This generates Chinese and English abstracts for NSFC grant proposals with strict formatting rules. It follows a five-sentence structure covering background, scientific question, preliminary evidence, research content, and significance. The Chinese version caps at 400 characters, English at 4000. It enforces specific punctuation rules (curved Chinese quotes only, no markdown in plain text) and includes a validation script that checks character counts and runs compression loops if you exceed limits. You also get six title suggestions with rationale. It's built for the青年基金 application workflow where reviewers want to see your actual research plan quickly, not a literature review. The skill will ask you six targeted questions if you don't provide the structured input form upfront.

skills.sh installs
209
GitHub stars
3K
last updated
Aug 21, 2026

Install

$ npx -y skills add huangwb8/chineseresearchlatex --skill nsfc-abstract --agent claude-code

Installs into .claude/skills of the current project.

Files

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%

Sponsors

Details

Repository
github.com/huangwb8/chineseresearchlatex
First seen
Jun 3, 2026

More from huangwb8/chineseresearchlatex

All 5

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs