huangwb8 avatar

Nsfc Justification Writer

If you're writing NSFC grant proposals in LaTeX, this automates the justification section that explains why your research matters and what gap it fills. It takes a minimal info form, outputs four structured pieces (value, current state, scientific question, entry point), and writes directly to extraTex/1.1.立项依据.tex without touching your main files. The built-in guardrails are the real value: it won't let you claim "internationally leading" without evidence, forces citation verification, and keeps terminology consistent with your research content section. Comes with a coaching mode that figures out whether you're at skeleton, draft, or polish stage. Made for Chinese research funding applications but the structured thinking applies elsewhere.

skills.sh installs
386
GitHub stars
3K
last updated
Aug 21, 2026

Install

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

Installs into .claude/skills of the current project.

Files

科研立项依据写作器

目标

本 Skill 将 NSFC/科研基金申请书的立项依据整理为可核验、论证连贯且保留 LaTeX 结构的正文。它适用于新写、重构、审查和润色立项依据;宿主 AI 负责理解材料、安排论证和改写正文,Python 脚本负责确定性检查与安全写入。科学问题与科学假设必须从研究现状的缺口自然收束出来,正文先推进科学判断,证据等级、外推边界和待核验项另列为审查记录;只有会改变本段解释的关键限定进入正文。

立项依据的默认内容链为:研究意义 → 国内外研究现状 → 科学问题与科学假设 → 小结,表示论证功能,不要求改成固定四节。已有标题和结构能完成这些功能时予以保留。研究目标、技术路线、主验证场景、终点、阈值和风险处理属于后续章节,本 Skill 只在需要时作简短衔接,不展开这些内容。

流程

输入

  • 必需:项目根目录,以及目标立项依据正文或可定位该正文的项目材料。
  • 通常读取:目标 .tex、研究内容、研究基础和项目 .bib;只读取完成当前论证所需的内容,不归档无关原始材料。
  • 可选:CLI 的 --target-file、完整正文提案文件和 --override 配置。目标文件按“显式配置 → 文件名含立项依据或 justification 的候选 → 字典序”选择;找不到时使用配置允许的默认目标并创建文件。
  • 先按需读取 分节写法 规划论证地图和段落推进;完成正文后读取 质量控制 执行一次语义复核;需要回归对照时读取 边界表达回归样例。
  • 不把密钥、令牌、凭据、Cookie、完整私有 Prompt 或不必要的大体积原始数据写入产物、日志或报告。

执行步骤

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