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.
npx skills add Wesley-Yin77/nsfc_medicine_all --skill nsfc-referencesgit clone --depth 1 https://github.com/Wesley-Yin77/nsfc_medicine_allWrote 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.
[](https://agentmods.dev/skills/wesley-yin77/nsfc_medicine_all/nsfc-references)<a href="https://agentmods.dev/skills/wesley-yin77/nsfc_medicine_all/nsfc-references"><img src="https://agentmods.dev/badge/skills/wesley-yin77/nsfc_medicine_all/nsfc-references/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.
<a href="https://agentmods.dev/skills/wesley-yin77/nsfc_medicine_all/nsfc-references"><img src="https://agentmods.dev/badge/skills/wesley-yin77/nsfc_medicine_all/nsfc-references.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00101 | $0.02345 |
| Opus 5 | $0.00051 | $0.01172 |
| Sonnet 5 | $0.00020 | $0.00469 |
| Haiku 4.5 | $0.00010 | $0.00234 |
Grade A, and why
nsfc-references 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 12d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NSFC References — 参考文献管理器
从标书假说中提取检索要素，调用学术搜索引擎查找近3年文献， 按NSFC标准格式化输出，标注建议插入位置，并诊断现有引用时效性。
Routing protocol
1. Load the manifest and core layer
Read manifest.yaml. Always load:
../../../_shared/core/winning-patterns.md— 参考文献模式（数量/时效/期刊层级）../../../_shared/references/nsfc-official-guide-2026.md— 2026查新要求static/core/stance.md— 默认立场
2. Detect axes
| Axis | Values | Method |
|---|---|---|
action |
search / audit / format | 从用户需求检测 |
grant_type |
面上 / 青年C类 / 地区 | 从标书信息检测 |
search_scope |
broad / targeted / 补漏 | 从检索范围检测 |
action 说明：
search— 从零检索新文献audit— 诊断现有文献的时效性和质量format— 将现有文献列表格式化为NSFC标准格式
3. Action: search — 检索新文献
3.1 提取检索要素
从用户的标书/假说中提取三组关键词：
| 词组 | 提取来源 | 示例 |
|---|---|---|
| 疾病/表型词 | 第1小节（疾病背景） | DLBCL, lymphoma, immune microenvironment |
| 核心分子/通路词 | 第3-4小节（核心分子） | CIP2A, MYC, lactate, histone lactylation, PP2A |
| 机制/方法词 | 假说段 | feedback loop, immune checkpoint, PD-L1, CD47, tumor microenvironment |
3.2 构建检索式
为每个小节构建针对性的PubMed检索式：
小节1（疾病背景）："(disease) AND (epidemiology OR clinical challenge)"
小节2（领域综述）："(disease) AND (pathway OR mechanism) AND review"
小节3（核心分子）："(gene/protein) AND (disease) AND (function OR mechanism)"
小节4（机制深入）："(gene) AND (pathway) AND (phenotype) AND (year:2023-2026)"
小节5（Gap+假说）: 通常引用上文已出现的文献即可
3.3 执行检索
使用 WebSearch 在以下来源检索：
- PubMed / Google Scholar — 主要来源
- Semantic Scholar — 补充高引文献
- PubMed Central — 获取全文链接
检索参数：
- 时间过滤：2023-2026
- 排序：按相关性
- 每关键词组合检索10-15条
3.4 筛选标准
按NSFC查新标准对检索结果分级：
| 等级 | 标准 | 处理 |
|---|---|---|
| Tier 1 | CNS主刊/大子刊，2024-2026，高相关 | 必纳入 |
| Tier 2 | 领域顶刊（IF>10），2023-2026，高相关 | 优先纳入 |
| Tier 3 | IF>5，2023-2026，中等相关 | 选择性纳入 |
| 排除 | 2022年之前 / 低IF期刊 / 低相关 | 不纳入 |
3.5 输出格式
对每篇入选文献输出：
[编号] Author AB, Author CD, Author EF. Full title with accurate capitalization[J].
Journal Abbreviation, Year, Volume(Issue): Pages.
- 检索来源：PubMed/Google Scholar
- 期刊IF：XX.X | 中科院分区：X区
- 发表年份：20XX
- 建议插入位置：[小节X] [具体论点]
- 引用理由：支撑[XX论点] / 提供[YY方法] / 对比[ZZ发现]
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 198 lines · 101 tokens per session scan A b7b363c82b34
nsfc-references is a skill published in the GitHub repository Wesley-Yin77/nsfc_medicine_all (63 stars, last pushed 2mo ago), licensed MIT. It adds 101 tokens to every session and 2,345 once invoked, about $0.0005 per session on Opus 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.
Other skills, from other repositories
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.