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-hypothesisgit 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-hypothesis)<a href="https://agentmods.dev/skills/wesley-yin77/nsfc_medicine_all/nsfc-hypothesis"><img src="https://agentmods.dev/badge/skills/wesley-yin77/nsfc_medicine_all/nsfc-hypothesis/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-hypothesis"><img src="https://agentmods.dev/badge/skills/wesley-yin77/nsfc_medicine_all/nsfc-hypothesis.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 | $0.00087 | $0.01562 |
| Opus 5 | $0.00044 | $0.00781 |
| Sonnet 5 | $0.00017 | $0.00312 |
| Haiku 4.5 | $0.00009 | $0.00156 |
Grade A, and why
nsfc-hypothesis 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NSFC Hypothesis — 科学假说构建器
从已掌握的证据链中提炼科学假说，形成NSFC标书的核心灵魂。
Routing protocol
1. Load the manifest and core layer
Read manifest.yaml. Always load:
../../../_shared/core/winning-patterns.md— 科学假说的标准写法../../../_shared/core/terminology.md— 术语一致性static/core/stance.md— 默认立场
2. Detect axes
| Axis | Values | Method |
|---|---|---|
stage |
探索（用户有散落证据）/ 凝练（已有框架需精炼）/ 挑战（对现有假说进行压力测试） | 从需求检测 |
complexity |
单通路 / 双通路 / 多层级 | 从假说内容检测 |
3. Apply hypothesis construction protocol
Step 1: 证据盘点
收集用户掌握的所有证据碎片：
- 已知的基因/蛋白表达变化
- 已证实的蛋白互作/功能关系
- 已发表的文献支撑
- 预实验结果
- 生物信息学分析结果
Step 2: 逻辑链构建
将碎片化证据连接成一条逻辑链：
[分子A] → [调控方式B] → [效应分子C] → [表型D] → [疾病E]
检查链中每个环节是否都有证据支撑（预实验/文献）， 标记薄弱环节（需要用虚线标注，作为"待验证"）。
Step 3: 假说表述
按中标标书标准格式输出：
"综上所述，[证据链回顾]。由此，我们提出如下科学假说： [分子A]可能通过[调控B]影响[效应C]，从而在[疾病D]中发挥[功能E]。 为验证上述假说，我们将[简要策略]。本研究将为[意义]。"
⚠️ 假说的三层验证标准：
- 可验证性 — 能否通过实验手段检验？
- 新颖性 — 是否提出了领域内未被充分认识的关联？
- 重要性 — 如果被证实，对领域的贡献是什么？
Step 4: 关键科学问题凝练
从假说中提取2-3个"卡脖子"问题。
⚠️ 强制格式要求：中标标书中的关键科学问题均为简洁的独立问句（1-2句话），不是段落。对照22份中标标书，关键科学问题都不超过3行。
字数限制：每个关键科学问题控制在50-80字，最多不超过100字。
每个问题以问句形式呈现，问题之间应有递进关系（what → how → significance），问题应对应研究内容的逻辑层次。
典型示例：
- [分子A]是否通过[通路B]影响[疾病C]的[表型D]？（what层面）
- [分子A]调控[通路B]的具体分子机制是什么？（how层面）
- 靶向[分子A/通路B]能否成为[疾病C]的新治疗策略？（significance层面）
常见错误：
| 错误 | 中标标书的正确做法 |
|---|---|
| 关键科学问题写成100-200字的大段文字 | 每个问题1-2句，简洁到可以一眼读完 |
| 一个"关键问题"里嵌套多个子问题 | 拆分为2个独立问题 |
| 关键问题与假说重复 | 关键问题是"卡脖子之处"，假说是"可能的答案" |
Step 5: 假说可视化
建议生成"机制假说图"（可后续交由 nsfc-figure 子技能实现）：
- 已知通路用实线
- 假设关系用虚线
- "?"标注待验证环节
- 关键分子突出显示
4. Anti-patterns（假说构建中的常见误区）
基于22份中标标书与未中标标书的对比：
| 误区 | 问题 | 修正 |
|---|---|---|
| "A→B→C→D"线性链 | 过于简单，缺乏机制深度 | 增加调控方式、修饰类型、反馈环路 |
| 假说=研究意义复述 | 没有可检验的预测 | 明确"如果假说成立，我们预期观察到什么" |
| 关键科学问题=研究步骤 | 把"要做什么"当"要回答什么" | 改为认知层面的卡点 |
| 假说不可证伪 | 无论结果如何都能自圆其说 | 增加排他性预测 |
| 证据链过长 | 6+环节，逻辑松散 | 缩减至3-4个核心环节，其余放入研究基础 |
6. 假设迭代参考
在构建假说时，强烈建议加载 ../../../_shared/references/hypothesis-iteration-patterns.md，其中收录了四种经典假设迭代模式，包括：
- 模式一：相关性→必要性→充分性→特异性（LAG3泛素化/Cell 42.5分）
- 模式二：体内外矛盾→剩余法推理→新假说（TCAIM/OGDH/Molecular Cell 16.6分）
- 模式三：多组学交叉→假设迭代→机制聚焦（GCGR/GLP1R→乳酸→H3K9乳酰化 14.6分）
- 模式四：筛选→功能验证→机制扩展→多维度闭环（HMGB2/Sci Adv 12.5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 · 109 lines · 87 tokens per session scan A f687fa0312bf
nsfc-hypothesis is a skill published in the GitHub repository Wesley-Yin77/nsfc_medicine_all (63 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 1,562 once invoked, about $0.0004 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
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…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…