nsfc-code

nsfc-code is a skill for Claude Code, Codex from huangwb8/ChineseResearchLaTeX. It costs 60 tokens per session (2,333 once invoked), scanned A, original, MIT.

A read-only tool that recommends five pairs of NSFC research application codes from the content of a grant proposal. NSFC is China's National Natural Science Foundation.

In plain words
What is it for?
Reading a proposal, matching its topics and methods to available codes, and writing recommendations with traceable reasons to a Markdown file.
Why use it?
It helps researchers choose codes that match their proposal while requiring each recommendation to come from the provided reference library.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; mentions Codex.

Good fit Reading a proposal, matching its topics and methods to available codes, and writing recommendations with traceable reasons to a Markdown file.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/huangwb8/chineseresearchlatex/nsfc-code
About the project

ChineseResearchLaTeX is a collection of LaTeX templates and an AI-assisted workflow for preparing Chinese research documents such as grant proposals, papers, theses, and academic CVs. Researchers use it to plan, format, review, compile, and revise these documents with human oversight. The catalogue skills and instructions support its agent-based research-writing workflow.

huangwb8/ChineseResearchLaTeX · 2,980 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add huangwb8/ChineseResearchLaTeX --skill nsfc-code
Clone the repo
git clone --depth 1 https://github.com/huangwb8/ChineseResearchLaTeX

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for nsfc-code

README.md
[![agentmods](https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/nsfc-code/github.svg)](https://agentmods.dev/skills/huangwb8/chineseresearchlatex/nsfc-code)
Your own site
<a href="https://agentmods.dev/skills/huangwb8/chineseresearchlatex/nsfc-code"><img src="https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/nsfc-code/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for nsfc-code

Your own site · 80×15
<a href="https://agentmods.dev/skills/huangwb8/chineseresearchlatex/nsfc-code"><img src="https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/nsfc-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,333 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00060 $0.02333
Opus 5.5 $0.00024 $0.00933
Sonnet 5.5 $0.00012 $0.00467
Haiku 4.5 $0.00006 $0.00233

Measured 1mo ago against content hash dfc2d073180f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

nsfc-code scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/nsfc_code_new_report.py, scripts/nsfc_code_rank.py, scripts/validate_skill.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/nsfc-code/SKILL.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

nsfc-code

技能定位

  • 你已经有一份 NSFC 标书正文(常见为 LaTeX 项目),但不确定应选择哪个申请代码。
  • 本技能读取你的正文内容,并结合 skills/nsfc-code/references/nsfc_code_recommend.toml 的“推荐描述”,输出 5 组代码推荐与理由。

输入(缺啥就问啥)

优先获取以下信息:

  • 标书正文路径:一个目录(如 projects/NSFC_Young/)或主 .tex 文件路径
  • (可选)用户偏好:希望主代码更偏“理论/方法/工程/交叉/转化”哪一侧
  • (可选)输出位置/文件名约定(如需写到指定目录)

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。

基于标书正文内容,推荐最贴切的 NSFC 申请代码(每条推荐包含:申请代码1=主代码、申请代码2=次代码),并把结果写入 Markdown 文件(全程只读,不修改标书)。

确定时间戳与工作区

每次运行开始时,确定分钟级时间戳 {ts}(格式 YYYYMMDDHHmm),并创建本次专属工作区:

TS=$(date +%Y%m%d%H%M)
TASK_DIR=".bensz-api/task-${TS:0:8}-${TS:8:4}-nsfc-code/nsfc-code"
mkdir -p "${TASK_DIR}/input" "${TASK_DIR}/output" "${TASK_DIR}/log"

后续所有中间文件均写入 ${TASK_DIR}/input|output|log/,最终交付文件写入工作目录根层。

读取正文(只读)

  • 递归读取输入路径下的正文文件(常见:.tex/.md/.txt;必要时包含 extraTex/)。
  • 忽略编译产物与缓存目录(如 .latex-cache/、build/ 等)。

候选代码粗排(确定性脚本)

运行脚本将正文内容与每个代码的 recommend 描述做启发式相似度打分,结果写入工作区:

python3 skills/nsfc-code/scripts/nsfc_code_rank.py \
  --input projects/NSFC_Young \
  --top-k 50 \
  --output-dir "${TASK_DIR}/output"

说明:

  • 该粗排只用于”缩小候选范围”,最终 5 条推荐仍由你结合全文语义判断。
  • 当使用 --output-dir 时,默认生成:
    • nsfc_code_rank.md(--format table)
    • nsfc_code_rank.json(--format json)
  • 如用户只给了一段文本/单个文件,也可把 --input 换成具体路径。
  • 如果用户明确知道学部/门类前缀(例如只可能是 A 类),建议加过滤降低噪声:
python3 skills/nsfc-code/scripts/nsfc_code_rank.py \
  --input projects/NSFC_Young \
  --top-k 50 \
  --prefix A \
  --output-dir "${TASK_DIR}/output"

生成 5 组推荐(AI 语义判断)

从候选列表中选择 5 组推荐(每组 2 个代码):

  • 申请代码1(主):最贴合核心研究问题与主要技术路线
  • 申请代码2(次):与主代码强相关的补充方向(常见策略:同一大类下相邻子方向;或同一研究对象但方法侧不同)

当存在不确定性时:

  • 不要瞎猜;在理由中明确”为何不确定”,并说明”需要用户确认的关键信息”。

Read the full file on GitHub · 169 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago Changed · +7 lines dfc2d073180f
  2. 1mo ago First seen · 162 lines · 60 tokens per session scan A 81c381739ef7

Subscribe to this mod's changes

nsfc-code is a skill published in the GitHub repository huangwb8/ChineseResearchLaTeX (2,980 stars, last pushed 10d ago), licensed MIT. It adds 60 tokens to every session and 2,333 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

codex-autoresearch

Run repeated, measured Git experiments toward a numeric target; keep improvements and revert failures. Use for autonomous optimization or managing an autoresearch run, not one-shot edits.

leo-lilinxiao/codex-autoresearch · 39 tokens

clipboard

Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".

CodeAlive-AI/ai-driven-development · 36 tokens

neo4j-modeling-skill

Design, review, and refactor Neo4j graph data models. Use when choosing node labels vs relationship types vs properties, migrating relational/document schemas to graph, detecting anti-patterns (generic labels, supernodes, missing constraints), designing intermediate nodes for n-ary relationships, enforcing schema with…

neo4j-contrib/neo4j-skills · 152 tokens

flue

Let agents control software, like Adobe Photoshop, Illustrator, After Effects, Premiere, Autodesk 3DS Max, Blender, Unity, Houdini, and Microsoft Office.

SFKislev/Flue · 36 tokens

rexai-image-generation

An image-generation skill that uses RexAI to create new images from text or transform existing images from other images. It returns the result as a local file.

rexleimo/aios · 80 tokens

code-that-fits-in-your-head

Software-engineering heuristics based on Mark Seemann's Code That Fits in Your Head (2021), updated for agent-driven development. Use when writing or reviewing code, refactoring accidental complexity or a Big Ball of Mud, controlling technical or architectural debt in generated code, designing APIs and invariants…

CodeAlive-AI/ai-driven-development · 169 tokens