Agent skill

Nsfc Proposal

by LeonChaoX in LeonChaoX/qinyan-academic-skills

撰写国家自然科学基金(NSFC)申请书,覆盖青年科学基金(C类)、优秀青年科学基金(B类)、国家杰出青年科学基金(A类)2026年度最新规范。提供分阶段写作工作流:基本信息、摘要、立项依据、研究内容、研究基础、个人简历、伦理与AI辅助声明等模块;内置文献检索策略与质量自查清单。工具中性,适配 Claude Code / Cursor / Codex / OpenClaw / Gemini…

MITAuto-check passedResearch & Science

Install Nsfc Proposal

skills CLI
$ npx skills add LeonChaoX/qinyan-academic-skills --skill nsfc-proposal -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LeonChaoX/qinyan-academic-skills nsfc-proposal --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LeonChaoX/qinyan-academic-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/'skills/04-研究方法与科学思维/nsfc-proposal' .claude/skills/nsfc-proposal && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
nsfc-proposal
GitHub stars
938
Token cost
~1.3k tokens
SKILL.md length
320 words
Files
4 (incl. references)
Skills in repo
22
Repo updated
First seen
Licence
MIT

At a glance

撰写国家自然科学基金(NSFC)申请书,覆盖青年科学基金(C类)、优秀青年科学基金(B类)、国家杰出青年科学基金(A类)2026年度最新规范。提供分阶段写作工作流:基本信息、摘要、立项依据、研究内容、研究基础、个人简历、伦理与AI辅助声明等模块;内置文献检索策略与质量自查清单。工具中性,适配 Claude Code / Cursor / Codex / OpenClaw / Gemini…

  • Works in 5 steps: 信息收集 → 文献检索 → 立项依据写作(6~10页) → …
  • Tasks that involve Academic paper search
  • SKILL.md covers 概述, 何时使用本 Skill, 三类项目核心差异速查 and 工作流程, plus 3 more sections
  • Calls codex, curl and bash

What it does

Nsfc Proposal is an agent skill from LeonChaoX/qinyan-academic-skills. 撰写国家自然科学基金(NSFC)申请书,覆盖青年科学基金(C类)、优秀青年科学基金(B类)、国家杰出青年科学基金(A类)2026年度最新规范。提供分阶段写作工作流:基本信息、摘要、立项依据、研究内容、研究基础、个人简历、伦理与AI辅助声明等模块;内置文献检索策略与质量自查清单。工具中性,适配 Claude Code / Cursor / Codex / OpenClaw / Gemini CLI。触发词:国家自然科学基金、国自然、NSFC、青基、青年基金、优青、杰青、面上项目、natural science foundation of china、nsfc grant、青年科学基金申报

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/LITERATURE_SEARCH.md`, `references/NSFC_WRITING_SPEC.md` and `references/QUALITY_CHECKLIST.md`).

It sits in Research & Science, covering Academic paper search. It works with arXiv and PubMed. The repository describes itself as: A curated, multilingual library of 182 installable AI agent skills for end-to-end academic research—spanning literature discovery, scientific writing, grant development… The licence is MIT.

When your agent uses it

  • Tasks that involve Academic paper search

Example prompts

  • “/nsfc-proposal”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. 信息收集
  2. 文献检索
  3. 立项依据写作(6~10页)
  4. 研究内容 + 研究基础写作
  5. 合规与自检

What it can do on your machine

Read from SKILL.md and the folder at commit df5a498. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • codex
    • curl
    • bash
    • cursor
    • gemini

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Nsfc Proposal loads about 1.3k tokens when it runs, and up to ~7.7k if it reads all its reference files. Until then it costs about 78 tokens; SKILL.md has 320 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~78
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from LeonChaoX/qinyan-academic-skills at commit df5a498, republished under its MIT licence (© LeonChaoX). 320 words, ~1,252 tokens.

Download SKILL.mdSave it as .claude/skills/nsfc-proposal/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
nsfc-proposal
description
撰写国家自然科学基金(NSFC)申请书,覆盖青年科学基金(C类)、优秀青年科学基金(B类)、国家杰出青年科学基金(A类)2026年度最新规范。提供分阶段写作工作流:基本信息、摘要、立项依据、研究内容、研究基础、个人简历、伦理与AI辅助声明等模块;内置文献检索策略与质量自查清单。工具中性,适配 Claude Code / Cursor / Codex / OpenClaw / Gemini CLI。触发词:国家自然科学基金、国自然、NSFC、青基、青年基金、优青、杰青、面上项目、natural science foundation of china、nsfc grant、青年科学基金申报
metadata.author
qinyan-academic
metadata.version
1.0.0
metadata.category
04-研究方法与科学思维
metadata.applicable-tools
claude-code, cursor, codex, openclaw, gemini-cli
license
MIT

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2430万~200万~400万(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-search Skill → 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
Phase 3 · 立项依据写作(6~10页)

按 references/NSFC_WRITING_SPEC.md §3.1 的"倒金字塔"结构:

  1. 开篇 500 字(极为关键,2026年分阶段评审初筛重点):
    • 第①句:本研究的核心科学问题与原创性切入点
    • 第②段:与现有研究的本质区别
    • 第③段:潜在科学价值
    • 严禁开头大段堆砌常规综述
  2. 研究背景与国内外现状:宏观 → 中观 → 微观空白,覆盖近5年核心文献
  3. 科学问题与立项依据:明确"why/how"型基础科学问题(非工程"how to do")
  4. C类 vs B/A类区别:
    • C类侧重申请人独立提出问题的能力
    • B/A类需充分前期工作支撑
Phase 4 · 研究内容 + 研究基础写作

研究内容(10~14页)— 2026 年改革要求:

  • 取消"研究方案 / 技术路线 / 年度计划"独立板块的强制要求
  • 研究方法须自然融入研究内容叙述
  • 各子内容必须统一在核心科学问题这条轴线上,逻辑递进而非平行罗列
  • 特色与创新点建议单独成段,2~4 条,每条含 [类型]+[现状]+[突破]+[意义] 四要素

研究基础(6~10页)— 5 篇代表作选排黄金法则:

维度要求
时效性近5年优先;CNS正刊/高水平子刊可放宽
期刊水平至少3篇二区及以上;避开预警/On-hold 期刊
作者顺序C类侧重一作(≥2篇唯一一作二区以上)
相关性5篇围绕同一方向,形成"机制发现→验证→拓展"链条
理想配置3篇直接相关 + 1篇拓展 + 1篇高影响力旁证

代表作个人贡献声明格式(2026 强化要求):

"本人在该研究中负责:[具体贡献],约占工作量的 [X]%。"

Phase 5 · 合规与自检

完成草稿后,逐项核对 references/QUALITY_CHECKLIST.md 中的:

  • 形式完整性:申请代码、页数、附件(伦理/人遗/生物安全)
  • 内容质量:开篇500字、创新点是否有文献对比支撑、代表作相关性
  • 诚信合规:AI 辅助声明、超项核查、与在研项目区别

输出最终申请书草稿(Markdown 格式),并附自检结果摘要。


工具兼容性说明

本 Skill 使用纯 Markdown + YAML frontmatter,不依赖任何工具专属语法。在各 Agent 中的使用方式:

工具加载方式调用建议
Claude Code~/.claude/skills/nsfc-proposal/,自动识别 frontmatter用户说"帮我写国自然青基"即触发
Cursor.cursor/skills/nsfc-proposal/ 或 .cursorrules 中引用 SKILL.md在 chat 中 @SKILL.md
Codex CLI~/.codex/skills/nsfc-proposal/,作为 prompt 上下文用 codex --skill nsfc-proposal 或在初始提示中 include
OpenClaw~/.openclaw/skills/nsfc-proposal/同 Claude Code
Gemini CLI~/.gemini/skills/nsfc-proposal/在 system prompt 中引用 SKILL.md 路径

安装命令:

bash
curl -fsSL https://raw.githubusercontent.com/LeonChaoX/qinyan-academic-skills/main/install.sh | \
  bash -s -- -s nsfc-proposal --tool <claude|cursor|codex|gemini|openclaw>

引用文件

文件用途
references/NSFC_WRITING_SPEC.md完整撰写规范(基本信息、摘要、三大正文模块、个人简历、特殊情形)
references/LITERATURE_SEARCH.md文献检索策略与各学部数据源推荐
references/QUALITY_CHECKLIST.md提交前形式 / 内容 / 诚信三类自检清单

高频错误警示

错误改正
套话堆砌("具有重大理论意义")用具体数据、机制、对比说明意义
研究方向发散(≥5个独立子方向)聚焦 2-3 个核心问题深挖
目标虚大("建立完整理论体系")改为 3 年内可实现的具体科学目标
方法缺失在研究内容中融入关键方法说明
创新点无文献对比支撑每条配"现状+突破"对比说明
篇幅失控(超过30页)删除套话,每句话须有实质信息量
代表作与课题无关只选强相关成果,详细说明个人贡献

最终提醒:申请书须由申请人本人撰写。本 Skill 仅作为结构框架与写作指导,所有科学内容必须来自申请人本人的研究工作与学术思考。高质量的申请书体现的是申请人的学术思维与表达能力,而非对模板的套用。

© LeonChaoX, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in skills/04-研究方法与科学思维/nsfc-proposal of LeonChaoX/qinyan-academic-skills.

  • SKILL.md
  • references/LITERATURE_SEARCH.md
  • references/NSFC_WRITING_SPEC.md
  • references/QUALITY_CHECKLIST.md

Open the folder on GitHubat commit df5a498

Compare with similar skills

Nsfc Proposal next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Nsfc Proposal compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Nsfc Proposal this skillLeonChaoX/qinyan-academic-skills938—~1.3kAutomated safety check: PassMIT
Literature Reviewneflibata-feng/MyArxiv-Agent12621 repos~5.9kAutomated safety check: NotesMIT
Citation ManagementK-Dense-AI/claude-scientific-writer2.4k3 repos~3.9kAutomated safety check: NotesMIT
Citation Managementneflibata-feng/MyArxiv-Agent12620 repos~8.1kAutomated safety check: NotesMIT
Paper Searchopenags/paper-search-mcp2.8k—~1.2kAutomated safety check: NotesMIT
Rival Search MCPdamionrashford/RivalSearchMCP1321 repos~796Automated safety check: PassMIT

Similar skills

  • Literature Review

    neflibata-feng/MyArxiv-Agent

    Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.).

    126 GitHub starsUsed in 21 repos~5.9k tokens
    Research & ScienceAuto-check: notes
  • Citation Management

    K-Dense-AI/claude-scientific-writer

    Finds papers in OpenAlex, PubMed and Google Scholar, turns DOIs, PMIDs and arXiv IDs into clean BibTeX, and validates citations for a manuscript or thesis.

    2.4k GitHub starsUsed in 3 repos~3.9k tokens
    Research & ScienceAuto-check: notes
  • Citation Management

    neflibata-feng/MyArxiv-Agent

    Comprehensive citation management for academic research. An agent skill from neflibata-feng/MyArxiv-Agent.

    126 GitHub starsUsed in 20 repos~8.1k tokens
    Research & ScienceAuto-check: notes
  • Paper Search

    openags/paper-search-mcp

    Search, download, and read academic papers from 20+ sources (arXiv, PubMed, Semantic Scholar, CrossRef, etc).

    2.8k GitHub stars~1.2k tokensUpdated 6 days ago
    Research & ScienceAuto-check: notes
  • Rival Search MCP

    damionrashford/RivalSearchMCP

    Deterministic deep research via RivalSearchMCP. An agent skill from damionrashford/RivalSearchMCP.

    132 GitHub starsUsed in 1 repo~796 tokens
    Research & ScienceAuto-check passed
  • Nature Academic Search

    wp-a/nature-academic-search

    A skill your agent uses when users ask to 找文献、做文献检索、查论文、查临床试验、核验引用、去重文献、设计 PubMed/MeSH 检索式、追踪上下游引文、解析 DOI/PMID/PMCID/arXiv/OpenAlex/Semantic Scholar/NCT ID, 或导出 RIS、BibTeX、NBIB、ENW;also use for…

    299 GitHub stars~1.4k tokensUpdated 6 days ago
    Research & ScienceAuto-check passed

More from LeonChaoX/qinyan-academic-skills

All 22 skills in this repo
  • Paper Slide Deck

    LeonChaoX/qinyan-academic-skills

    Generate professional slide deck images from academic papers and content.

    938 GitHub starsUsed in 2 repos~4.6k tokens
    Auto-check passed
  • Research Proposal

    LeonChaoX/qinyan-academic-skills

    Generate academic research proposals for PhD applications. An agent skill from LeonChaoX/qinyan-academic-skills.

    938 GitHub starsUsed in 2 repos~4.8k tokens
    Auto-check passed
  • Medical Imaging Review

    LeonChaoX/qinyan-academic-skills

    Write comprehensive literature reviews for medical imaging AI research.

    938 GitHub starsUsed in 3 repos~1.1k tokens
    Auto-check: notes
  • Phylogenetics

    LeonChaoX/qinyan-academic-skills

    Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML).

    938 GitHub starsUsed in 2 repos~3.5k tokens
    Auto-check passed
  • Geomaster

    LeonChaoX/qinyan-academic-skills

    Comprehensive geospatial science skill covering remote sensing, GIS, spatial analysis, machine learning for earth observation, and 30+ scientific domains.

    938 GitHub starsUsed in 1 repo~2.9k tokens
    Auto-check passed
  • Qinyan Nature Figures

    LeonChaoX/qinyan-academic-skills

    面向 Nature Portfolio 与高影响力期刊的证据驱动科研绘图技能。用于从原始或汇总数据设计单图与多面板 figure、选择合适图形语法、编写 Python/R 绘图代码、重绘现有图件、生成机制示意图草案、撰写图注并导出可编辑 SVG/PDF 与高分辨率 TIFF/PNG;同时检查数据完整性、颜色可访问性、统计标注和最终尺寸可读性。触发场景包括 Nature…

    938 GitHub stars~600 tokensUpdated 2 mo ago
    Auto-check passed

Works with

Questions about Nsfc Proposal

What does Nsfc Proposal do?

撰写国家自然科学基金(NSFC)申请书,覆盖青年科学基金(C类)、优秀青年科学基金(B类)、国家杰出青年科学基金(A类)2026年度最新规范。提供分阶段写作工作流:基本信息、摘要、立项依据、研究内容、研究基础、个人简历、伦理与AI辅助声明等模块;内置文献检索策略与质量自查清单。工具中性,适配 Claude Code / Cursor / Codex / OpenClaw / Gemini…. Nsfc Proposal is an agent skill from LeonChaoX/qinyan-academic-skills.

When should I use Nsfc Proposal?

Nsfc Proposal fits situations like: tasks that involve Academic paper search.

How do I install Nsfc Proposal in Claude Code?

Run `npx skills add LeonChaoX/qinyan-academic-skills --skill nsfc-proposal -a claude-code`. Or copy the skill folder (skills/04-研究方法与科学思维/nsfc-proposal in LeonChaoX/qinyan-academic-skills) into .claude/skills/nsfc-proposal in your project. Claude Code loads it when a task matches its description.

How do I install Nsfc Proposal in Codex?

Run `npx skills add LeonChaoX/qinyan-academic-skills --skill nsfc-proposal -a codex`. Or copy the skill folder (skills/04-研究方法与科学思维/nsfc-proposal in LeonChaoX/qinyan-academic-skills) into .agents/skills/nsfc-proposal in your project. Codex loads it when a task matches its description.

Can I use Nsfc Proposal in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeonChaoX/qinyan-academic-skills --skill nsfc-proposal -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nsfc-proposal, .gemini/skills/nsfc-proposal, .github/skills/nsfc-proposal and .opencode/skills/nsfc-proposal in your project.

What does Nsfc Proposal need to run?

Going by SKILL.md and its folder, Nsfc Proposal needs the command-line tools its instructions call (codex, curl, bash, cursor and gemini).

Does Nsfc Proposal access the network?

SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Nsfc Proposal safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Nsfc Proposal use?

Nsfc Proposal is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Nsfc Proposal use?

About 1.3k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6.5k tokens, read only when the agent opens those files.

What are the alternatives to Nsfc Proposal?

Skills that share tags, products or a category with Nsfc Proposal: Literature Review (neflibata-feng/MyArxiv-Agent, 126 stars), Citation Management (K-Dense-AI/claude-scientific-writer, 2.4k stars), Citation Management (neflibata-feng/MyArxiv-Agent, 126 stars) and Paper Search (openags/paper-search-mcp, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Nsfc Proposal?

LeonChaoX (a GitHub user) maintains it in LeonChaoX/qinyan-academic-skills, which has 938 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on July 20, 2026.

Source: LeonChaoX/qinyan-academic-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.