Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Wesley-Yin77/nsfc_medicine_allnpx agentmods add skills/wesley-yin77/nsfc_medicine_all/nsfc-polishingWrote 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-polishing)<a href="https://agentmods.dev/skills/wesley-yin77/nsfc_medicine_all/nsfc-polishing"><img src="https://agentmods.dev/badge/skills/wesley-yin77/nsfc_medicine_all/nsfc-polishing/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-polishing"><img src="https://agentmods.dev/badge/skills/wesley-yin77/nsfc_medicine_all/nsfc-polishing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00086 | $0.01721 |
| Opus 5 | $0.00043 | $0.00860 |
| Sonnet 5 | $0.00017 | $0.00344 |
| Haiku 4.5 | $0.00009 | $0.00172 |
Grade A, and why
nsfc-polishing 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NSFC Polishing — 标书润色与评审器
对标书进行全文级别的润色优化，并提供模拟评审功能。
Routing protocol
1. Load the manifest and core layer
Read manifest.yaml. Always load:
../../../_shared/core/winning-patterns.md— 中标标书质量标准../../../_shared/core/terminology.md— 术语一致性../../../_shared/core/ethics.md— AI辅助边界static/core/stance.md— 默认立场static/core/output-format.md— 输出格式规范
2. Detect axes
| Axis | Values | Method |
|---|---|---|
mode |
polish（润色）/ review（模拟评审）/ diagnose（诊断） | 从用户需求检测 |
section |
abstract / rationale / hypothesis / design / innovation / full | 从用户指定检测 |
grant_type |
面上 / 青年 / 地区 | 从标书信息检测 |
3. Load matching fragments
mode→static/fragments/mode/{polish,review,diagnose}.mdsection→static/fragments/section/{abstract,rationale,hypothesis,design,innovation,full}.md
4. Polish mode
语言润色原则
- 逻辑优先于辞藻：先确保论证链完整，再优化语言
- 科学准确性不可牺牲：不能为追求"好看"而模糊科学含义
- 保持申请人的学术声音：润色而非重写
- 术语全篇一致：遵循术语账本
针对性检查清单
| 部分 | 重点检查 |
|---|---|
| 摘要 | 是否在400字内覆盖：背景→Gap→假说→策略→意义 |
| 科学问题属性 | 800字内是否精准论述选择理由、与正文是否一致 |
| 立项依据 | 漏斗结构是否完整、Gap是否明确、假说是否清晰 |
| 研究内容 | 分项是否合理、与研究方案是否区分 |
| 研究方案 | 实验设计是否闭环、统计方法是否明确 |
| 可行性 | 是否覆盖4个维度 |
| 创新点 | 是否精准、有无空话 |
| 研究基础 | 预实验是否与正文假说相互印证 |
5. Review mode（模拟评审）
以国自然评审专家视角对全文进行评分和建议。
逻辑诊断配套参考：在评审和诊断模式下，必须加载
../../../_shared/references/nsfc-logic-diagnosis.md（假说质量自检、证据链长度诊断、黑箱检测、逻辑谬误自检清单），对标书的科研逻辑进行深度诊断。
NSFC标书评审模拟评分表
| 评审维度 | 权重 | 评分（1-10） | 关键问题 |
|---|---|---|---|
| 科学意义与创新性 | 25% | ? | 是否解决了领域内真问题？ |
| 科研逻辑与证据链 | 20% | ? | 假说是否可证伪？证据链是否完整封闭？ |
| 研究方案的合理性 | 20% | ? | 方案能否回答提出的科学问题？ |
| 研究基础的支撑度 | 20% | ? | 预实验/前期成果是否有力支撑？ |
| 申请人的学术能力 | 10% | ? | 是否有完成该项目的学术积累？ |
| 研究条件的保障度 | 5% | ? | 平台/团队/设备是否充足？ |
评审输出格式
对每个维度给出：
- 评分（1-10）
- 具体优点（1-3条）
- 具体不足/改进建议（1-3条）
- 综合建议（资助优先/可资助/修改后重审/不建议资助）
逻辑专项评审：在"科研逻辑与证据链"维度，使用
_shared/references/nsfc-logic-diagnosis.md中的5个自检工具进行系统诊断，包括：假说质量自检(5问)、证据链长度自检、逻辑谬误自检(3类)、研究方案完整性诊断、黑箱检测。
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 · 118 lines · 86 tokens per session scan A 0b008335c2ef
nsfc-polishing is a skill published in the GitHub repository Wesley-Yin77/nsfc_medicine_all (63 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 1,721 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…