Mgmt Paper Nsfc

Community

HaonanAlex

mgmt-paper-nsfc

国家自然科学基金 (NSFC) 申请书写作 SOP，覆盖面上 / 青年 / 重点 / 重大 / 杰青 / 优青 / 创新群体 / 国合等 8 类项目，含立项依据、研究内容、研究方案、创新点、工作基础 5 大模块写作模板，预算编制规范，及评审专家视角的退稿信号清单。当用户撰写、修改、审阅 NSFC 申请书，或需要按 NSFC 标准组织叙事 / 编预算 / 检查退稿风险时调用本 Skill。

Overview

Publisher	HaonanAlex
Repository	`MGMT-Paper-Skills`
Skill name	`mgmt-paper-nsfc`
Stars	130
Forks	18
Bundled files	14
License	Apache-2.0
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
14 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by HaonanAlex on GitHub. Read the source before you install it.

Installation

Install the Mgmt Paper Nsfc AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/HaonanAlex/MGMT-Paper-Skills/tree/main/mgmt-paper-nsfc
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/HaonanAlex/MGMT-Paper-Skills.git /tmp/MGMT-Paper-Skills
mkdir -p .claude/skills
cp -r /tmp/MGMT-Paper-Skills/mgmt-paper-nsfc .claude/skills/mgmt-paper-nsfc

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mgmt Paper Nsfc in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Mgmt Paper Nsfc on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Mgmt Paper Nsfc is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

MGMT - Paper - NSFC — 国家自然科学基金申请书写作指引

适用场景

本 Skill 服务于撰写 国家自然科学基金委 (NSFC) 各类项目申请书的科研工作者。常见任务：

起草或重写 NSFC 申请书的"报告正文"五大模块
评估申请书是否符合不同项目类别（面上 / 青年 / 重点 / 重大 / 杰青 / 优青 / 创新群体 / 国合）的体例与定位
按 NSFC 评审视角（函评 + 会评）做自检，提前发现退稿信号
编制预算并核对直接费用 / 间接费用各科目合规性
选择并核对学部 / 申请代码（7 大学部、二级学科）

核心原则

小同行可读：函评打分由 5 位"小同行"专家完成（学科细分相同或相近），论证必须让小同行 30 分钟内看懂"做什么、有何新意、为什么你能做"。不要堆砌外行性介绍。
关键科学问题驱动：每份申请书必须凝练出 2-3 个拟解决的关键科学问题。问题要"可证伪、可检验、有价值"，避免"研究 XX 的影响因素"这种宽泛表述。
创新性 ≥ 工作量：评审打分中"创新性"与"科学价值"权重最高。一个"工作量饱满但思路平庸"的申请书远不如"工作量适中、想法新颖"。
可行性的硬证据：可行性不能靠"我们有信心"。要靠 预实验数据 / 已发表的相关论文 / 已掌握的核心技术 / 已有平台与样本 这四类硬证据支撑。
基础与项目匹配：申请人近 5 年代表作必须与申请课题在主题上有可见的延续关系。"跨界申请"是重要的退稿信号。
预算编制要"该多则多、该少则少"：故意压低预算（比如把材料费写成 1 万）反而是减分项。预算与研究内容必须互相印证。

五大模块章节模板

NSFC 申请书"报告正文"标准为 5 节，详见 references/section-template.md：

立项依据与研究内容
- 项目的立项依据（研究意义、国内外研究现状及发展动态）
- 项目的研究内容、研究目标，以及拟解决的关键科学问题
- 拟采取的研究方案及可行性分析
- 本项目的特色与创新之处
- 年度研究计划及预期研究结果
研究基础与工作条件
- 研究基础（与本项目相关的研究工作积累和已取得的研究工作成绩）
- 工作条件（实验室、仪器、协作单位等）
- 正在承担的与本项目相关的科研项目情况
- 完成国家自然科学基金项目情况（限近 5 年）
其他需要说明的问题

项目类别选择

8 类常见项目对比详见 references/project-types.md，要点：

青年科学基金：35 岁以下（女 40 岁以下），首次申请，重视潜力 > 完整性
面上项目：博士后或副高 / 副教授为主流人群，强调"自由探索"
重点项目：要求有较好积累，强调"前沿方向 + 团队"
杰青 / 优青：人才类项目，看代表作质量与原创性
重大项目 / 重大研究计划：聚焦国家战略需求，多为团队
创新群体：依托已有杰青 / 长江群体
国际合作 (NSFC-XXX)：双边或多边合作，需海外伙伴

预算编制

直接费用 + 间接费用两大类，详见 references/budget-guide.md。要点：

设备费一般不超过总预算 30%（青年项目通常压缩到 5% 以内）
劳务费可全额发放给在校生与博士后，无固定上限但需合理
间接费用按所属单位分档计提（一般 ≤ 30%，含绩效）
国际合作交流费要写清楚"派出 / 来访人次"

学部与申请代码

7 大学部（数理 / 化学 / 生命 / 地球 / 工材 / 信息 / 管理 / 医学）+ 三级代码体系，详见 references/disciplines-codes.md。写错代码 = 函评直接被退回，务必核对当年公布的最新代码表。

评审视角自检

函评（5 位小同行）+ 会评（学科组）双轮制度，详见 references/reviewer-perspective.md。常见的函评 5 维评分：

科学价值 / 学术意义
创新性
研究方案的可行性与合理性
申请人 / 团队基础
预算合理性

高频退稿原因

详见 references/common-mistakes.md。最常见的 5 类被毙：

创新点表述像"工作进度计划"而非"思想创新"
关键科学问题宽泛、不可证伪
研究方案写成文献综述，缺技术路线图
申请人代表作与课题不相关
预算与研究内容明显不匹配

提示词目录

prompts/lipoy-yiju.md — 立项依据撰写
prompts/research-content.md — 研究内容撰写
prompts/research-plan.md — 研究方案与技术路线
prompts/innovation.md — 特色与创新点
prompts/basis.md — 工作基础与条件

工作模式

drafting（起草）：从研究问题出发起草各模块
polishing（润色）：在不改变原意前提下提升论证密度
auditing（自审）：以函评专家视角逐条检查退稿风险
budgeting（预算）：根据研究内容反推合理预算

注意事项

当年《项目指南》《申请须知》《撰写提纲》是终极依据，最终请以 NSFC 官网当年公布的最新文件为准。
本 Skill 描述的是 NSFC 公开制度的稳定部分；具体字数限制、代码表、预算科目年度间会有调整。
本 Skill 不替代本单位科研处审核与小同行预审。
申请书内容必须为申请人原创，严禁抄袭或代写。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Mgmt Paper Nsfc AI skill do?

Why use Mgmt Paper Nsfc on TypingMind?

Because you install it once and use it with any model. Mgmt Paper Nsfc is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Mgmt Paper Nsfc in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/HaonanAlex/MGMT-Paper-Skills/tree/main/mgmt-paper-nsfc. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Mgmt Paper Nsfc?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Mgmt Paper Nsfc?

As many as you like. As long as a model supports skills, you can use Mgmt Paper Nsfc with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Mgmt Paper Nsfc AI skill free?

Yes. It is published on GitHub by HaonanAlex under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Creative Ideation

NousResearch

OrganizationPopular

Generate ideas via named methods from creative practice.

Inference Sh Cli

Run 150+ AI apps (image, video, LLM) via inference.sh CLI.

Firecrawl Build Search

firecrawl

OrganizationPopular

Integrate Firecrawl `/search` into product code and agent workflows. Use when an app needs discovery before extraction, when the feature starts with a query instead of a URL, or when the system should…

Firecrawl Build

Integrate Firecrawl into application code whenever a product, agent, or workflow needs web data inside the app — web search, live search results, page scraping, structured extraction, or browser…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

MGMT - Paper - NSFC — 国家自然科学基金申请书写作指引

适用场景

核心原则

五大模块章节模板

项目类别选择

预算编制

学部与申请代码

评审视角自检

高频退稿原因

提示词目录

工作模式

注意事项

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now