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 kinhluan/skills --skill ai-figure-generationgit clone --depth 1 https://github.com/kinhluan/skillsWrote 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/kinhluan/skills/ai-figure-generation)<a href="https://agentmods.dev/skills/kinhluan/skills/ai-figure-generation"><img src="https://agentmods.dev/badge/skills/kinhluan/skills/ai-figure-generation/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/kinhluan/skills/ai-figure-generation"><img src="https://agentmods.dev/badge/skills/kinhluan/skills/ai-figure-generation.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 | $0.00057 | $0.02600 |
| Opus 5 | $0.00028 | $0.01300 |
| Sonnet 5 | $0.00011 | $0.00520 |
| Haiku 4.5 | $0.00006 | $0.00260 |
Grade A, and why
ai-figure-generation 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 11d 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Figure Generation
Turn research concepts into compelling visuals.
This skill generates scientific figures, diagrams, and illustrations using AI image models. It bridges the gap between technical research content and visual communication — essential for slides, papers, posters, and outreach.
"A picture is worth a thousand words — but only if it's the right picture." — Unknown
1. When to Use AI Image Generation
Use Cases
| Scenario | AI Tool | Output |
|---|---|---|
| Conceptual diagram | DALL-E 3 / Midjourney v6 | System architecture, workflow overview |
| Data visualization style | Stable Diffusion XL | Stylized charts, infographics |
| Illustrative figure | DALL-E 3 | Metaphorical representation of abstract concept |
| Poster figure | Midjourney v6 | Eye-catching, high-resolution scientific art |
| Slide background | Stable Diffusion | Themed backgrounds for presentation sections |
| Process flowchart | DALL-E 3 | Step-by-step methodology illustration |
When NOT to Use
- Exact data plots → Use
slide-automation(matplotlib/plotly) for accuracy - Mathematical notation → Use LaTeX/TikZ for precision
- Network topology → Use draw.io/Gephi for correctness
- Screenshots of code/results → Use actual screenshots
2. Prompt Engineering for Scientific Figures
2.1 The Scientific Prompt Formula
[Subject] + [Style] + [Context] + [Technical Details] + [Composition] + [Quality]
Example:
Subject: "A federated learning system with 5 edge devices"
Style: "clean vector illustration, flat design, scientific diagram"
Context: "medical AI training on hospital data without sharing patient records"
Technical: "each device labeled 'Hospital A-E', central server labeled 'Aggregator', arrows showing gradient updates"
Composition: "white background, devices arranged in circle around server, color-coded data types"
Quality: "4K, crisp lines, professional publication quality, no text clutter"
Full prompt:
"Clean vector illustration of a federated learning system. Five edge devices
labeled Hospital A through E arranged in a circle around a central server labeled
'Aggregator'. Each hospital has a different colored data icon (blue for imaging,
green for text, orange for genomics). Dashed arrows show encrypted gradient
updates flowing to the server. Solid arrows show updated model returning to
hospitals. White background, flat design, scientific diagram style, 4K,
crisp lines, professional publication quality, minimal text, no clutter"
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 283 lines · 57 tokens per session scan A 0cba52cf69f9
ai-figure-generation is a skill published in the GitHub repository kinhluan/skills (4 stars, last pushed 14d ago), licensed MIT. It adds 57 tokens to every session and 2,600 once invoked, about $0.0003 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
manim-skill
Create mathematical animations with Manim Community Edition(manimce). Generates distinctive, production-grade animations that avoid generic "AI slop" aesthetics. Use when user wants to animate concepts, equations, illustrate proofs, visualize algorithms, create math explainers, or produce 3Blue1Brown-style videos.
scientific-figure-prompt-compiler
Transform concise scientific or technical descriptions into structured visual specifications and high-quality image-generation prompts. Use for scientific figures, technical diagrams, system architectures, mechanisms, workflows, spatial models, timelines, layered systems, and information-dense visuals. Model-agnostic…
paper-illustration-image2
Generate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation. This is a separate experimental alternative to paper-illustration, intended for Claude Code users who want a GPT-image-style renderer without modifying the original skill.
scientific-slides
Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and…
paper-2-web
Use when converting academic papers into dissemination assets such as Paper2Web websites, Paper2Video video abstracts, or Paper2Poster conference posters from LaTeX or PDF sources.
ernie-image
Build Baidu ERNIE-Image / ERNIE-Image-Turbo workflows, primarily TEXT-TO-IMAGE. Pick ERNIE when you need precise multilingual text rendering, posters/signage, manga/anime multi-panel layouts, or strong instruction following for complex multi-object scenes. Also supports denoise-based image-to-image refine (NOT…