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 nsfc-proposalgit 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/nsfc-proposal)<a href="https://agentmods.dev/skills/leonchaox/qinyan-academic-skills/nsfc-proposal"><img src="https://agentmods.dev/badge/skills/leonchaox/qinyan-academic-skills/nsfc-proposal/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/nsfc-proposal"><img src="https://agentmods.dev/badge/skills/leonchaox/qinyan-academic-skills/nsfc-proposal.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 | $0.00167 | $0.02783 |
| Opus 5 | $0.00084 | $0.01392 |
| Sonnet 5 | $0.00033 | $0.00557 |
| Haiku 4.5 | $0.00017 | $0.00278 |
Grade A, and why
nsfc-proposal scanned grade A with 1 finding 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 13d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/LeonChaoX/qinyan-academic-skills/main/install.sh | \ How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
国家自然科学基金（NSFC）申请书撰写
概述
本 Skill 指导 AI Agent 协助用户撰写国家自然科学基金申请书，依据2026年度官方最新版规范，覆盖青年（C类）、优青（B类）、杰青（A类）三类项目。区别于本仓库已有的 research-grants（面向 NSF/NIH/DOE 等海外基金），本 Skill 专为中国大陆 NSFC 体系设计，遵循"瘦身提质"改版后的三大正文模块结构（立项依据 / 研究内容 / 研究基础），并对2026年新评审机制（分阶段评审、前500字初筛、AI 辅助声明）做了重点提示。
学术诚信声明：禁止使用 AI 直接生成申请书内容；AI 仅可用于辅助检索文献、整理结构、润色语言。所有科学观点、研究思路、创新点必须由申请人本人提供，并由人工核实事实准确性。
何时使用本 Skill
当用户的请求涉及以下情形时应触发本 Skill：
- 撰写、修改或润色 NSFC 申请书的任一模块
- 询问青基 / 优青 / 杰青的申报规范、字数限制、申请代码、亚类说明
- 检查申请书是否符合 2026 年新版"瘦身"要求（不超过30页、无独立"研究方案"板块等）
- 评估立项依据是否在前500字内呈现创新性（应对分阶段评审）
- 整理 5 篇代表作、撰写"本人贡献声明"
- 撰写伦理审查、AI辅助声明、人类遗传资源说明等合规文档
三类项目核心差异速查
| 维度 | C类（青基） | B类（优青） | A类（杰青） |
|---|---|---|---|
| 申请人年龄 | 男≤35 / 女≤40 | 男≤35 / 女≤40 | 男≤45 / 女≤48 |
| 资助金额 | ~200万 | ~400万（延续800万） | |
| 资助期限 | 3年 | 3年 | 5年 |
| 评审焦点 | 创新潜力 | 已有较好研究成绩 | 顶尖人才已取得突出成绩 |
| 正文上限 | 不超过30页 | 不超过30页 | 不超过30页 |
| 经费 | 包干制，无需编预算 | 包干制 | 包干制 |
| 申请书结构（2026） | 立项依据+研究内容+研究基础 | 同左 | 同左 + 申请人情况 |
详细规范见
references/NSFC_WRITING_SPEC.md。
工作流程
Phase 1 · 信息收集
通过对话（或在支持的工具中使用结构化提问）收集以下要素：
【申请类型】：C类（青基）/ B类（优青）/ A类（杰青）/ A类延续
【项目名称】：20字以内名词性短语
【申请代码】：必须选至二级（4位数字），可附2~3个辅助代码
【研究期限】：C/B类3年；A类5年
【关键词】：3-5个，含研究对象、核心方法、关键科学问题
【申请人信息】：职称、单位、研究方向、年龄（核对资格）
【拟解决的核心科学问题】：1-2句话
【现有研究基础】：已发论文（按相关性排序）、初步实验数据、技术平台
【是否涉及伦理 / 人遗 / 生物安全 / 临床】：用于决定附件清单
【是否使用 AI 辅助检索】：用于撰写AI使用声明
如果用户信息不全，针对最影响 Agent 决策的字段（申请类型、核心科学问题、研究基础）追问；其余可填"请自行补充"占位。
Phase 2 · 文献检索
参照 references/LITERATURE_SEARCH.md，按学科领域选择检索策略：
- 如果已安装
qinyan-paper-searchSkill → 优先调用其统一检索接口（覆盖 Google Scholar / PubMed / ArXiv / 万方） - 如果可用
WebSearch/WebFetch→ 用关键词组合检索近5年综述与代表性论文 - 如果未配置外网工具 → 提示用户在本地准备 PDF/Markdown 文献库，Agent 据此撰写综述
学科取向建议：
| 学部方向 | 优先检索库 | 备注 |
|---|---|---|
| 生命科学 / 医学 | PubMed → Web of Science → 万方 | PubMed 仅英文 query |
| 化学 / 材料 | Web of Science → SciFinder → ArXiv | |
| 信息 / 数学 / 物理 | ArXiv → Google Scholar → DBLP | |
| 工程 / 环境 | Web of Science → Google Scholar → 万方/CNKI | |
| 交叉学科 | OpenAlex → Google Scholar | 用 OpenAlex 获取引用网络 |
What ships with it
3 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.
- 13d ago First seen · 183 lines · 167 tokens per session scan A f35bb120a300
nsfc-proposal is a skill published in the GitHub repository LeonChaoX/qinyan-academic-skills (884 stars, last pushed 1mo ago), licensed MIT. It adds 167 tokens to every session and 2,783 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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…
paper-workbench
Researcher-profile-driven paper intake and literature workbench for academic workflows. Use whenever the user wants to skim, deep-read, card, compare, synthesize, map research gaps, or build a literature review from papers, arXiv/AlphaXiv links, DOIs, PDFs, or existing workbench artifacts. Trigger even when the user…
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.
scholar-deep-research
Use when the user asks for a literature review, academic deep dive, research report, state-of-the-art survey, topic scoping, comparative analysis of methods/papers, grant background, or any request that needs multi-source scholarly evidence with citations. Also trigger proactively when a user question clearly requires…
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…
openalex
A skill for searching OpenAlex, a free catalog of research papers, authors, institutions, journals, and research topics.