Figure
SkillDocs & knowledgeThis skill creates publication-quality econometric figures, including event study and coefficient plots, styled for the look of top economics journals. Figures are generated through the Google Gemini Nano Banana 2 API, using either your prompt or the surrounding context of the conversation. Once added, your AI can turn a request into a journal-ready chart.
Available today. Use it from your connected AI after setup.
No other account needed.
After adding the skill, describe the figure you want or point your AI to the results in your conversation, and it will generate the plot for you.
Then ask your AI: use the Figure skill
What your AI can do with it
- Generate figures from a prompt or the surrounding context
- Create event study plots
- Create coefficient plots
- Style figures to match top economics journals
What this skill tells your AI
The instructions your AI receives, as published by a554b554/reactant in skills/figure/SKILL.md and read by ahel’s review.
Activation Boundary
This is a tag-only worker skill. Use it only after execute or execute-one
selects an exact <@figure...> annotation in a target document and hands off
its context. Never activate it from an ordinary chat image request, semantic
similarity, or any skill other than those two routers. Without that handoff,
do not generate or save an image.
Generate an image described by the prompt and surrounding context, save it, and replace the tag with an image reference.
Tag
<@figure: description of the figure>
<@figure: description, save to ``figures/name.png``>
Input
- File path — the document being processed.
- Surrounding block — the maximal run of non-blank lines containing the tag; blank lines bound it.
- Prompt (optional) — the figure description. If absent, infer the figure from the surrounding text.
Workflow
- Read the prompt and surrounding block. Resolve any double-backtick context references: input references are files to read for context; an output reference is the image destination.
- Synthesize a detailed image-generation prompt from the user's intent and the document context.
- Generate the image with whatever image-generation capability your host provides — a built-in tool, an MCP tool, or an API the user has configured. Reactant does not prescribe or hardcode a provider.
- Save the image:
- To the output context reference, when the prompt gives one (path relative to the document's directory unless absolute).
- Otherwise to a
figures/directory next to the document (create it if needed), with a sanitized name derived from the prompt: lowercase, underscores, no spaces or special characters (for examplefigures/system_architecture.png).
- Replace the
<@figure: ...>tag with a format-appropriate reference using a path relative to the document:- Markdown:
 - LaTeX:
\includegraphics{figures/name.png}(inside a figure environment when the document's existing figures use one)
- Markdown:
Rules
- Consume only this tag; do not rewrite surrounding prose. Preserve every
unrelated tag,
<@comment: ...>tag,<@chat-model>block, and escaped literal byte-for-byte. - If the host has no image-generation capability, fail cleanly: leave the tag, change nothing, and report the missing capability.
- The generated image is accepted as produced; Reactant runs no quality check, regeneration, or second model pass on it.
Signals
- GitHub stars
- 54
- Forks
- 11
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
figure- Source
- github.com/a554b554/reactant