Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

Scientific Visualization

Design, audit, and export truthful, accessible, publication-ready scientific figures with Matplotlib, Seaborn, or Plotly.

Data & AnalyticsAdvanced★ 33,030⑂ 3,248AI score 9/10Last updated: Aug 9, 2026

What it does

  • Enforces honest encodings: zero baselines for bars/areas, cautious handling of dual axes, log scales, area/volume scaling, and mandatory disclosure of binning, normalization, and smoothing.
  • Handles uncertainty and missing data: requires naming SD/SE/CI/posterior intervals with n and replication unit, and visually distinguishing missing, zero, censored, and excluded values.
  • Builds accessibility in: color plus marker, line style, hatching, or direct labels; contrast audited at rendered size against WCAG 2.2 thresholds plus grayscale separation screening.
  • Exports deterministically with provenance: figure_export preserves physical page size, DPI, Type 42 font embedding, TIFF LZW, refuses silent overwrite, and writes a provenance manifest.
  • Bundled offline CLIs: raster/vector metadata inspection (Pillow, pypdf), palette contrast audit, publisher export planning (export_plan.py), and style previews.
  • Assets included: publication/Nature/presentation mplstyle files, Okabe-Ito and Paul Tol palettes, dated publisher profile JSON.

Who it's for

  • Researchers and grad students preparing figures for journals, theses, or posters
  • Anyone who wants to pre-empt reviewer complaints about truncated axes, ambiguous error bars, or color-vision accessibility
  • Teams juggling per-journal width (mm), DPI, and file-format requirements
  • Labs that need reproducible, integrity-respecting figure pipelines

Example uses

  1. Single-column figure: "Plot time vs. response by treatment at 89 mm width, 600 dpi PDF + PNG, with 95% bootstrap CIs" → figure built inside a style context, then exported with a provenance manifest.
  2. Pre-submission check: "Does figure1.tiff meet Nature's combination-figure spec?" → image_metadata.py reports DPI, mode, alpha, and page size; export_plan.py compares against the dated publisher snapshot.
  3. Palette audit: "Will this six-color palette separate for color-blind readers on white?" → WCAG contrast plus CIE L* grayscale report, then add redundant marker/line-style cues.

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/scientific-visualization folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/scientific-visualization/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/scientific-agent-skills && mkdir -p ~/.claude/skills && cp -r /tmp/scientific-agent-skills/skills/scientific-visualization ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Prerequisites: install Python 3.11+ and uv. If you plan to use Plotly static export (write_image), also install Chrome/Chromium.
  2. Clone the repo: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Copy the skill: mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/scientific-visualization ~/.claude/skills/
  4. Verify: run ls ~/.claude/skills/scientific-visualization and confirm SKILL.md, scripts/, assets/, and references/ are present.
  5. Restart Claude Code, then trigger it with prompts like "make a publication-ready figure" or "audit this figure for journal compliance".
  6. Optional smoke test: uv run --isolated --no-project --python 3.13 --with "matplotlib==3.11.1" python ~/.claude/skills/scientific-visualization/scripts/figure_export.py --demo outputs/export-smoke --manifest
  7. Caveat: publisher profiles and journal notes are dated snapshots, not compliance guarantees — re-check the live journal page right before you upload.
View source on GitHub ↗License: MIT