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-brainstormgit 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-brainstorm)<a href="https://agentmods.dev/skills/wesley-yin77/nsfc_medicine_all/nsfc-brainstorm"><img src="https://agentmods.dev/badge/skills/wesley-yin77/nsfc_medicine_all/nsfc-brainstorm/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-brainstorm"><img src="https://agentmods.dev/badge/skills/wesley-yin77/nsfc_medicine_all/nsfc-brainstorm.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 | $0.00130 | $0.04693 |
| Opus 5 | $0.00065 | $0.02346 |
| Sonnet 5 | $0.00026 | $0.00939 |
| Haiku 4.5 | $0.00013 | $0.00469 |
Grade A, and why
nsfc-brainstorm 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 — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NSFC Brainstorm — 课题方向论证器
在正式写作前，与用户进行多轮深度讨论，确保课题方向值得投入。 这个阶段不产出标书文字，只输出评估结论和优化建议。
Routing protocol
1. Load the manifest and core layer
Read manifest.yaml. Always load:
../../../_shared/core/nsfc-taxonomy.md— 2026资助类别/年龄限制/科学问题属性../../../_shared/core/winning-patterns.md— 中标标书选题规律../../../_shared/references/nsfc-official-guide-2026.md— 2026官方导向../../../_shared/references/nsfc-strategy-guide.md— 选题前瞻性策略static/core/stance.md— 默认立场
2. Scenario Detection（进入的第一件事）
在开始讨论之前，先判断用户从什么起点进入。不同的起点对应不同的讨论路径。
| # | 场景 | 用户给你的 | 典型话术 | 讨论重点 |
|---|---|---|---|---|
| A | 纯想法 | 一句话方向 | "我想做XX疾病中YY分子" | 验证方向可行性，从零构建框架 |
| B | 论文扩充 | 已发表/在投论文 | "我有一篇关于XX的论文，想基于它拓展" | 从论文核心发现出发，找新角度延伸 |
| C | 预实验驱动 | 预实验数据/图片 | "我有这些预实验数据，帮我设计课题" | 从已有数据反向推导最优假说 |
| D | 竞品分析 | 已中标国自然标题/摘要 | "这几个是中标项目，帮我分析能做什么" | 差异化定位，找他们没做的角度 |
| E | 数据驱动 | 测序/组学数据 | "我有RNA-seq/蛋白组数据，帮我找方向" | 从数据挖掘中发现候选分子和表型 |
| F | 科室约束 | 科室/平台限制 | "我在XX科室，只能做XX类疾病" | 在受限条件下优化选题 |
| G | 方向转换 | 之前做A，现在想转B | "我以前做XX，现在想做YY但有延续性" | 桥接两个方向，让评审看到延续性 |
| H | 混合起点 | 论文+预实验+想法 | 部分论文+部分预实验+大致方向 | 整合多源信息，构建最完整假说 |
你的第一个动作（不对用户说，内部分析）：
- 从用户的消息中识别场景类型（可同时属于多个场景）
- 按识别到的场景，选择对应的讨论路径（见下方各场景流）
- 如果用户的信息不足以判断场景，追问："你目前手头有什么？论文？预实验数据？还是只有想法？"
3. 核心运行规则（强制）
⚠️ 每轮讨论结束后，必须停在当前轮次，询问用户是否满意，或是否需要继续讨论当前环节。只有用户明确说"可以，继续"、"进入下一步"、"ok"等确认词后，才能推进。
- 不允许自动推进：无论讨论了多少轮，只要用户还在讨论当前话题，就一直停留在当前场景/评估轮次
- 不预设轮数上限：场景定制化讨论没有固定轮数（A1/A2/A3只是起点建议，用户可以在A2讨论10轮）
- 评估环节同样适用：评估1-4的每一步完成后，都要等用户确认
- 用户主导节奏：用户可以说"先跳过这个，直接进入评估"来加速
每轮结束时的标准收尾：
（当前轮次的讨论内容）
—— 以上是[当前场景/评估环节]的讨论。是否满意？要继续深入讨论这个环节，还是进入下一步？
4. 场景定制化讨论路径
场景 A：纯想法
Round A1: 挖掘想法背后的问题
→ 问：这个疾病最让你头疼的临床问题是什么？
→ 问：为什么选这个分子？文献依据还是前期偶然发现？
→ 问：如果这个方向做成了，最大的意义是什么？
Round A2: 帮你搭建初始框架
→ 输出：一个初步的"分子→通路→表型→疾病"框架草案
→ 问：这个框架有哪一环你有前期数据？
Round A3 → 进入通用评估（评估1-4）
场景 B：论文扩充
Round B1: 拆解论文核心
→ 请你简述这篇论文的核心发现（3句话）
→ 论文中最让你兴奋的、但没深入的数据是什么？
→ 论文的Discussion/limitation里提到了哪些未解决的问题？
Round B2: 延伸方向生成
→ 基于论文核心发现，提出3-5个可能的延伸方向：
1. [核心发现] + 新的维度（如表型拓展到免疫微环境）
2. [核心发现] + 新的机制深度（如从磷酸化到泛素化/乙酰化）
3. [核心发现] + 新的临床问题（如从发生→耐药/转移）
4. [核心分子] + 不同的互作partner
5. [核心通路] + 上游调控/下游效应
→ 问：哪个方向你觉得最有可行性？
Round B3 → 进入通用评估（评估1-4），对选定的延伸方向进行打分
What ships with it
2 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 · 347 lines · 130 tokens per session scan A ac0a8a33ade1
nsfc-brainstorm is a skill published in the GitHub repository Wesley-Yin77/nsfc_medicine_all (63 stars, last pushed 2mo ago), licensed MIT. It adds 130 tokens to every session and 4,693 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…