Alterlab Figure Qa

Organization

NVlabs

alterlab-figure-qa

Verify publication figures with a render-then-check QA pass — data-fidelity against every underlying row, axis/label floor-and-ceiling legibility, bounding-box collision detection for overlapping text/markers, and 300-dpi print-readiness. Use when proofing or auditing a finished figure for correctness and print quality, catching mislabeled or overlapping elements, or confirming a plot faithfully represents its data before submission. For CREATING the plot prefer alterlab-matplotlib (or alterlab-seaborn / alterlab-plotly); for multi-panel publication layout prefer alterlab-scientific-viz; for schematic diagrams prefer alterlab-scientific-schematics. Part of the AlterLab Academic Skills suite.

Overview

Publisher	NVlabs
Repository	`Skill2Env`
Skill name	`alterlab-figure-qa`
Stars	189
Forks	18
Bundled files	2
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
2 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by NVlabs on GitHub. Read the source before you install it.

Installation

Install the Alterlab Figure Qa AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/NVlabs/Skill2Env/tree/main/SkillHub/skills/alterlab-figure-qa
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/NVlabs/Skill2Env.git /tmp/Skill2Env
mkdir -p .claude/skills
cp -r /tmp/Skill2Env/SkillHub/skills/alterlab-figure-qa .claude/skills/alterlab-figure-qa

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Alterlab Figure Qa in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Alterlab Figure Qa on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Alterlab Figure Qa is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Figure QA (render-then-verify)

Overview

A finished figure can look fine and still be wrong: a series plotted from the wrong column, a legend covering a data point, tick labels clipped at the axis edge, or a 150-dpi export that pixelates in print. This skill is a render-then-verify QA pass — it re-renders the figure and checks it against a concrete, measurable checklist before submission. It complements the plotting skills (which make figures); it does not create plots.

When to Use This Skill

Use this skill when the user wants to:

Proof a finished figure for correctness and print-readiness before submission.
Confirm the plot faithfully represents its data (every row/series accounted for).
Catch overlapping or clipped labels, legends, and markers.
Verify resolution / export settings (e.g. 300 dpi, vector where required).

Does NOT Trigger

Scenario	Use instead
Create/plot the figure in the first place	`alterlab-matplotlib` / `alterlab-seaborn` / `alterlab-plotly`
Lay out a multi-panel publication figure	`alterlab-scientific-viz`
Draw a schematic / diagram	`alterlab-scientific-schematics`
Build an infographic	`alterlab-infographics`

Core Capabilities

1. Data-fidelity check

Verify the rendered marks against every row of the source data: series count, point count per series, min/max/range on each axis, and that categorical labels match the data's categories. Flag any series plotted from the wrong column or a silently dropped subset.

2. Label floor-and-ceiling legibility

Check that tick labels, axis titles, and annotations are within legibility bounds — a font floor (nothing below the journal's minimum pt at final size) and a ceiling (titles not so large they crowd the panel) — and that nothing is clipped at the axis boundary.

3. Bounding-box collision detection

Compute the bounding boxes of text, legend, and markers and detect overlaps/collisions (legend over data, colliding labels, out-of-axes text). Report each collision with its location so it can be nudged.

4. Resolution and export QA

Confirm the export meets the target: ≥300 dpi for raster, vector format where the venue requires it, correct figure dimensions/column width, and embedded fonts. Fail the check if the raster resolution is below the floor.

5. Report

Emit a pass/fail checklist per criterion with the specific offending element(s), so the fix is actionable. See references/figure_qa_checklist.md for the full rubric and Matplotlib bbox recipes.

Resources

references/figure_qa_checklist.md — the full QA rubric, Matplotlib renderer/bbox recipes for collision detection, dpi/vector export checks, and journal legibility floors. Loaded on demand.

Part of the AlterLab Academic Skills suite.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

evals/evals.json3 KB
references/figure_qa_checklist.md3 KB

Frequently asked questions

What does the Alterlab Figure Qa AI skill do?

Why use Alterlab Figure Qa on TypingMind?

Because you install it once and use it with any model. Alterlab Figure Qa is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Alterlab Figure Qa in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/NVlabs/Skill2Env/tree/main/SkillHub/skills/alterlab-figure-qa. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Alterlab Figure Qa?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Alterlab Figure Qa?

As many as you like. As long as a model supports skills, you can use Alterlab Figure Qa with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Alterlab Figure Qa AI skill free?

Yes. It is published on GitHub by NVlabs under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Angular Developer

affaan-m

CommunityPopular

Angular コードを生成し、アーキテクチャガイダンスを提供します。プロジェクトの作成、コンポーネント、またはサービスを作成するとき、または反応性（シグナル、linkedSignal、リソース）、フォーム、依存性注入、ルーティング、SSR、アクセシビリティ（ARIA）、アニメーション、スタイリング（コンポーネントスタイル、Tailwind CSS）、テスト、または CLI ツール作成のベスト…

Anatomy

Explain an idea as an interactive isometric machine figure.

Auteur

Design and build cinematic, award-level web pages.

Skill Creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Figure QA (render-then-verify)

Overview

When to Use This Skill

Does NOT Trigger

Core Capabilities

1. Data-fidelity check

2. Label floor-and-ceiling legibility

3. Bounding-box collision detection

4. Resolution and export QA

5. Report

Resources

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now