Draw Science
Create, revise, audit, and export publication-style scientific flowcharts and schematic workflows in diagrams.net/draw.io. Use for research-paper flowcharts, Nature-style workflows, graphical abstracts, method pipelines, experimental design, cohort/study flow, mechanism schematics, model architecture, editable .drawio files, and SVG/PDF-ready scientific diagrams, including 科研流程图, 论文流程图, draw.io作图, 方法流程图, 实验设计图, 技术路线图, 机制示意图, and 图形摘要. Start from a scientific message, topology, grid layout, semantic composite-element plan, collision-free routing, math-label contract, export contract, and review
Install
npx skills add QIANJINYDX/research-drawio-skill --skill draw-sciencegit clone --depth 1 https://github.com/QIANJINYDX/research-drawio-skill.git /tmp/research-drawio-skill
mkdir -p ~/.claude/skills
cp -r /tmp/research-drawio-skill/skills/draw-science ~/.claude/skills/draw-sciencePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Draw Science Build scientific flowcharts as visual arguments, not decorative process maps. The diagram must make a paper's method, mechanism, cohort flow, model architecture, or analytical logic easier to review. This skill mirrors the `nature-figure` philosophy: first define the scientific claim and evidence hierarchy, then choose the minimum diagram structure, then engineer the layout and connectors, then apply restrained journal style and export QA. The output should not be an all-text box diagram when the topic has visual entities. Use editable draw.io primitives to build semantic glyphs for the key scientific objects, while keeping labels short and reviewable. ## Routing Protocol Follow these steps whenever the skill is invoked. ### 1. Load the manifest and core layer Read [manifest.yaml](manifest.yaml). Then read every file listed under `always_load`: - `static/core/contract.md` - `static/core/stance.md` Do not draw from memory or from a favorite template before the contract exists. If the diagram contains formulas, load `references/math-typesetting.md` before authoring any formula labels. If the diagram contains biological structures, charts, tensors, model modules, or other visual entities, load `references/composite-elements.md` before drawing those entities. If the diagram is traced from a GPT/imagegen/raster reference and close visual matching matters, load `references/strict-visual-comparison.md` before final QA.
Details
- Skill name
draw-science- Repository
- QIANJINYDX/research-drawio-skill
- Path
skills/draw-science/SKILL.md- Repo updated
- 30 July 2026
FAQ
What does the Draw Science skill do?
Create, revise, audit, and export publication-style scientific flowcharts and schematic workflows in diagrams.net/draw.io. Use for research-paper flowcharts, Nature-style workflows, graphical abstracts, method pipelines, experimental design, cohort/study flow, mechanism schematics, model architecture, editable .drawio files, and SVG/PDF-ready scientific diagrams, including 科研流程图, 论文流程图, draw.io作图, 方法流程图, 实验设计图, 技术路线图, 机制示意图, and 图形摘要. Start from a scientific message, topology, grid layout, semantic composite-element plan, collision-free routing, math-label contract, export contract, and review
How do I install the Draw Science skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add QIANJINYDX/research-drawio-skill --skill draw-science. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Draw Science popular?
It lives in QIANJINYDX/research-drawio-skill, which has 49 GitHub stars and 2 forks.
Related skills
Add SVG
49QIANJINYDX/research-drawio-skill
Add, collect, design, audit, and integrate SVG elements into editable diagrams.net/draw.io scientific figures. Use when the user asks to supplement a draw.io diagram with SVG icons, mechanisms, biological objects, model components, pathway symbols, instruments, graphical abstract elements, or publication-style vector assets. Every execution must first ask the user to choose the SVG source mode: network search or self-designed SVG. For network mode, search for multiple relevant SVG candidates for later user selection, record sources and license notes, and fall back to self-designed SVG for conc
Research Draw
49QIANJINYDX/research-drawio-skill
Two-stage workflow for publication-style scientific schematics: generate or use a raster reference with imagegen/PNG/JPG/WebP, then trace it into an editable diagrams.net/draw.io file using draw-science. Use for Nature-style scientific illustrations, graphical abstracts, model or mechanism schematics, biomedical workflows, AI architecture figures, and paper-style visual drafts that should become editable .drawio source. For complex recognizable elements, author or select dedicated SVG glyphs and compare rendered SVGs against reference crops before inserting them, instead of assembling those el
Zju Literature Downloader
36baihe26/zju-literature-downloader
Use this skill whenever the user wants to use their own logged-in Zhejiang University Library, WebVPN, CAS SSO, 求是学术搜索, Summon, ScienceDirect, publisher, or Chrome session to legally search, download, organize, retry, and read academic PDFs and supporting information. Trigger on requests like “用浙大图书馆下载文献”, “WebVPN 下载 PDF”, “CAS 认证失败后重试下载”, “ScienceDirect 人机验证后继续”, “自动下载补充材料”, “读取全文和 supporting information”, “批量整理文献到项目文件夹”, or “导入 Zotero 后帮我读全文”.
Genealogy Research
43sliday/genealogy-research
Use when the user works on family history: shares scans, photos, or database screenshots of parish, civil, census, military, or migration records; asks about ancestors, surnames, or a family tree; edits or validates a GEDCOM file; keeps genealogical notes in an Obsidian vault; or needs archives, databases, APIs, or lawful retrieval methods for a country, region, or time period. Any language or script, including handwritten historical records.
Alterlab Zarr
87AlterLab-IEU/AlterLab-Academic-Skills
Chunked, compressed N-dimensional arrays for cloud storage with Zarr — parallel I/O, S3/GCS integration, and NumPy/Dask/Xarray compatibility. Use when storing or reading large N-D scientific arrays, streaming chunked data to/from cloud object stores, or building large-scale scientific computing pipelines. Part of the AlterLab Academic Skills suite.
Research Artist for Suno
43nwp/suno-song-creator-plugin
This skill should be used when the user asks to "research an artist", "analyze [artist] style", "study [song]", "look up [artist] patterns", or wants to explore musical patterns before creating a Suno song. Automatically launches song-researcher sub-agent for comprehensive pattern analysis from web sources.
Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.