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 LeonChaoX/qinyan-academic-skills --skill qinyan-nature-writinggit clone --depth 1 https://github.com/LeonChaoX/qinyan-academic-skillsWrote 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/leonchaox/qinyan-academic-skills/qinyan-nature-writing)<a href="https://agentmods.dev/skills/leonchaox/qinyan-academic-skills/qinyan-nature-writing"><img src="https://agentmods.dev/badge/skills/leonchaox/qinyan-academic-skills/qinyan-nature-writing/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/leonchaox/qinyan-academic-skills/qinyan-nature-writing"><img src="https://agentmods.dev/badge/skills/leonchaox/qinyan-academic-skills/qinyan-nature-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00140 | $0.01222 |
| Opus 5 | $0.00070 | $0.00611 |
| Sonnet 5 | $0.00028 | $0.00244 |
| Haiku 4.5 | $0.00014 | $0.00122 |
Grade A, and why
qinyan-nature-writing 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 9d 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.
What it actually says
沁言 Nature 论文写作
把论文视为一条可审计的论证链，而不是一组“像顶刊”的句子。先锁定事实和证据，再安排读者路径，最后写作。
工作边界
- 处理从材料到论文章节的起草、重构与首次投稿材料。
- 将纯语言精修交给
qinyan-nature-polishing。 - 将投稿前同行评审交给
qinyan-nature-review。 - 将统计设计与报告核验交给
qinyan-nature-statistics。 - 将科研图设计和导出交给
qinyan-nature-figures。 - 不生成不存在的结果、机制、统计显著性、参考文献、实验细节或期刊政策。
必须先建立的写作底稿
从用户材料中提取并明确标注：
Central claim：论文实际证明或支持的核心命题。Evidence set：支撑命题的图、表、实验、模型、数据集和统计结果。Boundary：证据不能支持的外推范围、机制解释或因果结论。Audience：跨领域读者为何应关心，以及专业读者需要看到什么。Terminology ledger：方法、数据集、指标、缩写、符号的唯一标准写法。Unresolved facts：仍需作者确认的事实；统一写为AUTHOR_INPUT_NEEDED。
如果核心命题、关键证据或边界缺失，先给出可继续工作的框架与缺口清单，不补造正文事实。
执行流程
- 分类任务。 确定论文类型、目标章节、目标期刊、源语言、字数限制和交付格式。
- 构建论证脊柱。 用一句话表达“研究对象—关键进展—方法—证据—适用边界”。
- 建立证据矩阵。 为每个主要声称绑定至少一个证据位置；把无证据声称降级、删除或标为待补。
- 设计章节职责。 让每段只承担一个主要功能：背景、缺口、方法、发现、比较、解释、意义或局限。
- 按证据顺序起草。 先写结果与图件逻辑，再写方法和讨论，最后收束摘要与标题；用户指定其他顺序时服从用户。
- 校准表达强度。 区分观察、关联、预测、干预和机制证据；使动词强度与证据层级一致。
- 运行结构审计。 对文本文件执行
python scripts/manuscript_audit.py <file>，处理 blocker 与 warning。 - 交付并暴露缺口。 给出可粘贴正文、关键编辑说明、证据风险和作者待确认项。
需要章节级结构时读取 references/section-blueprints.md。需要完整论证与证据映射方法时读取 references/argument-workflow.md。需要首次投稿材料时读取 references/submission-package.md。
默认输出
写作设定
- 论文类型 / 章节 / 目标期刊：
- 核心命题：
- 证据边界：
论证与段落地图
- P1:
- P2:
可粘贴正文
[draft]
证据与措辞风险
- [claim] → [evidence pointer / missing]
AUTHOR_INPUT_NEEDED
- [仅列事实性问题]
用户只要求正文且材料充分时，简化输出，但仍保留必要的风险标记。
质量门槛
- 每个主要声称都能回指用户提供的证据。
- 摘要中的结果、方向和数值与正文一致。
- 引言提出的缺口由本研究真正回应。
- 结果段不把解释冒充观察，讨论段不引入未展示的新结果。
- 局限具体说明适用边界，不写成礼貌性尾句。
- 标题与摘要避免无法核验的“首次”“突破性”“普适”等表述。
- 首次投稿材料中的作者、单位、利益冲突和推荐审稿人信息均由作者确认。
资料路由
| 任务 | 读取 |
|---|---|
| 建立 claim–evidence map、论证脊柱或术语账本 | references/argument-workflow.md |
| 起草或重构具体章节 | references/section-blueprints.md |
| cover letter、title page、声明与投稿检查 | references/submission-package.md |
What ships with it
5 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.
- 9d ago First seen · 86 lines · 140 tokens per session scan A 07f1522c3e90
qinyan-nature-writing is a skill published in the GitHub repository LeonChaoX/qinyan-academic-skills (884 stars, last pushed 1mo ago), licensed MIT. It adds 140 tokens to every session and 1,222 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 2026-09-03.
Other skills, from other repositories
academic-research
Nested swiss-knife reference for academic literature work — find papers, fetch full-text PDFs, trace citations, write LaTeX manuscripts. First action for any "get me this paper" request: python3 /scripts/fetchpaper.py — walks arXiv → Unpaywall → Europe PMC → CORE → in-house publisher-page extraction…
research-agent
Project-first Research pipeline with live gates, source/PDF evidence, claim boundaries, compute and publication controls; includes an optional PubMed/arXiv standard-library helper.
openalex
Use when the user asks about academic literature, research papers, scholarly works, authors, citations, institutions, journals, or any academic metadata. Trigger when users want to search for papers, find author profiles, track citations, discover related works, or explore academic topics. Also use when users mention…
paper-comic
A visual-explanation workflow for showing what a research paper's method does and how it works. It analyzes the paper, proposes cover, overview, and mechanism diagrams, and waits for the user's choices before generating them.
scopus-researcher
Expert academic researcher using the Scopus MCP. Finds papers, retrieves full abstracts, builds author profiles, analyzes citation impact, and constructs advanced Boolean queries across the Elsevier Scopus database. Activate when asked to search for academic papers, analyze research trends, find citations, profile…
lc_arxiv
A tool for searching arXiv, a public repository of research papers, mainly in science and technology.