Agent skill

NSFC Abstract Writer

by huangwb8 in huangwb8/ChineseResearchLaTeX

Writes Chinese and English abstracts for NSFC grant applications, with a recommended title and five alternatives, within set character limits.

MITAuto-check passedResearch & Science

SKILL.md written in Chinese; this summary is our English description.

Install NSFC Abstract Writer

skills CLI
$ npx skills add huangwb8/ChineseResearchLaTeX --skill nsfc-abstract -a claude-code

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

GitHub CLI
$ gh skill install huangwb8/ChineseResearchLaTeX nsfc-abstract --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/huangwb8/ChineseResearchLaTeX.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/nsfc-abstract .claude/skills/nsfc-abstract && 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-abstract
GitHub stars
2.9k
Used in
1 other repo
Token cost
~1.3k tokens
SKILL.md length
268 words
Files
10 (incl. scripts, references)
Skills in repo
27
Repo updated
First seen
Licence
MIT

At a glance

Writes Chinese and English abstracts for NSFC grant applications, with a recommended title and five alternatives, within set character limits.

  • Works in 5 steps: 重要性/背景(≤ 15%):严格 1… → 科学问题(15–20%):指出关键未知与当前不足(具体到机制/指标/因果链的缺口)。 → 可行性证据(前期研究)(20–25%):给出 1-2… → …
  • Drafting or polishing the abstract section of an NSFC grant application
  • SKILL.md covers 流程 and 约束
  • Runs Python scripts from its folder; calls python3

What it does

The skill is written in Chinese for applicants preparing NSFC proposals. It collects project details, ideally through the form in `references/info_form.md`, and asks three to six questions about the research object, the gap, early findings, the hypothesis and the research content when information is missing. It then drafts a five-part abstract: importance, the scientific question, evidence of feasibility, research content in three or four points, and significance.

Output is a Chinese abstract of at most 400 characters and an English abstract of up to 4000 characters that must be a faithful translation, plus title suggestions: one recommended and five candidates with reasons. Length is enforced by a loop of drafting, running `scripts/validate_abstract.py`, compressing and rechecking for up to three rounds before asking you how to proceed. Results go to `NSFC-ABSTRACTS.md`, and limits sit in `config.yaml`.

It is not meant for translating unrelated text or for writing other proposal sections such as the rationale, research content or research foundation, which have their own nsfc skills.

When your agent uses it

  • Drafting or polishing the abstract section of an NSFC grant application
  • Producing an English abstract that faithfully mirrors the Chinese one
  • Brainstorming a recommended title and alternatives for an NSFC proposal
  • Cutting an overlong abstract down to the character limit

Example prompts

  • “Write the Chinese and English abstracts for my NSFC proposal on perovskite solar cell stability.”
  • “Translate my Chinese NSFC abstract into English without adding anything new.”
  • “My NSFC abstract is over the 400 character limit; compress it and keep the key data.”

Requirements

  • Python 3 for the validation and writing scripts

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. 重要性/背景(≤ 15%):严格 1 句,点明研究对象的重要性与核心瓶颈,不展开背景综述。
  2. 科学问题(15–20%):指出关键未知与当前不足(具体到机制/指标/因果链的缺口)。
  3. 可行性证据(前期研究)(20–25%):给出 1-2 条前期发现/预实验(尽量可定量),并顺势提出科学假说/核心判断。
  4. 研究内容(3-4 点)(35–40%):用动词开头,写清”做什么→怎么做→要验证什么/得到什么判据”(点数默认以 config.yaml:limits.content_points_min/max 为准);此句是摘要主体,应获得最多篇幅。
  5. 意义/价值(10–15%):总结预期贡献(科学机制 + 方法/策略/应用潜力),与第 2 句的问题形成闭环。

What it can do on your machine

Read from SKILL.md and the folder at commit b8b4142. 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

    Ships 3 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

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

  • Network

    No URLs in SKILL.md.

    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 Abstract Writer loads about 1.3k tokens when it runs, and up to ~3k if it reads all its reference files. Until then it costs about 66 tokens; SKILL.md has 268 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~66
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
~3k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from huangwb8/ChineseResearchLaTeX at commit b8b4142, republished under its MIT licence (© huangwb8). 268 words, ~1,285 tokens.

Download SKILL.mdSave it as .claude/skills/nsfc-abstract/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.
name
nsfc-abstract
description
当用户明确要求"写/润色 NSFC 标书摘要""生成中文摘要和英文摘要""把中文摘要翻译成英文摘要"时使用。输出中文、英文两个版本(英文必须是中文的忠实翻译版),同时输出标题建议(1个推荐标题+5个候选标题及理由)。中文摘要默认≤400字符,英文摘要默认≤4000字符。输出方式:将结果写入工作目录下的 `NSFC-ABSTRACTS.md`。⚠️ 不适用:用户只想翻译一段与标书无关的通用文本(应直接翻译);用户只想写立项依据/研究内容/研究基础正文(应使用对应 nsfc 系列 skill)。
metadata.author
Bensz Conan

NSFC 中英文摘要生成器

输入(先要信息,缺啥就问啥)

优先让用户按信息表提供(见 skills/nsfc-abstract/references/info_form.md)。若用户只给了零散信息,先用 3-6 个问题补齐最关键缺口:

  • 你希望题目更偏“机制向 / 方法向 / 转化向 / 场景向”哪一类?(不确定可不选,默认给混合候选)
  • 研究对象/场景是什么?(疾病/材料/系统/任务)
  • 领域痛点与未解决的科学问题是什么?(一句话)
  • 你们的关键前期发现/预实验/数据点是什么?(1-2 条,可定量)
  • 拟验证的科学假说/核心判断是什么?(一句话)
  • 研究内容 3-4 点分别要做什么、用什么方法、得到什么可验证结果?
  • 预期科学意义/应用价值是什么?(避免空话)

流程

输入

按用户请求和配置文件提供必要输入;缺失信息应明确列出并停止依赖该输入的步骤。

执行步骤
  • 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 gh 与 bensz-collect-bugs,仅上传新增 bug 到 huangwb8/bensz-bugs;不要 pull / clone 整个 bug 仓库。

目标:写出“评审一眼读懂”的五句式摘要,做到重要性、科学问题、可行性证据、研究内容、科学意义五个要素齐全;并输出与之一致的英文翻译。

篇幅比例原则:资深评审希望尽快看到申请人”进入正题”,背景铺垫过多是专业度不足的信号。各句目标占比如下(超出即压缩):

句子功能目标占比
① 背景入场券≤ 15%
② 科学问题定位缺口15–20%
③ 前期研究建立可信度20–25%
④ 研究内容主体35–40%
⑤ 意义闭环10–15%
  1. 重要性/背景(≤ 15%):严格 1 句,点明研究对象的重要性与核心瓶颈,不展开背景综述。
  2. 科学问题(15–20%):指出关键未知与当前不足(具体到机制/指标/因果链的缺口)。
  3. 可行性证据(前期研究)(20–25%):给出 1-2 条前期发现/预实验(尽量可定量),并顺势提出科学假说/核心判断。
  4. 研究内容(3-4 点)(35–40%):用动词开头,写清”做什么→怎么做→要验证什么/得到什么判据”(点数默认以 config.yaml:limits.content_points_min/max 为准);此句是摘要主体,应获得最多篇幅。
  5. 意义/价值(10–15%):总结预期贡献(科学机制 + 方法/策略/应用潜力),与第 2 句的问题形成闭环。

当用户明确要求“中文≤400字符/英文≤4000字符”等硬约束时,必须走闭环:先检测,再压缩,再检测,合格后再写入。

  1. 先生成一个“可读但可能超限”的初稿(五句式要素齐全)。
  2. 用确定性脚本检测(必须用 --json,让硬编码负责精确计数):
    • python3 skills/nsfc-abstract/scripts/validate_abstract.py - --json --diff --strict
    • 输入可通过 stdin(无需先写文件),或在写入 NSFC-ABSTRACTS.md 后对文件校验。
  3. 若超限:按“压缩优先级”执行压缩,再回到步骤 2,最多 3 轮。
  4. 连续 3 轮仍超限:停止自动压缩,向用户说明当前超限数(ZH/EN exceeded),并请用户选择:
    • 允许删减某些信息(哪些可删)
    • 放宽字数上限(修改 config.yaml)
    • 人工给出更短的关键信息摘要(例如只保留最关键 1 条证据 + 3 点研究内容)
压缩优先级(从上到下)
  • P0(必须保留):研究对象/关键科学问题缺口/定量证据(若有)/核心方法名称/预期贡献闭环
  • P1(优先精简):程度副词、形容词修饰、”我们将/本研究”主语、过程性描述、”通过/采用”等介词短语、并列重复表达
  • P2(优先删除):背景超出 15% 的部分(首先压缩)、空洞评价(无定量支撑的”显著/重要/领先”等)、重复句、与科学问题无关的背景扩展

如需确定性写入/校验,可使用脚本:

  • 写入:python3 skills/nsfc-abstract/scripts/write_abstracts_md.py <input> --strict
  • 校验:python3 skills/nsfc-abstract/scripts/validate_abstract.py NSFC-ABSTRACTS.md --json --diff --strict
输出
  • 必须同时给出中文与英文;英文是中文的忠实翻译(不扩写、不新增假设、不引入新结果)。
  • 中文摘要使用中文标点。
  • 引号硬约束(不可绕过):中文摘要中若需引号,唯一合法形式为中文弯引号 ” (U+201C)与 ” (U+201D)。以下形式一律禁止:ASCII 双引号 ”、全角引号 "、直角引号 「」 / 『』、单引号 ' / ',以及任何其他替代形式。
  • 中文摘要正文为纯文本:不得含有 Markdown 标记(**、*、_、# 等),用户会直接将正文 copy 到只支持纯文本的系统中。
  • 中文摘要数字不使用千分位逗号:写 1000,不要写 1,000 或 1,000。
  • 必须给出”主要研究领域”:放在英文摘要之后,一句话(汉字数 ≤ 25),精简表达核心研究方向,不得写成多条或列表。
  • 写入 NSFC-ABSTRACTS.md 时,中文摘要正文末尾与英文摘要分段标题之间不留空行。
  • 必须给出标题建议:遵循 skills/nsfc-abstract/references/title-rules.md 的”中标题目”结构偏好;至少包含:
    • 推荐标题:...(中文)
    • Recommended Title: ...(英文,紧跟推荐标题下一行)
    • 1) ... —— 理由:... / EN: ...(至少 5 条;数量以 config.yaml:title.title_candidates_default 为准;每条末尾附英文翻译)
  • 中文摘要:默认 ≤ 400 字符(含标点);推荐 5 句(以 config.yaml:limits.zh_recommended_sentences 为准),每句 1 个功能。
  • 英文摘要:≤ 4000 字符(含标点);语法正确、术语一致。
  • 不使用夸大/营销式表达(如“国际领先/填补空白/首创”),除非用户提供可核验依据且明确要求保留。
  • 不堆砌背景,不罗列方法学名词;每个方法名词必须服务于“要验证什么”。

按如下格式写入 NSFC-ABSTRACTS.md(标题文本以 config.yaml:output.zh_heading/en_heading 为准)。在末尾给出长度自检(字符数计数口径:把连续空白折叠为单个空格后计数,含标点):

text
# 标题建议
推荐标题:...
Recommended Title: ...
1) ... —— 理由:... / EN: ...
2) ... —— 理由:... / EN: ...
3) ... —— 理由:... / EN: ...
4) ... —— 理由:... / EN: ...
5) ... —— 理由:... / EN: ...

# 中文摘要
(正文)
# English Abstract
(translation)
# 主要研究领域
(一句话,≤ 25 个汉字)

### 输出管理

本 Skill 的新任务中间文件统一写入 `./.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/{skill名}/input|output|log/`。同一任务复用一个任务根目录;多 Skill 协作才创建 `shared/`。正式交付物不写入该目录,历史隐藏目录只允许显式兼容读取、迁移或清理。

### 校验

- 中文摘要字符数:N/400
- 英文摘要字符数:M/4000

写入文件后,在对话中不要重复粘贴全文(除非用户明确要求),只需回报:

  • 写入的文件路径(默认 ./NSFC-ABSTRACTS.md)
  • 标题候选数量是否满足默认要求
  • 中文/英文字符数与是否超限
失败与恢复

保留错误证据和已完成产物;仅在输入、环境或外部依赖恢复后从最近的失败步骤重试。

约束

遵守以下公共约束,并执行本 Skill 的专属边界。

公共硬约束
  • 任务需要落盘时,使用唯一的 ./.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/ 根目录;共享材料放入 shared/,Skill 专属材料放入该 Skill 的 input/、output/、log/。
  • 正式交付物、源代码和正式计划按项目约定保存,不写入任务工作区;未经授权不覆盖、删除、迁移或远程写入。
  • 项目维护变更检查 BAC 可用性并记录需求、AI 产出、工具结果、文件改动和验证摘要;BAC 只做过程审计,不替代署名、责任或合规判断。
  • 不记录 API Key、访问令牌、密码、Cookie、环境/凭据文件、私有 Prompt、身份信息、本地用户名、主机名或不必要的大体积原始数据。
  • 文件路径必须规范化并限制在授权项目范围内;外部 URL、子进程和网络访问遵循最小权限,防止路径遍历、SSRF 和命令注入。
  • Skill 版本唯一记录在自身 config.yaml:skill_info.version;公开 API、协议、目录或配置变更同步文档与 CHANGELOG.md。
  • 仅将 Skill 或 Bensz 基础设施本身的设计缺陷交给 bensz-collect-bugs;先脱敏写入 ~/.bensz-skills/bugs/,当前任务不中断,只有用户明确要求才公开上报,禁止直接修改用户已安装的 Skill 源码。
<!-- End of canonical common constraints. -->
Skill 专属约束

不得超出本 Skill description 和上方流程所声明的范围;不将未验证的信息伪装成确定结论。

© huangwb8, 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 9 other files (scripts, references) in skills/nsfc-abstract of huangwb8/ChineseResearchLaTeX.

  • SKILL.md
  • CHANGELOG.md
  • README.md
  • config.yaml
  • examples/demo_output.txt
  • references/info_form.md
  • references/title-rules.md
  • scripts/README.md
  • scripts/validate_abstract.py
  • scripts/write_abstracts_md.py

Open the folder on GitHubat commit b8b4142

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in huangwb8/ChineseResearchLaTeX, which our catalogue first saw on October 7, 2026.

Compare with similar skills

NSFC Abstract Writer 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 Abstract Writer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
NSFC Abstract Writer this skillhuangwb8/ChineseResearchLaTeX2.9k1 repos~1.3kAutomated safety check: PassMIT
Academic HumanizerAIScientists-Dev/academic-humanizer1.9k1 repos~4.2kAutomated safety check: PassMIT
NSFC Literature Review WriterHuiyuLi-2000/Chinese-Grant-Writer-Skills4391 repos~1.4kAutomated safety check: NotesMIT
NSFC Research Significance WriterHuiyuLi-2000/Chinese-Grant-Writer-Skills4391 repos~790Automated safety check: PassMIT
Paper Micro-Unit Generatoryushui2022/MathModel-Skill454—~1.1kAutomated safety check: PassMIT
NSFC Technical Route WriterHuiyuLi-2000/Chinese-Grant-Writer-Skills4391 repos~701Automated safety check: PassMIT

Similar skills

  • Academic Humanizer

    AIScientists-Dev/academic-humanizer

    Improve the clarity and voice of AI-assisted academic writing (papers, theses, rebuttals) and funding proposals (NSF Project Summary/Description, NIH Specific Aims): preserve scholarly conventions…

    1.9k GitHub starsUsed in 1 repo~4.2k tokens
    Research & ScienceAuto-check passed
  • NSFC Literature Review Writer

    HuiyuLi-2000/Chinese-Grant-Writer-Skills

    Writes the research-status literature review and critique section of an NSFC grant proposal, backed by a bundled multi-source literature search.

    439 GitHub starsUsed in 1 repo~1.4k tokens
    Research & ScienceAuto-check: notes
  • NSFC Research Significance Writer

    HuiyuLi-2000/Chinese-Grant-Writer-Skills

    Drafts the research significance section of an NSFC grant application from your project inputs, backed by searched policy documents and statistics.

    439 GitHub starsUsed in 1 repo~790 tokens
    Research & ScienceAuto-check passed
  • Paper Micro-Unit Generator

    yushui2022/MathModel-Skill

    Repairs one failing section of a mathematical modeling paper from the repair queue, or builds a legacy or quickstart scaffold when you ask for one by name.

    454 GitHub stars~1.1k tokensUpdated 3 days ago
    Research & ScienceAuto-check passed
  • NSFC Technical Route Writer

    HuiyuLi-2000/Chinese-Grant-Writer-Skills

    Polishes the research methods, technical route and innovation sections of an NSFC grant proposal from an idea you already have, without inventing a new research plan.

    439 GitHub starsUsed in 1 repo~701 tokens
    Research & ScienceAuto-check passed
  • Six-phase workflow for writing, revising and adapting grant proposals for NSF, NIH, DOE, DARPA, NASA and China's NSFC, from profiling through simulated peer review.

    1.2k GitHub stars~9.2k tokensUpdated 22 days ago
    Research & ScienceAuto-check passed

More from huangwb8/ChineseResearchLaTeX

All 27 skills in this repo
  • NSFC Grant Rationale Writer

    huangwb8/ChineseResearchLaTeX

    Writes, restructures, reviews and polishes the rationale section of NSFC research grant applications in LaTeX, with backups and a diff before every write.

    2.9k GitHub stars~945 tokensUpdated 6 days ago
    Auto-check passed
  • LaTeX Example Content Generator

    huangwb8/ChineseResearchLaTeX

    Fills an existing LaTeX project with sample sections, tables and figure narratives, protecting the template structure and previewing before writing.

    2.9k GitHub starsUsed in 1 repo~744 tokens
    Auto-check passed
  • Journal Selector for Manuscripts

    huangwb8/ChineseResearchLaTeX

    Recommends journals for a manuscript by filtering a bundled impact-factor catalog, verifying scope and quality online, and writing a ranked Markdown report.

    2.9k GitHub stars~1.7k tokensUpdated 6 days ago
    Auto-check passed
  • NSFC Budget Justification Writer

    huangwb8/ChineseResearchLaTeX

    Writes a submission-ready NSFC budget justification as a LaTeX project and renders budget.pdf from your grant proposal text and supporting materials.

    2.9k GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check passed
  • NSFC Application Code Recommender

    huangwb8/ChineseResearchLaTeX

    Recommends five pairs of NSFC application codes, primary and secondary, from a grant proposal's text and writes the reasons to a Markdown report.

    2.9k GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check passed
  • NSFC Proposal Length Aligner

    huangwb8/ChineseResearchLaTeX

    Checks a Chinese NSFC grant proposal against section length budgets, reports where it runs short or long, and guides meaning-preserving expansion or trimming.

    2.9k GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed

Works with

Questions about NSFC Abstract Writer

What does NSFC Abstract Writer do?

Writes Chinese and English abstracts for NSFC grant applications, with a recommended title and five alternatives, within set character limits. The skill is written in Chinese for applicants preparing NSFC proposals.md`, and asks three to six questions about the research object, the gap, early findings, the hypothesis and the research content when information is missing.

When should I use NSFC Abstract Writer?

NSFC Abstract Writer fits situations like: drafting or polishing the abstract section of an NSFC grant application; producing an English abstract that faithfully mirrors the Chinese one; brainstorming a recommended title and alternatives for an NSFC proposal; cutting an overlong abstract down to the character limit.

How do I install NSFC Abstract Writer in Claude Code?

Run `npx skills add huangwb8/ChineseResearchLaTeX --skill nsfc-abstract -a claude-code`. Or copy the skill folder (skills/nsfc-abstract in huangwb8/ChineseResearchLaTeX) into .claude/skills/nsfc-abstract in your project. Claude Code loads it when a task matches its description.

How do I install NSFC Abstract Writer in Codex?

Run `npx skills add huangwb8/ChineseResearchLaTeX --skill nsfc-abstract -a codex`. Or copy the skill folder (skills/nsfc-abstract in huangwb8/ChineseResearchLaTeX) into .agents/skills/nsfc-abstract in your project. Codex loads it when a task matches its description.

Can I use NSFC Abstract Writer 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 huangwb8/ChineseResearchLaTeX --skill nsfc-abstract -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-abstract, .gemini/skills/nsfc-abstract, .github/skills/nsfc-abstract and .opencode/skills/nsfc-abstract in your project.

What does NSFC Abstract Writer need to run?

Going by SKILL.md and its folder, NSFC Abstract Writer needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3 for the validation and writing scripts.

Does NSFC Abstract Writer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is NSFC Abstract Writer 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does NSFC Abstract Writer use?

NSFC Abstract Writer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does NSFC Abstract Writer use?

About 1.3k tokens (SKILL.md is roughly 5.1k 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 1.7k tokens, read only when the agent opens those files.

What are the alternatives to NSFC Abstract Writer?

Skills that share tags, products or a category with NSFC Abstract Writer: Academic Humanizer (AIScientists-Dev/academic-humanizer, 1.9k stars), NSFC Literature Review Writer (HuiyuLi-2000/Chinese-Grant-Writer-Skills, 439 stars), NSFC Research Significance Writer (HuiyuLi-2000/Chinese-Grant-Writer-Skills, 439 stars) and Paper Micro-Unit Generator (yushui2022/MathModel-Skill, 454 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains NSFC Abstract Writer?

huangwb8 (a GitHub user) maintains it in huangwb8/ChineseResearchLaTeX, which has 2,880 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on October 4, 2026.

Source: huangwb8/ChineseResearchLaTeX on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.