
Nsfc Research Foundation Writer
This is a specialized writing assistant for Chinese NSFC grant applications, specifically for section 3: research foundation, working conditions, and risk mitigation. It enforces a strict evidence-based approach, generating two LaTeX files that tie your prior work and available resources directly to your proposed research tasks. The skill won't let you handwave. It requires verifiable details like paper DOIs, patent numbers, and platform specs, and uses placeholders when you haven't provided them. It runs consistency checks to ensure your stated conditions actually support your research plan and that your risk mitigation strategies align with your timeline. The whole thing is built around a structured workflow that collects missing information upfront and refuses to touch your main.tex or style files. It's designed for researchers who need to systematically prove feasibility to grant reviewers.
- skills.sh installs
- 240
- GitHub stars
- 3K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add huangwb8/chineseresearchlatex --skill nsfc-research-foundation-writer --agent claude-codeInstalls into .claude/skills of the current project.
Files
NSFC(三)研究基础编排写作器
目标输出(契约)
- 写入落点(2 个文件):
extraTex/3.1.研究基础.tex(包含“研究风险的应对措施”)extraTex/3.2.工作条件.tex
- 禁止改动:
main.tex、extraTex/@config.tex、任何.cls/.sty - 核心目标:用“证据链 + 条件对位 + 风险预案”回答评审的三个问题:你做过吗?你做得成吗?出问题你怎么兜底?
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:只输出两段可复制的 LaTeX 正文草稿(并标注应写入的目标文件路径),不写入文件apply:仅写入两份目标文件(见“目标输出”),不触碰其他文件
必需输入(最小信息表)
- 若用户未提供,请先收集/补全:references/info_form.md
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。
Sponsors
Details
- Repository
- github.com/huangwb8/chineseresearchlatex
- Category
- Data Science & ML
- First seen
- Jun 3, 2026