Happy Figure Skill

Use when 用户想根据论文、科研文档、研究文本、图注、开题/答辩材料或具备读图条件的参考图生成可复制的 AI 科研绘图提示词；触发场景包括论文配图、科研绘图、图形摘要、Graphical Abstract、机制图、技术路线图、实验装置图、模型架构图、多面板对比图、汇报总览图、参考图风格迁移、未知领域母版生成，或上传/引用 PDF、Word、LaTeX、Markdown、摘要、方法段、图注、课题说明、研究方案、参考图片。Also use when the user asks for scientific figure prompts, research illustration prompts, graphical abstract prompts, mechanism diagrams, technical roadmaps, experimental setup diagrams, model architecture diagrams, multi-panel scientific figures, paper/conference figures, or AI image prompts based on papers, research documents, abstracts, methods sections, figure captions, proposals

177 stars 13 forksResearch & Science

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add BAIKEMARK/happy-figure-skill --skill happy-figure-skill

Manual install

git clone --depth 1 https://github.com/BAIKEMARK/happy-figure-skill.git /tmp/happy-figure-skill
mkdir -p ~/.claude/skills
cp -r /tmp/happy-figure-skill/. ~/.claude/skills/happy-figure-skill

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# happy-figure-skill

这个 Skill 专门把论文、开题材料、实验方案、研究说明或具备读图条件的参考图转换成可直接复制给 AI 绘图模型的科研绘图提示词。它只生成 prompt，不生成图片，不推荐草图工具，不展开矢量化或后处理流程。最终 prompt 和图中文字使用中文还是英文，由论文语言、投稿场景和用户需求决定。

## 核心流程

1. 解析用户提交的研究内容。
   - 如果用户给了文件路径，先运行 `scripts/extract_research_doc.py`。
   - 支持 `.docx`、`.pdf`、`.tex`、`.latex`、`.md`、`.txt`。可以尝试解析 `.doc`，但旧版 Word 文件依赖本地转换工具；失败时要求用户转换为 `.docx` 或粘贴相关文本。
   - 提取标题、摘要、方法、结果、图注、结论和候选上下文片段。
   - 如果用户给的是 LaTeX 文件夹，要求用户指定主 `.tex` 文件，不要自行猜入口。
   - 如果 PDF 或 Word 解析质量不高，要明确说明，只基于已成功提取的文本生成提示词。

2. 判断绘图上下文。
   - 识别研究主题、学科领域、候选图类型、最适合可视化的论文片段。
   - 如果明显属于计算机/机器学习、材料与化学、生物与医学，优先使用领域母版。
   - 领域母版必须使用对应学科的发表语境：计算机类优先 ACM/IEEE/NeurIPS/ICML/CVPR/ACL/VLDB/KDD/WWW 等论文架构图的信息组织方式，不要套用 Nature/Science/Cell 的生物医学或材料科学视觉语言；材料化学、生物医学再使用各自对应期刊风格。
   - 对计算机/机器学习论文，不要把“领域会议风格”和“图面气质”混成一个选择；先分开判断两件事：**内容社区**（论文主题更接近哪个会议/期刊家族，决定信息组织方式）和 **视觉气质**（用户想要严格正文论文图、高级科研 graphical abstract、科研汇报/白皮书总览图，还是极简扁平矢量图）。
   - 如果用户未指定目标风格，不要直接锁死一个单一风格；先给出 2-3 个很短的“出图预期确认”候选，每个只写清“内容社区 + 视觉气质 + 适合什么结果”，并标注推荐项。目的是让用户在付费生图前确认大方向，不要写成长篇风格说明。
   - 如果用户提到“好看、质感、高级、出彩、精修、teaser、graphical abstract、海报、项目主页、展示图”等审美目标，优先推荐 **Premium Academic Graphical Abstract / 高级科研图形摘要** 视觉气质，而不是朴素的会议正文流程图；但内容社区仍然按论文主题选择。
   - 如果风格选择会显著改变最终 prompt，先让用户在候选风格中选择，此时不要同时输出最终绘图提示词；如果用户要求快速生成、“直接默认”或“只要 prompt”，才使用推荐项继续生成最终 prompt。
   - 图类型只作为表达任务规则，不替代领域母版。领域明确时，领域母版负责科学对象、学科语义和视觉语言；`references/figure-type-masters.md` 只作为适配层，约束表达目标、布局、区域、连接关系、可见文字和常见失败。
   - 只有当领域不明确、交叉学科明显或没有合适领域母版，且通用图类型结构不会丢失关键领域语义时，才单独使用图类型规则。

Read the full skill on GitHub

Details

Skill name: happy-figure-skill
Repository: BAIKEMARK/happy-figure-skill
Repo updated: 3 June 2026

FAQ

What does the Happy Figure Skill skill do?

How do I install the Happy Figure Skill skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add BAIKEMARK/happy-figure-skill --skill happy-figure-skill. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Happy Figure Skill popular?

It lives in BAIKEMARK/happy-figure-skill, which has 177 GitHub stars and 13 forks.

Related skills

Research Mode

154

assafkip/research-mode

Anti-hallucination research mode. Toggle on to enforce citation requirements, source grounding, and "I don't know" behavior. Toggle off for creative work.

Research & Science19

Paper Search Pro

223

O0000-code/paper-search-pro

Find academic papers across up to 8 sources (OpenAlex / Semantic Scholar / CrossRef / PubMed / arXiv for English, OpenReview for AI venues, plus native-Chinese retrieval via NSSD 国家哲社文献中心 + yiigle 中华医学期刊) with adjustable depth — Quick scan (5 min) to Audit prep (3 hr). Use when the user wants to find papers, run a literature search, gather references, scope a research topic, search Chinese-language / 中文原生 literature (中文文献/中文核心/CSSCI/C刊/国内研究/国内文献/中华××期刊/心理学报/经济研究), or filter results by journal tier (中科院分区/一区/几区, Q1, JCR/SJR quartile, 影响因子/impact factor, 期刊分区, 顶刊/top journal, '按分区筛'), or export

Research & Science16

Papercash

159

Jesseovo/PaperCash

使用本地 Python CLI 辅助论文检索、摘要级文献整理、DOI 引用格式化、Word 格式检查、查重预检和写作修改。涉及“降AI率”时只提供表达建议；不把检索结果当成全文阅读或正式查重结果。

Research & Science10

Paper Finder

241

bchao1/paper-finder

Finds and organizes ML, CV, NLP, and AI research papers based on textual descriptions and keywords. Searches across arxiv, Google Scholar, Semantic Scholar, and top venues (CVPR, ECCV, ICCV, NeurIPS, ICML, ICLR, SIGGRAPH, SIGGRAPH Asia, EMNLP, ACL, CoRL, RSS, AAAI, IJCAI, WACV, BMVC, MICCAI, KDD, WWW, NAACL, COLM, and more). Maintains a persistent memory bank of discovered papers, a mind-graph linking papers to topics, individual paper summaries, and BibTeX entries. Use this skill whenever the user wants to find papers, search for related work, build a literature review, discover what exists o

Research & Science22

Research Junshi

129

junshi-research/research-junshi

Personalized academic literature digests and ranked research ideas grounded in the researcher's papers and persistent memory. Use for research brainstorming, daily paper discovery, strategic research advice, and updating research interests, projects, or feedback.

Research & ScienceIn 1 list

Anima

260

Garinmckayl/anima

Create crafted, accurate visualizations of anatomy, neurobiology, pharmacology, drugs, cells, and molecular biology. Show real biological structures and make their mechanisms visible, using literal anatomy or a clearly identified mechanical metaphor. Build interactive isometric SVG figures with sourced numbers, accessible motion, optional WebGL, a framed card and live readout. Use for biological explainers, educational illustrations, documentation and interactive figures.

Research & Science24

Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.