Academic Figure Generator is a local web application that analyzes uploaded academic papers and generates prompts and research figures with AI. Researchers use it to turn papers into downloadable diagrams through a workflow for uploading, reviewing, generating, and editing images. The catalogue skills provide this figure-generation workflow for coding agents.
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 LigphiDonk/academic-figure-generator --skill academic-figure-prompt-pastelgit clone --depth 1 https://github.com/LigphiDonk/academic-figure-generatorWrote 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/ligphidonk/academic-figure-generator/academic-figure-prompt-pastel)<a href="https://agentmods.dev/skills/ligphidonk/academic-figure-generator/academic-figure-prompt-pastel"><img src="https://agentmods.dev/badge/skills/ligphidonk/academic-figure-generator/academic-figure-prompt-pastel/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/ligphidonk/academic-figure-generator/academic-figure-prompt-pastel"><img src="https://agentmods.dev/badge/skills/ligphidonk/academic-figure-generator/academic-figure-prompt-pastel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 5 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Prompt Injection · line 295 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 297 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00122 | $0.03731 |
| Opus 5 | $0.00061 | $0.01865 |
| Sonnet 5 | $0.00024 | $0.00746 |
| Haiku 4.5 | $0.00012 | $0.00373 |
Grade A, and why
Academic Figure Prompt — Modern ML Airy Style 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 13d 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 — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Academic Figure Prompt — Modern ML Airy Style v4
为学术论文生成极其详细的英文提示词，产出的图片风格对标近年 ICLR / NeurIPS / ICML 顶会中常见的现代柔彩风格。
⚠️ 核心风格规则（经 7 轮迭代验证）
规则 1：纯白画布 + 白色面板 + 微弱阴影
画布（canvas）= 纯白 #FFFFFF，无渐变、无灰度、无暖色调
面板（panel）= 白色 #FFFFFF 圆角矩形 + 极微弱的 soft drop-shadow
(3px blur, 1px y-offset, rgba(0,0,0,0.06))
区分方式 = 仅靠阴影浮起，不靠灰色填充或边框
❌ 不要用灰色
#F5F5F5填充面板
❌ 不要用渐变画布背景
✅ 面板是白色，浮在白色画布上，靠阴影区分
规则 2：圆角友好字体
字体 = 圆角几何无衬线体（Nunito / Poppins / Quicksand / Comfortaa）
特征 = 字母末端圆润，手感友好温暖，不是锐利的 Helvetica/Arial
标题 = semi-bold ~ bold (600-700)，~16-18pt
正文 = regular (400)，~10-11pt
公式 = italic serif (Computer Modern / STIX)
字体是区分这种风格与传统论文图的核心特征之一
规则 3：排满但不拥挤
每个面板 = 充满内容（token、曲线、公式、图标、箭头）
元素间距 = 8-12px 微间距，不留大面积空白
整体感 = "信息丰富、排列有序" 而非 "空旷稀疏"
但也不 = 重叠、堆砌、文字墙
❌ 每个面板只放 1-3 个元素（太空）
❌ 密密麻麻文字标注堆砌（太挤）
✅ 丰富的视觉元素 + 一致的微间距 = 充实而有序
规则 4：浮动元素，不嵌套框
元素直接浮在白色面板上，不套独立的背景框
不要 box-in-box 嵌套结构
概念名用白色/极淡色 pill 药丸标签
曲线、公式、图标直接画在面板表面
规则 5：色彩通过 token + 文字 + 曲线传达
Token 小方块 = 10-14px 圆角方块，pastel 填充 + 1px 略深边框
彩色文字 = 关键概念名用语义色（coral/teal/purple/green）
曲线线条 = 用 pastel 色画线
面板/画布 = 始终白色，不参与色彩
五种色彩载体
| 载体 | 说明 | 示例 |
|---|---|---|
| Token 方块 | 小圆角方块，pastel 填充 + 暗 1px 边框 | soft blue #BBDEFB square with 1px #90CAF9 border, "s₁" label |
| 彩色文字 | 关键词直接用彩色字体 | bold coral #E05555 text "Exciter" |
| Pill 标签 | 极淡底色圆角药丸 | faint green-tinted pill badge "Random Forest" |
| 曲线线条 | 内嵌缩略图的线条颜色 | sigmoid curve in warm amber #DAA520 line |
| 叶节点/圆点 | 小彩色圆点标记类别 | 5 tiny circles in blue, pink, amber, purple, green |
工作流程
Step 1: 理解论文内容
- 阅读论文源文件，提取核心概念、方法、数据流
- 识别需要配图的位置
- 理解数学符号和维度
Step 2: 配色方案选择
展示选项，等待用户确认后再生成：
| # | 方案名 | Token 色 | 文字强调色 |
|---|---|---|---|
| P1 | Warm ML | 粉 #FFD0D0 · 蓝 #BBDEFB · 黄 #FFF3C4 · 紫 #E1BEE7 · 绿 #C8E6C9 |
coral #E05555 · teal #1A9988 · purple #6A5ACD · green #3A8F3A |
| P2 | Cool Research | 蓝 #B3E5FC · 靛 #C5CAE9 · 灰蓝 #CFD8DC · 青 #B2DFDB · 薰衣草 #D1C4E9 |
navy #1565C0 · indigo #3949AB · teal #00897B |
| P3 | Earthy Warm | 米 #FFE0B2 · 驼 #D7CCC8 · 灰绿 #C8E6C9 · 灰 #E0E0E0 · 浅棕 #EFEBE9 |
brown #6D4C41 · olive #827717 · forest #2E7D32 |
| P4 | 自定义 | 用户指定 | 用户指定 |
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.
- 13d ago First seen · 309 lines · 122 tokens per session scan A 9b26014aed7d
Academic Figure Prompt — Modern ML Airy Style is a skill published in the GitHub repository LigphiDonk/academic-figure-generator (2,309 stars, last pushed 5mo ago), licensed MIT. It adds 122 tokens to every session and 3,731 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…