nsfc-research-content-writer

huangwb8/chineseresearchlatex · updated Apr 8, 2026

MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.

$npx skills add https://github.com/huangwb8/chineseresearchlatex --skill nsfc-research-content-writer
0 commentsdiscussion
summary

两阶段工作模式:

skill.md

NSFC(二)研究内容编排写作器

与 bensz-collect-bugs 的协作约定

  • 当用户环境中出现因本 skill 设计缺陷导致的 bug 时,优先使用 bensz-collect-bugs 按规范记录到 ~/.bensz-skills/bugs/,严禁直接修改用户本地 Claude Code / Codex 中已安装的 skill 源码。
  • 若 AI 仍可通过 workaround 继续完成用户任务,应先记录 bug,再继续完成当前任务。
  • 当用户明确要求“report bensz skills bugs”等公开上报动作时,调用本地 ghbensz-collect-bugs,仅上传新增 bug 到 huangwb8/bensz-bugs;不要 pull / clone 整个 bug 仓库。

目标输出(契约)

  • 写入落点(3 个文件)
    • extraTex/2.1.研究内容.tex
    • extraTex/2.2.特色与创新.tex
    • extraTex/2.3.年度研究计划.tex
  • 禁止改动main.texextraTex/@config.tex、任何 .cls/.sty
  • 编排原则:先把 2.1 写成“可验证闭环”,再从 2.1 抽取创新点生成 2.2,最后把 2.1 的任务拆分成三年里程碑生成 2.3

参数与输出模式(建议显式提供)

  • project_root:标书项目根目录(如 projects/NSFC_Young
  • output_mode(默认 apply):
    • preview:不直接写入文件;输出三段可复制粘贴的 LaTeX 正文草稿,并标注应写入的目标文件路径
    • apply:仅写入三份目标文件(见“目标输出”),不触碰其他文件

必需输入(最小信息表)

写入安全约束(必须遵守)

  1. 仅编辑三份 extraTex/2.*.tex 文件;不得修改 main.texextraTex/@config.tex、任何 .cls/.sty
  2. 目标文件若已包含标题命令(如 \\subsection{...} / \\subsubsection{...}),只替换正文内容,不改标题与结构层级
  3. 信息不全时先提问补齐,不要用“看起来像真的”的细节硬写

工作流(按顺序执行)

  1. 定位项目与目标文件:确认 project_root,读取并仅编辑三份 extraTex/2.*.tex 文件;如目标文件不存在,提示用户先初始化/拷贝模板项目。
  2. 固定”子目标三件套”:把目标拆成 3–4 个子目标(内部规划时可用 S1–S4 编号便于自检回溯,此编号仅用于 AI 内部规划,禁止出现在最终 LaTeX 正文中),并对每个子目标强制写清:
    • 指标(可判定/可验收)
    • 对照/基线(与谁比、怎么比)
    • 数据来源/验证方案(样本/实验体系/评估方法)
  3. 生成 2.1 研究内容(以”问题→目标→内容→路线→验证”为主线):
    • 篇幅控制原则(推荐值,非强制):
      • 推荐页数:12–15 页(含图表),约占标书总页数(≤28 页)的 50%
      • 推荐字数:12000–15000 字(纯文字部分)
      • 图表策略:插入 10–20 张图通常不会显著压缩文字篇幅;图片是“提质”的重要手段
      • 核心原则:评审标准已从“字数控制”转向“页数控制”,不要以字数为导向规划篇幅
    • 组织逻辑框架(按研究类型选择):新版不再预设提纲,可按研究的内在逻辑自主组织:
      • 基础研究推荐框架:科学问题提出 → 研究假说 → 验证思路 → 预期结果
      • 应用研究推荐框架:技术瓶颈 → 解决方案 → 实验设计 → 效果验证
      • 通用主线(兜底):问题 → 目标 → 内容 → 路线 → 验证
    • 研究问题与总体目标(不超过 2 段,用连贯段落而非条目)
    • 研究内容与任务展开(以科学叙事驱动,把验证逻辑自然编织进行文,而非逐条填写三件套)
    • 技术路线与验证口径(对照/消融/外部验证/泄漏防控/统计方法,融入叙述而非单独罗列)
  4. 2.1 抽取 2.2 特色与创新
    • 1–3 条即可,少而精(调研报告强调:创新点数量不在多,在于说服力);每条从”为什么这个选择是必然的”出发,说清楚现有路线的局限、本项目的不同之处、以及这个差异预期带来什么——让评审感受到研究者真的想清楚了,而不是在填写创新点模板。
    • 避免绝对化措辞(如”首次””领先”);如确需使用,必须给出可核验证据或改写为可审稿的相对表述。
  5. 2.1 推导 2.3 年度研究计划(三年不跨年):
    • 每年:年度目标 → 关键任务 → 里程碑(可验收)→ 可交付成果(论文/数据/原型/规范/软件等)
    • 里程碑必须与子目标挂钩(否则评审会认为“计划与研究内容脱节”)
    • 推进逻辑:让评审看到研究的依赖关系和递进节奏——第一年为什么先做这个、第二年为什么能做那个(避免“第一年做基础研究;第二年做深入研究;第三年做总结”的流水账)
  6. 一致性校验
    • 检查 2.2 创新点是否能回溯到 2.1 的具体任务与验证;
    • 检查 2.3 里程碑是否覆盖全部子目标,且每年都有可交付物。
    • 术语口径对齐:研究对象/缩写/指标命名尽量与 (一)立项依据(三)研究基础 保持一致(如项目中已存在)
    • 输出净化:最终写入 .tex 文件前,确认正文中不含任何 S1/S2/Sx/Ty/Vz 等内部规划编号;如需表达对应关系,改用自然语言(如"针对第一个研究目标")
  7. 任务完成后的用户提醒
    • 技术路线图建议放在研究内容开头,可使用 nsfc-roadmap skill 生成。

验收标准(Definition of Done)

写作哲学:像人类专家一样写

两阶段工作模式

  • 规划阶段(内部,不写入正文):用三件套、S1–S4 编号、验证口径菜单把研究逻辑想清楚,确保每个目标都有指标、对照和数据来源。
  • 写作阶段(输出到 .tex):切换到叙事模式。把规划阶段的结论融化进连贯的段落里,让读者感受到研究者真的想清楚了,而不是在填表。

专家写作的核心特征

  • 有科学故事主线:读者能感受到"为什么做这个、为什么这样做、怎么证明做对了"的内在逻辑,而不是三个并列条目。
  • 验证逻辑是叙述的一部分:不是"验证方案:对照/消融/外部验证",而是在描述研究内容时自然说明"将通过……与……对比,以排除……的干扰"。
  • 创新点有说服力:不是填写"相对 A,差异在 X,预计 Y"的公式,而是从问题出发,说清楚为什么现有路线走不通、本项目的选择是必然的。
  • 年度计划体现推进逻辑:不是三年的四级结构填空,而是让评审看到研究的依赖关系和递进节奏——第一年为什么先做这个、第二年为什么能做那个。

一个判断标准:写完后,把正文给一位不了解这个项目的同行看,他能否在不看任何框架标注的情况下,自然地理解这个研究的逻辑?如果能,写作是成功的。

写作小抄(可选)

变更记录

  • 本技能不在本文档内维护变更历史;统一记录在根级 CHANGELOG.md
how to use nsfc-research-content-writer

How to use nsfc-research-content-writer on Cursor

AI-first code editor with Composer

1

Prerequisites

Before installing skills in Cursor, ensure your development environment meets these requirements:

  • Cursor installed and configured on your development machine
  • Node.js version 16.0+ with npm package manager (verify with node --version)
  • Active project directory or workspace where you want to add nsfc-research-content-writer
2

Execute installation command

Execute the skills CLI command in your project's root directory to begin installation:

$npx skills add https://github.com/huangwb8/chineseresearchlatex --skill nsfc-research-content-writer

The skills CLI fetches nsfc-research-content-writer from GitHub repository huangwb8/chineseresearchlatex and configures it for Cursor.

3

Select Cursor when prompted

The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:

◆ Which agents do you want to install to?
│ ── Universal (.agents/skills) ── always included ────
│ • Amp
│ • Antigravity
│ • Cline
│ • Codex
│ ●Cursor(selected)
│ • Cursor
│ • Windsurf
4

Verify installation

Confirm successful installation by checking the skill directory location:

.cursor/skills/nsfc-research-content-writer

Reload or restart Cursor to activate nsfc-research-content-writer. Access the skill through slash commands (e.g., /nsfc-research-content-writer) or your agent's skill management interface.

Security & Verification Notice

We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.

Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.

List & Monetize Your Skill

Submit your Claude Code skill and start earning

GET_STARTED →

Use Cases

Task Automation & Efficiency

Automate repetitive workflows and reduce manual effort

Example

Generate reports, summarize documents, draft communications

Save 3-5 hours per week on routine tasks

Knowledge Enhancement

Learn new skills, understand complex topics, get expert guidance

Example

Explain concepts, provide examples, suggest learning resources

Accelerate learning and skill development by 2x

Quality Improvement

Enhance output quality through reviews, suggestions, and refinements

Example

Review drafts, suggest improvements, catch errors

Improve work quality by 30-40% with less effort

Implementation Guide

Prerequisites

  • Claude Desktop or compatible AI client with skill support
  • Clear understanding of task or problem to solve
  • Willingness to iterate and refine outputs

Time Estimate

15-45 minutes depending on use case complexity

Installation Steps

  1. 1.Install skill using provided installation command
  2. 2.Test with simple use case relevant to your work
  3. 3.Evaluate output quality and relevance
  4. 4.Iterate on prompts to improve results
  5. 5.Integrate into regular workflow if valuable

Common Pitfalls

  • Expecting perfect results without iteration
  • Not providing enough context in prompts
  • Using skill for tasks outside its intended scope
  • Accepting outputs without review and validation

Best Practices

✓ Do

  • +Start with clear, specific prompts
  • +Provide relevant context and constraints
  • +Review and refine all outputs before using
  • +Iterate to improve output quality
  • +Document successful prompt patterns

✗ Don't

  • Don't use without understanding skill limitations
  • Don't skip validation of outputs
  • Don't share sensitive information in prompts
  • Don't expect skill to replace human judgment

💡 Pro Tips

  • Be specific about desired format and style
  • Ask for multiple options to choose from
  • Request explanations to understand reasoning
  • Combine AI efficiency with human expertise

When to Use This

✓ Use When

Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.

✗ Avoid When

Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.

Learning Path

  1. 1Familiarize yourself with skill capabilities and limitations
  2. 2Start with low-risk, non-critical tasks
  3. 3Progress to more complex and valuable use cases
  4. 4Build expertise through regular use and experimentation

Discussion

Product Hunt–style comments (not star reviews)
  • No comments yet — start the thread.
general reviews

Ratings

4.562 reviews
  • Ama Khanna· Dec 20, 2024

    nsfc-research-content-writer has been reliable in day-to-day use. Documentation quality is above average for community skills.

  • Yusuf Anderson· Dec 12, 2024

    Keeps context tight: nsfc-research-content-writer is the kind of skill you can hand to a new teammate without a long onboarding doc.

  • Dhruvi Jain· Dec 8, 2024

    Useful defaults in nsfc-research-content-writer — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

  • Noor Diallo· Dec 8, 2024

    We added nsfc-research-content-writer from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.

  • Fatima Martin· Dec 8, 2024

    nsfc-research-content-writer reduced setup friction for our internal harness; good balance of opinion and flexibility.

  • Oshnikdeep· Nov 27, 2024

    nsfc-research-content-writer has been reliable in day-to-day use. Documentation quality is above average for community skills.

  • Ama Haddad· Nov 27, 2024

    nsfc-research-content-writer is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.

  • Chen Huang· Nov 19, 2024

    nsfc-research-content-writer fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.

  • Arya Ramirez· Nov 11, 2024

    Useful defaults in nsfc-research-content-writer — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

  • Yusuf Huang· Nov 3, 2024

    Registry listing for nsfc-research-content-writer matched our evaluation — installs cleanly and behaves as described in the markdown.

showing 1-10 of 62

1 / 7