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 Lzy599775/agent-auto-sci-skills --skill scipilot-figure-skillgit clone --depth 1 https://github.com/Lzy599775/agent-auto-sci-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/lzy599775/agent-auto-sci-skills/scipilot-figure-skill)<a href="https://agentmods.dev/skills/lzy599775/agent-auto-sci-skills/scipilot-figure-skill"><img src="https://agentmods.dev/badge/skills/lzy599775/agent-auto-sci-skills/scipilot-figure-skill/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/lzy599775/agent-auto-sci-skills/scipilot-figure-skill"><img src="https://agentmods.dev/badge/skills/lzy599775/agent-auto-sci-skills/scipilot-figure-skill.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 | $0.00519 | $0.05361 |
| Opus 5 | $0.00260 | $0.02681 |
| Sonnet 5 | $0.00104 | $0.01072 |
| Haiku 4.5 | $0.00052 | $0.00536 |
Grade A, and why
scipilot-figure-skill 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 11d 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.
This is a copy
100% identical to scipilot-figure-skill — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
scipilot-figure-skill — 科研数据可视化顾问
SciPilot Skills 家族成员 | 从数据剖析到出版级成图
概述
科研工作者最大的画图痛点往往不是"不会用 matplotlib",而是"手上一堆数据,不知道该用什么图把结论讲清楚"。本技能的首要能力是【思考与判断】,其次才是【绘制】。
具体地——永远先思考再画:
- 先理解数据再选图——拿到数据先做 EDA,用事实驱动图型选择
- 先想清楚"这张图要论证什么"——同样数据,不同论点 = 不同图
- 主动拦截科研画图的经典错误,而不是顺从
- 维度太多就建议拆图,不硬塞
只覆盖纯数据图:折线、柱状、散点、箱线/小提琴、热力图、误差棒、分布图、相关性矩阵、多面板组合。不做示意图、流程图、架构图。
何时使用
- 用户给了一个 CSV / Excel / DataFrame 说"帮我画一下"或"用什么图好"
- 用户在写论文要插数据图
- 用户已有草图但说"达不到投稿要求"
- 用户提到 Nature / Science / IEEE 等具体期刊
- 用户问"中文论文 matplotlib 出方框怎么办"
- 用户提到误差棒、显著性、色盲、矢量导出、多面板
核心工作流(8 步)
这是本技能与普通画图工具的根本区别——不能上来就画。每一步缺位前一步的成果都不该执行。
第 0 步:理解任务
开画前先搞清楚两件事:
- 这张图要论证什么观点 / 回答什么问题? 同样数据,论点不同图就不同(详见
references/chart_selection.md的"同一批数据、不同论点 → 不同图"小节) - 数据在哪里?长什么样? 文件路径 / 字段含义 / 多少行 / 是否已经清洗
如果用户没说清论证目标,主动问一句:"你这张图主要想说服读者相信什么?" 或从论文上下文推断并明确告诉用户你的假设。不要默认"用户知道自己要什么"。
第 1 步:剖析数据
调用 scripts/profile_data.py:
python scripts/profile_data.py data.csv --group group --group condition
输出包含:每列类型、样本量、缺失率、连续列的描述统计 + 偏度 + 异常值、分组样本量分布、相关性矩阵、初步图型建议。
不会读这份报告?查 references/data_profiling.md。
重点核对:
- 列类型识别对不对?(数字 ID 被认成 ordinal 是常见误判)
- 每组 n 是多少?小样本警告?
- 是否高度偏态?是否需要对数轴?
第 2 步:选图
这是顾问职责的核心。基于第 0、1 步的事实,查 references/chart_selection.md 的决策框架决定图型。要点:
- 给出推荐 + 简短理由 + 1-2 个备选(不要只丢一个选择给用户)
- 如果数据维度过多(如分组组合 > 12)→ 明确建议拆图,而不是硬塞
- 如果用户指定的图型不适合数据(如 n=5 要画均值柱)→ 善意指出问题并说明更好的选择,让用户决定。详见下方"主动拦截"小节
- 如果数据特征意味着特殊处理(双峰分布、严重异常值、跨量级)→ 在选图建议里明确提及
第 3 步:查期刊规范
确定目标期刊后查 references/journal_specs.md 拿到:单/双栏宽(mm 与 inch)、字号、推荐字体、DPI、矢量格式偏好。
不知道目标期刊就问一句。"毕业论文 / 中文核心 / 英文 SCI / NeurIPS" 都对应不同规范。
第 4 步:配环境
from setup_style import setup_style
setup_style(journal='nature', lang='en') # 英文 Nature
setup_style(journal='general', lang='zh', serif_for_zh=True) # 中文宋体混排
SciencePlots 装了自动用,没装回退到内置预设——不会因为缺它崩溃。
第 5 步:绘制
按 references/plot_recipes.md 对应章节的配方画。每节都有可直接复制的 Python 代码 + 常见坑。
画图时强制做到:
figsize=(目标宽, 目标高)单位英寸——直接定最终尺寸- 用
seaborn.color_palette('colorblind')或 Okabe-Ito + 冗余编码(不同线型/marker) - 误差棒 / 阴影要在图注交代是 SD / SEM / 95% CI + n
What ships with it
19 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.
- .gitignore 513 B
- agents/openai.yaml 352 B
- LICENSE 1.0 KB
- NOTICE.md 403 B
- README.md 14 KB
- references/chart_selection.md 11 KB
- references/data_profiling.md 8.4 KB
- references/journal_specs.md 7.3 KB
- references/plot_recipes.md 19 KB
- references/publication_checklist.md 5.9 KB
- references/visual_review.md 7.2 KB
- references/viz_pitfalls.md 15 KB
- requirements.txt 287 B
- scripts/check_figure.py 9.5 KB runs code
- scripts/export_figure.py 6.3 KB runs code
- scripts/layout_tools.py 9.1 KB runs code
- scripts/profile_data.py 17 KB runs code
- scripts/setup_style.py 12 KB runs code
- scripts/visual_qa.py 12 KB runs code
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.
- 11d ago First seen · 329 lines · 519 tokens per session scan A 79e743810930
scipilot-figure-skill is a skill published in the GitHub repository Lzy599775/agent-auto-sci-skills (2 stars, last pushed 5d ago), licensed MIT. It adds 519 tokens to every session and 5,361 once invoked, about $0.0026 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to scipilot-figure-skill, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
papers-reading-skill
Evidence-grounded AI research workflow for turning supplied economics, finance, management, and social-science papers or structured records into versioned PaperReading artifacts. Use when Codex must ingest text, Markdown, or a text-based PDF; separate source-grounded claims from researcher analysis; bind findings to…
scopus-researcher
Expert academic researcher using the Scopus MCP. Finds papers, retrieves full abstracts, builds author profiles, analyzes citation impact, and constructs advanced Boolean queries across the Elsevier Scopus database. Activate when asked to search for academic papers, analyze research trends, find citations, profile…
write-literature-review
Iterative literature-review workflow for a research topic. Use this skill to draft up to 10 search keywords, build a seed set from OpenAlex title-and-abstract matches, expand by backward and forward citations, screen candidates by title and abstract, repeat until no new relevant papers remain, rank the final set…
nature-experiment-log
A workflow for turning experiment notes, images, audio, or text into structured Markdown laboratory logs with YAML metadata. It can also organize raw attachments and optionally connect the logs to Feishu or Obsidian.
researchwrite
Proposal-first scientific writing pipeline, installed under the compatibility trigger researchwrite and the repository package name nature-proposal-writer. Use for composing, revising, or auditing research proposals, opening reports, research plans, and evidence-grounded scientific writing. Three modes…
nature-writing
Draft, restructure, or plan Nature-style manuscript sections and initial-submission materials from author-provided claims, results, figures, notes, or Chinese drafts. Use for abstracts, introductions, related work, methods, Results or experiments, discussions, conclusions, titles, full manuscript arguments, and…