 Word 已完成。
不可违反的事实边界
- 不虚构姓名、单位、人数、比例、均值、检验结果、日期、地点、活动、访谈原话、文献和链接。
- 计划、分工和活动成果必须分开。方案文件不能单独证明活动已经发生。
- 非概率样本只描述本次样本或受访者,不外推为全部公众。
- 相关关系不写成因果关系。横断面调查不能证明某因素导致某结果。
- 图表必须来自可核验数据。只有统计结论而没有原始数据时,不反推精确数据或生成伪造图表。
- 引语必须来自原始记录并保留语境。公开材料应处理姓名、联系方式、学号、未成年人和其他可识别信息。
- 正式报告不出现聊天话语、提示词、模型说明、过程自夸、获奖承诺或针对评委的迎合表达。
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 87 lines · 132 tokens per session scan A 21a2f153d987
humanities-report-writer is a skill published in the GitHub repository xuedai-mayi/humanities-report-writing-suite (6 stars, last pushed 20d ago), licensed MIT. It adds 132 tokens to every session and 1,512 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
writing-anti-ai
This skill should be used when the user asks to "remove AI writing patterns", "humanize this text", "make this sound more natural", "remove AI-generated traces", "fix robotic writing", or needs to eliminate AI writing patterns from prose. Supports both English and Chinese text. Based on Wikipedia's "Signs of AI…
patina-aside
Use Patina's local options page and verified CLI rewrite when drafting or revising blog posts in Aside, including automatic blog workflows.
humanizer-ru
A Russian-language editing guide that makes text sound more natural and less like it was produced by an AI system.
humanizer-ru
A Russian-language editing tool that checks text for signs it was generated by a machine and can rewrite it in a more natural style when asked.
hermesoffice-decks
Produce presentations in HermesOffice Slides — the plandeck/generatedeck pipeline, native element editing, and the templates/decks style specs (modern, elegant, professional, keynote-speaker, minimal, tech-dark, investor-pitch, workshop). Load for any request that creates or restyles a deck.
humanizer-zh-next
A Chinese-language editing skill that rewrites text to sound more natural and less like it was generated by artificial intelligence.