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 HuiyuLi-2000/Chinese-Grant-Writer-Skills --skill fund-background-writergit clone --depth 1 https://github.com/HuiyuLi-2000/Chinese-Grant-Writer-SkillsWrote 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/huiyuli-2000/chinese-grant-writer-skills/fund-background-writer)<a href="https://agentmods.dev/skills/huiyuli-2000/chinese-grant-writer-skills/fund-background-writer"><img src="https://agentmods.dev/badge/skills/huiyuli-2000/chinese-grant-writer-skills/fund-background-writer/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/huiyuli-2000/chinese-grant-writer-skills/fund-background-writer"><img src="https://agentmods.dev/badge/skills/huiyuli-2000/chinese-grant-writer-skills/fund-background-writer.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 | $0.00047 | $0.01641 |
| Opus 5 | $0.00023 | $0.00821 |
| Sonnet 5 | $0.00009 | $0.00328 |
| Haiku 4.5 | $0.00005 | $0.00164 |
Grade A, and why
fund-background-writer 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fund-background-writer
基于 16 本成功 NSFC 申请书提炼的写作范式，实现"主题分析 → 政策调研 → 数据调研 → 立项依据撰写"的自动化流程。
技能范围
本技能只负责 NSFC 申请书中立项依据的 1.1 研究意义 部分，包含：
- 研究背景（含国家战略、现实困境、学术问题、本项目方案）
- 理论意义
- 实践意义
触发条件
当用户要求撰写 NSFC 立项依据、研究意义、项目背景，或提供研究主题并要求生成立项依据时，激活本技能。
执行流程
收到用户提供的材料后，严格按以下 7 步执行：
用户至少会提供以下输入：研究内容、研究方法、技术路线、特色与创新、研究目标、关键科学问题。如果输入不足，必须先追问补全再继续。
Step 1：读取知识库
读取以下文件，学习写作范式：
assets/templates/writing_style_guide.md—— 风格规范和叙事逻辑assets/templates/structure_template.md—— 段落安排和句子逻辑角色
Step 2：主题分析
- 解析研究主题的核心关键词
- 识别所属学科领域（管理科学与工程 / 医学 / 经济学 / 信息科学等）
- 确定科学问题属性（鼓励探索 / 聚焦前沿 / 需求牵引 / 交叉融通）
Step 3：输入-背景锚定
映射原则：让 agent 知道背景的每一段要"指向"什么，确保逻辑贯通。锚定是逻辑层面的"影子对应"，不是文字层面的"复制粘贴"——背景中的困境/不足/方案要用背景自己的语言和论证视角来写，但逻辑上要能追溯到后续输入。
输入→段落映射表：
| 用户输入 | 对应背景段落 | 写作视角转换 |
|---|---|---|
| 研究内容 | 段落C 的困境条数 | "现实问题"视角，不用"研究内容"视角 |
| 研究方法细节 | 段落D 的不足条数 | "现有方法的局限"视角，不用"本研究方法"视角 |
| 技术路线 | 段落E 的方案展开顺序 | 浓缩为"做什么"不说"怎么做"，用"本项目拟……" |
| 特色与创新 | 理论意义的条目 | 创新点说"做了什么"，理论意义说"有什么学术价值" |
| 研究目标 | 实践意义的条目 | 研究目标说"要实现什么"，实践意义说"对社会/行业有什么价值" |
| 关键科学问题 | 段落F 的科学问题列举 | 进行轻微改写，但不要直接复制，且与后续输入表述接近合理 |
独立约束：段落A和B（政策背景+数据背景）不受后续输入约束，由联网检索结果决定。
Step 4：联网检索
按以下策略执行联网搜索（由 agent 自行选择可用工具）：
政策检索（详见 references/policy_search_strategy.md）
- 优先来源：国务院、科技部、NSFC、国家统计局、教育部、国家卫健委、工信部、国家发改委及研究主题对应主管部门
- 目标：找到 2-3 个与主题直接相关的国家/部门级政策文件
- 记录：政策名称、发布年份、核心要求/表述
数据检索（详见 references/data_search_strategy.md）
- 优先来源：国家统计局、行业蓝皮书、权威白皮书、国际组织报告、高水平综述
- 目标：找到 3-5 个支撑问题严重性的统计数据
- 记录：年份 + 具体数值 + 出处 + 原始链接
- 禁止使用营销文章、无来源数据、转载数据
Step 5：生成立项依据大纲
按 structure_template.md 的段落结构，生成大纲：
- 每段标注：写什么、用什么数据/政策、句子逻辑角色
- 确保问题-方案一一对应
- 向用户展示大纲，确认后进入撰写
Step 6：撰写完整立项依据
严格遵循 writing_style_guide.md 的风格规范：
- 按段落 A→B→C→D→E→F → 理论意义 → 实践意义的顺序撰写
- 每段确保有政策/数据支撑
- 理论意义用"动词+对象+价值"结构分点阐述
- 实践意义从宏观到微观层层递进
- 避免"首次""填补空白"等绝对化表述
- 方法术语只做背景/验证手段，不撑段落主线
Step 7：自检与输出
- 按
references/dod_checklist.md检查结构完整性 - 按
references/boastful_expression_guidelines.md排查浮夸表达 - 按
references/dimension_coverage_design.md检查四个维度覆盖 - 输出最终文本，同时附上：
- 使用的政策清单（政策名称 + 年份 + 核心表述）
- 使用的统计数据清单（数据项 + 年份 + 数值 + 出处 + 链接）
What ships with it
13 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.
- assets/templates/structure_template.md 8.3 KB
- assets/templates/writing_style_guide.md 11 KB
- config.yaml 3.5 KB
- references/boastful_expression_guidelines.md 1.7 KB
- references/data_search_strategy.md 3.8 KB
- references/dimension_coverage_design.md 1.0 KB
- references/dod_checklist.md 1.7 KB
- references/info_form.md 2.4 KB
- references/methodology_term_examples.md 1.1 KB
- references/policy_search_strategy.md 3.0 KB
- references/scientific_hypothesis_guidelines.md 2.2 KB
- references/scientific_question_guidelines.md 2.0 KB
- references/theoretical_innovation_guidelines.md 2.1 KB
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 · 117 lines · 47 tokens per session scan A 05d91068c74d
fund-background-writer is a skill published in the GitHub repository HuiyuLi-2000/Chinese-Grant-Writer-Skills (383 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 1,641 once invoked, about $0.0002 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…