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 nssfc-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/nssfc-proposal)<a href="https://agentmods.dev/skills/leonchaox/qinyan-academic-skills/nssfc-proposal"><img src="https://agentmods.dev/badge/skills/leonchaox/qinyan-academic-skills/nssfc-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/nssfc-proposal"><img src="https://agentmods.dev/badge/skills/leonchaox/qinyan-academic-skills/nssfc-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 | $0.00189 | $0.03209 |
| Opus 5 | $0.00095 | $0.01605 |
| Sonnet 5 | $0.00038 | $0.00642 |
| Haiku 4.5 | $0.00019 | $0.00321 |
Grade A, and why
nssfc-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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
国家社会科学基金（NSSFC）年度项目申请书撰写
概述
本 Skill 指导 AI Agent 协助用户撰写国家社会科学基金年度项目申请书，依据 2025 年全国哲学社会科学工作办公室官方模板，覆盖重点项目（A）、一般项目（B）、青年项目（C）、西部项目（X）四类。区别于本仓库已有的 research-grants（面向 NSF/NIH 等海外自然科学基金）与 nsfc-proposal（面向国家自然科学基金），本 Skill 专为中国大陆哲学社会科学基金设计，特别关注：
- 2025 年新增"选题说明"模块（≤300字，单独成段，评审专家首读内容）
- 活页匿名化要求（不得出现作者姓名、单位、发表刊物名、合作者等可识别身份信息）
- 学科评审标准差异（25 个学科分类，各学科评审重点不同）
- "目标导向、问题意识、学科视角"三大核心评审原则
学术诚信声明：申请书的科学观点、研究思路、创新点必须由申请人本人提供；AI 仅可用于辅助检索文献、整理结构、润色语言，且须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、修改或润色国社科申请书的任一模块
- 询问重点 / 一般 / 青年 / 西部项目的申报规范、字数限制、经费额度
- 检查申请书是否符合 2025 年新版要求（选题说明 300 字、单独成段）
- 准备活页版（须严格匿名化处理）
- 整理前期成果（限报 5 项，与本课题高度相关）
- 设计经费概算（间接费用≤40%，劳务费一般≤直接费用 30%）
四类项目核心差异速查
| 维度 | A 重点项目 | B 一般项目 | C 青年项目 | X 西部项目 |
|---|---|---|---|---|
| 申请人资格 | 副高及以上，或博士学位 | 副高及以上，或博士学位 | 35 周岁以下 | 西部省区在职人员 |
| 资助经费 | 35 万元 | 20 万元 | 20 万元 | 20 万元 |
| 完成时间 | 基础研究3-5年，应用研究2-3年 | 同左 | 同左 | 同左 |
| 评审侧重 | 重大理论与现实问题 | 学科前沿与创新性 | 创新潜力与学术训练 | 西部经济社会发展 |
详细规范见
references/NSSFC_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：
【课题名称】：不超过 40 个汉字，不加副标题
【项目类别】：A 重点 / B 一般 / C 青年 / X 西部
【学科分类】：一级学科 + 二级学科（如：社会学 / 社会学理论）
【研究类型】：A 基础研究 / B 应用研究 / C 综合研究
【关键词】：≤3 个，空格分隔
【申请经费】：A=35 万；B/C/X=20 万
【计划完成时间】：基础研究 3-5 年；应用研究 2-3 年
【预期成果形式】：专著 / 论文集 / 论文 / 研究报告
【申请人背景】：职称、研究方向、代表性成果
【课题组成员】：姓名、职称、单位、研究专长
【核心研究问题】：2-3 句话描述
【前期成果】：与本课题相关的已有成果，最多 5 项
【与已有项目关系】：无 / 有（说明联系与区别）
【是否需要活页版】：是 / 否（决定匿名化处理）
如用户信息不全，针对最影响 Agent 决策的字段（项目类别、学科分类、核心研究问题）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：
- 优先：CNKI（中国知网）、万方、维普 → 中文核心 / CSSCI 来源期刊
- 国际：JSTOR、SSCI、A&HCI、SAGE、Project MUSE
- 专项数据库：
- 法学类：北大法宝、聚法案例、Westlaw、HeinOnline
- 经济学类：EconLit、NBER、CEIC
- 历史学类：中华古籍资源库、爱如生数据库、JSTOR
- 文学类：CNKI 古籍库、中华经典古籍库
- 如果已安装
qinyan-paper-searchSkill → 用wanfang（中文）与google（外文）双源
学科领域取向建议：
| 学科 | 优先检索库 | 备注 |
|---|---|---|
| 哲学 / 宗教学 / 中国文学 | CNKI → 古籍数据库 → JSTOR | 注重中外文兼顾 |
| 经济学 / 应用经济 | EconLit → CNKI → NBER | 数据来源用 CEIC/Wind |
| 法学 | 北大法宝 → CNKI → HeinOnline | 案例检索用聚法/Westlaw |
| 社会学 / 民族学 | CNKI → 万方 → SSCI | 田野资料须标注获取方式 |
| 政治学 / 国际问题 | CNKI → SSCI → 智库报告 | 用 RAND/Brookings 等智库 |
| 教育学 / 心理学 | CNKI → ERIC → APA PsycInfo | 实证研究优先 SSCI |
| 历史学 / 考古学 | 中华古籍资源库 → CNKI → JSTOR | 史料须辨章学术 |
| 新闻传播 / 图情 | CNKI → Communication Abstracts | 政策类引用《传媒》 |
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 · 210 lines · 189 tokens per session scan A 13a9c0b400ab
nssfc-proposal is a skill published in the GitHub repository LeonChaoX/qinyan-academic-skills (884 stars, last pushed 1mo ago), licensed MIT. It adds 189 tokens to every session and 3,209 once invoked, about $0.0009 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.