Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ymo6/illustrator-figure-mcp --skill recreate-scientific-figuregit clone --depth 1 https://github.com/ymo6/illustrator-figure-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ymo6/illustrator-figure-mcp/recreate-scientific-figure)<a href="https://agentmods.dev/skills/ymo6/illustrator-figure-mcp/recreate-scientific-figure"><img src="https://agentmods.dev/badge/skills/ymo6/illustrator-figure-mcp/recreate-scientific-figure/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ymo6/illustrator-figure-mcp/recreate-scientific-figure"><img src="https://agentmods.dev/badge/skills/ymo6/illustrator-figure-mcp/recreate-scientific-figure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00086 | $0.01558 |
| Opus 5 | $0.00043 | $0.00779 |
| Sonnet 5 | $0.00017 | $0.00312 |
| Haiku 4.5 | $0.00009 | $0.00156 |
Grade A, and why
recreate-scientific-figure scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recreate Scientific Figure in Illustrator
Coordinate the four-role protocol: Designer, Drawer, Reviewer, Corrector. Keep the roles logically separate even though you perform all four. Use design-scientific-figure for the spec, audit-scientific-figure as the Reviewer, and correct-scientific-figure as the Corrector.
Reconstruct structure; never trace. Tracing preserves appearance and destroys semantics, which is the entire point of the exercise. Image Trace, "place the reference and draw on top", and pasting vector art are all failures, and audit_figure reports them as trace-signature.
A successful tool call is not evidence of anything. Only two channels are evidence:
- geometry —
audit_figure, which proves internal correctness deterministically; - appearance — an exported PNG compared against the matching reference crop, judged visually.
A passing audit does not mean the figure resembles the reference. A good-looking render does not mean the structure is sound. Require both.
Before drawing
- Call
get_document_infoto confirm Illustrator is reachable and see what is already open. If the user has documents open, do not touch them — create your own withcreate_document. - Inspect the reference at full resolution, then region by region at readable resolution.
- Produce a
reconstruction_specwithdesign-scientific-figure: region ids, object names, geometry, styles, connector routes, grouping, raster decisions, and per-region acceptance conditions. - Create the document with
create_documentat the reference's aspect ratio. Work inartboard-webcoordinates: (0,0) is the artboard's top-left and Y increases downward.
Record unreadable text and obscured boundaries as explicit ambiguities. Never invent content.
Naming is not cosmetic
Every object's name is its semantic identity — the auditor reports findings by name, connectors bind by name, and corrections address objects by name.
- Give every object a stable, unique semantic name. Duplicates are a hard failure (
duplicate-semantic-name). - Name repeated series
panel-1,panel-2,panel-3. The auditor infers the series axis from the names and checks cross-axis alignment and equal spacing. A series namedleft,middle,rightis invisible to that check. - Set
semantic_typeto the object's role (box,panel,label,axis,connector,container,background). Objects typedpanel/container/backgroundare exempted from connector-intrusion checks, so a connector may legitimately cross them.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 94 lines · 86 tokens per session scan A 242ec406e7d9
recreate-scientific-figure is a skill published in the GitHub repository ymo6/illustrator-figure-mcp (0 stars, last pushed 14d ago), licensed MIT. It adds 86 tokens to every session and 1,558 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
scientific-schematics
Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.6 Flash for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and…
paper-poster-html
A workflow for building an academic conference poster as one HTML/CSS file and printing it to a PDF at an exact page size. It uses the paper’s real figures and checks layout details before review.
paperFig
Design, implement, revise, and validate publication-quality scientific figures from references, existing plotting code, and real project data. Trace every figure to source code and inputs; deconstruct reference figures; plan the scientific story and multi-panel structure; build complex model architecture and…
latex-posters
Use when creating or revising LaTeX research posters with beamerposter, tikzposter, or baposter, including poster layout, typography, color, print sizing, figure placement, QR codes, compilation, and print-ready PDF checks.
figure-composer
Compose a publication-grade multi-panel scientific figure from a claim, dataset, or draft result. Use when the task needs panel planning, consistent figure layout, figure review, or final figure assembly.
ccf-visual-composer
A visual design assistant for research papers, presentations, posters, and README graphics. It can lay out figures, tables, diagrams, icons, colors, and other visual elements, including editable SVG, PDF, and PPTX outputs.