FigMirror

FigMirror is a Data skill for Claude Code, published by VILA-Lab in FigMirror.

508 stars37 forkson VILA-Lab/FigMirrorAdded 2026/08/26+1% in starsRepository updated 2026/08/12

agentagent-skillsclaude-codecodexdata-visualizationllm-agentsmatplotlibpaper-figuresplottingpythonresearch-toolsscientific-visualizationskill

Install in seconds

Install FigMirror

Copy FigMirror into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/VILA-Lab/FigMirror/tree/main/.claude/skills/figmirror ~/.claude/skills/figmirror

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/VILA-Lab/FigMirror.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: .claude/skills/figmirror/SKILL.md in VILA-Lab/FigMirror
Installs to: ~/.claude/skills/figmirror
Collection: One of 6 skills cataloged from this repository
Category: Data — 668 skills

What FigMirror does

FigMirror transfers the visual style of a reference paper figure onto your own data and outputs matplotlib code, PNG, and PDF. Use it when you want a chart to match a paper’s aesthetic rather than just plotting data.

FigMirror is cataloged under Data on DirSkills. FigMirror comes from a repository tagged agent, agent-skills, claude-code, codex and data-visualization.

Documentation

README

Excerpt

FigMirror (`figmirror`)

Transfer the visual style of a top-conference paper figure (NeurIPS / ICML / ICLR / Nature / Science) onto user data via an iterative Drawer / Reviewer loop. Output is a self-contained matplotlib script + PNG + type-42 PDF that matches the reference's STYLE — not its data.

When to use

Trigger when the user provides all three:

A reference paper-figure screenshot.
Their own data in any parseable form (pasted table, CSV, TSV, markdown table, or dirty terminal text).
An expectation that the output should look like the reference — even via casual phrasing ("make this chart but with my numbers", "redo this in matplotlib"). This includes 3D references when the reference or data is actually 3D.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about FigMirror

What else does VILA-Lab publish alongside FigMirror?
FigMirror is one of 6 skills that DirSkills catalogs from VILA-Lab/FigMirror, the repository it ships in. Its siblings there include Fig Mirror, OpenSpec Apply Change and OpenSpec Archive Change. Each one is a separate skill with its own page in this directory, installs the same way FigMirror does, and is maintained by VILA-Lab in that same repository. The rest of the collection is listed on the VILA-Lab/FigMirror page.
How does FigMirror compare to other Data skills?
FigMirror ranks #604 by stars among the 668 Data skills in this catalog. The most-starred ones next to it are Benchmark Methodology, Jupyter Notebook and Solana. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of FigMirror against them. Open each page to compare what they document and how they install.