# Scientific figure

> Scientific figure is an open-source agent skill for health and science. Use when the user has scientific data (or a prompt alluding to scientific data) and wants a publication-quality figure made from it. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.

- **Kind:** Skill
- **Pricing:** Open source
- **Platforms:** Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- **Website:** https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/scientific-figure
- **Repository:** https://github.com/gaasher/agent-loop-skills
- **GitHub stars:** 183
- **License:** MIT
- **Skill name:** scientific-figure
- **Collection:** https://github.com/gaasher/Agent-Loop-Skills
- **Categories:** health and science
- **Listing updated:** 2026-11-17

## About

Use when the user has scientific data (or a prompt alluding to scientific data) and wants a publication-quality figure made from it. A generator drafts and renders a figure that lands a frozen communication goal; an adversarial critic critiques it hard and grades it 1-5 per axis against a fixed rubric (message, aesthetic, clarity, integrity, and a conditional domain-completeness axis), aggregates to 0-100, and decides pass; the generator revises against the critic's findings until the grade clears a threshold or the budget is hit. Both roles may consult the literature (Semantic Scholar + arXiv) to verify domain content (e.g. a pathway figure's gene set, or a benchmark's reported numbers), and conform to / grade against a named journal's figure spec fetched via web search. Not for writing a paper or analyzing a dataset, and not for editing an existing finished image — this renders a figure from data/brief and iterates on it.

## When your agent uses it

> Use when the user has scientific data (or a prompt alluding to scientific data) and wants a publication-quality figure made from it. A generator drafts and renders a figure that lands a frozen communication goal; an adversarial critic critiques it hard and grades it 1-5 per axis against a fixed rubric (message, aesthetic, clarity, integrity, and a conditional domain-completeness axis), aggregates to 0-100, and decides pass; the generator revises against the critic's findings until the grade clears a threshold or the budget is hit. Both roles may consult the literature (Semantic Scholar + arXiv) to verify domain content (e.g. a pathway figure's gene set, or a benchmark's reported numbers), and conform to / grade against a named journal's figure spec fetched via web search. Not for writing a paper or analyzing a dataset, and not for editing an existing finished image — this renders a figure from data/brief and iterates on it.

## What it can access

From a static check of the files on GitHub; nothing was run.

- [Instructions only, no scripts](https://github.com/gaasher/Agent-Loop-Skills/tree/HEAD/loops/scientific-figure)
- [License: MIT](https://github.com/gaasher/Agent-Loop-Skills/tree/HEAD/loops/scientific-figure)

## Install

### Claude Code

This skill ships in the `agent-loops` plugin. In Claude Code, add the marketplace and install the plugin (it may include other skills too):

```sh
/plugin marketplace add gaasher/Agent-Loop-Skills
/plugin install agent-loops@agent-loop-skills
```

Or copy only this skill to `~/.claude/skills/scientific-figure`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/scientific-figure &&
cp -R "$tmp/loops/scientific-figure" ~/.claude/skills/scientific-figure &&
rm -rf "$tmp"
```

For one project only, put the folder in `.claude/skills/scientific-figure` inside it instead.

### Codex

Copy the skill folder to `~/.agents/skills/scientific-figure` to use it in every repository:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/scientific-figure &&
cp -R "$tmp/loops/scientific-figure" ~/.agents/skills/scientific-figure &&
rm -rf "$tmp"
```

For one repository only, put the folder in `.agents/skills/scientific-figure` inside it instead.

### Cursor

Copy the skill folder to `~/.cursor/skills/scientific-figure` to use it in every project:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/scientific-figure &&
cp -R "$tmp/loops/scientific-figure" ~/.cursor/skills/scientific-figure &&
rm -rf "$tmp"
```

For one project only, put the folder in `.cursor/skills/scientific-figure` inside it instead.

### Gemini CLI

Run in a terminal (add `--scope workspace` to install it for the current workspace only):

```sh
gemini skills install https://github.com/gaasher/Agent-Loop-Skills.git --path loops/scientific-figure
```

Or copy the folder to `~/.gemini/skills/scientific-figure` yourself.

### VS Code

For GitHub Copilot in VS Code, copy the skill folder to `~/.copilot/skills/scientific-figure`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/scientific-figure &&
cp -R "$tmp/loops/scientific-figure" ~/.copilot/skills/scientific-figure &&
rm -rf "$tmp"
```

For one project only, put the folder in `.github/skills/scientific-figure` inside it instead.

### Other agents

Get the folder:

```sh
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.git
```

Then copy `Agent-Loop-Skills/loops/scientific-figure` into your agent's skills folder as `scientific-figure`. Agents that support SKILL.md read one folder per skill.

## FAQ

### How do I install Scientific figure in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/scientific-figure to use it in all your projects, or to .claude/skills/scientific-figure in one project. Or install the agent-loops plugin, which includes it: /plugin marketplace add gaasher/Agent-Loop-Skills, then /plugin install agent-loops@agent-loop-skills.

### Does Scientific figure run scripts?

No. It is instructions only, with no scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

### Which AI agents can use Scientific figure?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

### What are the best alternatives to Scientific figure?

The closest alternatives to Scientific figure are AWS resource health diagnose, Azure resource health diagnose, Assess observability health, Scientific writer and Medical bill organizer.

## Alternatives

- [AWS resource health diagnose](https://ai-powered.com/skills/aws-resource-health-diagnose): AWS resource health diagnose is an open-source agent skill for cloud and infrastructure.
- [Azure resource health diagnose](https://ai-powered.com/skills/azure-resource-health-diagnose): Azure resource health diagnose is an open-source agent skill for cloud and infrastructure.
- [Assess observability health](https://ai-powered.com/skills/assess-observability-health): Assess observability health is an open-source agent skill for health and science.
- [Scientific writer](https://ai-powered.com/skills/scientific-writer): Scientific writer is an open-source agent skill for health and science.
- [Medical bill organizer](https://ai-powered.com/skills/medical-bill-organizer): Medical bill organizer is an open-source agent skill for files and documents.
- [Phdtaketaketake](https://ai-powered.com/skills/phdtaketaketake): Phdtaketaketake is an open-source agent skill for health and science.
- [Session health](https://ai-powered.com/skills/session-health): Session health is an open-source agent skill for health and science.
- [Drug discovery pipeline](https://ai-powered.com/skills/drug-discovery-pipeline): Drug discovery pipeline is an open-source agent skill for health and science.

---
Source: https://ai-powered.com/skills/scientific-figure
