Nature Skills is a collection of reusable skills that help AI agents handle academic writing and scientific visualization. Researchers and AI-assisted scholars use it to turn research tasks into repeatable workflows and usable outputs. The catalogue entries are skills from this collection.
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 Yuan1z0825/nature-skills --skill nature-social-sciencegit clone --depth 1 https://github.com/Yuan1z0825/nature-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/yuan1z0825/nature-skills/nature-social-science)<a href="https://agentmods.dev/skills/yuan1z0825/nature-skills/nature-social-science"><img src="https://agentmods.dev/badge/skills/yuan1z0825/nature-skills/nature-social-science/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/yuan1z0825/nature-skills/nature-social-science"><img src="https://agentmods.dev/badge/skills/yuan1z0825/nature-skills/nature-social-science.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk 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 | $0.00171 | $0.03362 |
| Opus 5.5 | $0.00068 | $0.01345 |
| Sonnet 5.5 | $0.00034 | $0.00672 |
| Haiku 4.5 | $0.00017 | $0.00336 |
Grade A, and why
nature-social-science 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 6d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nature Social Science — 社科写作与选题论证工作台
本技能将社科硕博科研选题可落地工作流（源自《Finding a PhD Topic with Codex》一文的思想）转成一套可执行的写作与自检流程，覆盖定量、质性、民族志、档案、文件、语料和数字研究。
适用范围：社会科学及相邻人文学科。定量、质性、民族志、档案、文件、语料和数字研究都能用。 判断标准始终相同：问题是否清楚，证据是否匹配，主张是否诚实，项目是否能由这名研究者完成。
不做什么：不替你生成一个"正确题目"，不保证新颖、录取、资助、发表或论文成功， 不把某种方法当作高质量研究的默认答案。AI 的自信不是证据；填完的表格不是通关证明。
一、先做路由：用户在哪个环节？
| 用户诉求 | 对应要素 | 走哪几步 | 读哪些参考 |
|---|---|---|---|
| "我想研究 XX"／"帮我找个论文题目" | 选题构思 | Step 1 → 2 → 3 | 01-foundations.md、02-workflow-steps1-3.md |
| "这方向有人做过吗"／文献怎么梳理／版图怎么画 | 文献梳理 | Step 2 → 3 | 02-workflow-steps1-3.md |
| "我有数据/我想用方法 M" | 选题构思（假起点） | 先回 Step 1 | 01-foundations.md §六 Two false starts |
| "这个题目能不能做"／证据够不够 | 论证组织 + 可行性 | Step 4 → 7 | 03-workflow-steps4-5.md、04-workflow-steps6-8.md |
| "帮我生成几个研究问题"／RQ 怎么写 | 选题构思 | Step 5 | 03-workflow-steps4-5.md |
| "帮我想想审稿人会怎么攻击"／查新颖性 | 论证组织 | Step 6 | 04-workflow-steps6-8.md |
| "结论是不是说过头了"／表述定级 | 学术表达 | Step 4 的 claim ceiling + 术语纪律 | 09-academic-expression.md、07-status-terminology.md |
| "帮我改稿／润色论证段落" | 学术表达 | 对照 claim ceiling 与 Red flags | 09-academic-expression.md |
| "怎么跟导师谈"／开题材料怎么写 | 交付使用 | Part III | 08-usage-handoff.md |
| 需要现成提示词 | — | 按步骤取 | 05-prompt-library.md（唯一权威版本） |
| 需要填表模板 | — | 按步骤取 | 06-worksheets.md |
入口判断（必做第一步）：只有兴趣 → Mode A；已有宽泛主题或关系 → Mode B； 已有暂定研究问题 → Mode C（audit route，不是 advanced route）。 只有数据集或方法偏好时，先问"它能帮助理解什么未决现象"，答不出来从 Mode A 开始。
二、四条铁律（每条回复都要守）
- 不知道的地方写"未知"，不要让 AI 补猜。
- 主动找矛盾、零结果、反向关系和替代解释——不是找支持起点的材料。
- 保留证据层级、证据状态、失败搜索和关键未知，不把它们抹平成一个乐观结论。
- 每步结束后更新
Current Research State，不要把整段旧对话带进下一步。
配套禁止项（写进每一次给出的提示词里）：
- 不要生成选题、题目或假设（在尚未到那一步时）；
- 不要声称存在研究空白或新颖性；
- 不要默认使用定量、定性、因果或任何特定方法；
- 不要把"本轮没找到"写成"没有研究"；
- 不要把个人兴趣写成已经得到证明的学术重要性；
- 不要编造引文、来源或结果。
三、十二个判断（写作自检红线）
任何一次关于选题或论证的判断，先过这张表。完整版见 01-foundations.md §四。
| 不要混为一谈 | 可操作的检查 |
|---|---|
| Interest ≠ Topic | 是否已经划出要探索的现象、过程和边界？ |
| Topic ≠ Research problem | 是否指出领域中具体哪里解释不通？ |
| Research problem ≠ Research question | 是否把知识困难变成可由证据推进的任务？ |
| Research gap ≠ "few studies" | 研究少造成了什么知识后果？ |
| Novelty ≠ nobody has studied it | 是否解决矛盾、机制、测量或新近可回答的问题？ |
| Interesting ≠ Important | 除了个人兴趣，答案会改变谁对什么的理解？ |
| Important ≠ Answerable | 是否有合适、合规且时间匹配的证据？ |
| Available source ≠ Valid evidence | 字段、文本或观察真的对应目标概念吗？ |
| Correlation ≠ Mechanism | 是否看见过程，还是只看见现象同时出现？ |
| Advanced method ≠ Strong contribution | 方法是否解决了原来的知识困难？ |
| Feasible study ≠ PhD-worthy project | 它能否支撑一个核心谜题与连贯发展？ |
| AI judgement ≠ Researcher judgement | 哪些决定需要用户的价值、经验和导师判断？ |
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.
- agents/openai.yaml 308 B
- manifest.yaml 2.4 KB
- README_EN.md 3.4 KB
- README.md 2.9 KB
- references/01-foundations.md 13 KB
- references/02-workflow-steps1-3.md 38 KB
- references/03-workflow-steps4-5.md 29 KB
- references/04-workflow-steps6-8.md 40 KB
- references/05-prompt-library.md 53 KB
- references/06-worksheets.md 13 KB
- references/07-status-terminology.md 11 KB
- references/08-usage-handoff.md 8.7 KB
- references/09-academic-expression.md 13 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.
- 6d ago First seen · 180 lines · 171 tokens per session scan A 62c1b5624734
nature-social-science is a skill published in the GitHub repository Yuan1z0825/nature-skills (48,730 stars, last pushed today), licensed Apache-2.0. It adds 171 tokens to every session and 3,362 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-10-11.
Other skills, from other repositories
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
playwright-frontend
For frontend engineers authoring UI — how to make components reliably locatable by tests and AI agents. Covers the official Playwright locator priority, semantic/accessible markup first, and how to add valid, unique, stable data-testid attributes (naming convention, uniqueness in lists, stability rules) for React…
cesiumjs-imagery
CesiumJS imagery layers - ImageryProvider, ImageryLayer, ImageryLayerCollection, WMS, WMTS, Bing, OpenStreetMap, ArcGIS, Mapbox, tile discard policies. Use when adding or swapping base map layers, configuring imagery providers, layering multiple map sources, or creating split-screen imagery comparisons.
cesiumjs-core-utilities
CesiumJS core utilities and networking - Resource, Color, Event, Request, RequestScheduler, error handling, helper functions, feature detection. Use when fetching remote data, managing HTTP requests, working with colors, handling events, debugging errors, or using utility functions like defined, clone, or…
migrate-brizy-to-gutenberg
Use when the user says 'migrate brizy to gutenberg', 'convert brizy to blocks', or 'replace brizy with native wordpress'. Parses the Brizy JSON data, maps elements to core blocks, and creates draft duplicates for review.
competitor-content-intelligence
Analyze competitor content coverage and uncover differentiated content opportunities using web search, page extraction, and DataForSEO content analysis. Use when asked for competitor content research, editorial gap analysis, content brief inputs, or topic whitespace.