跳转到主要内容
此内容尚未提供您的语言版本,正在以英文显示。

AlterLab Scientific Schematics

技能 活跃

Part of the AlterLab Academic Skills suite. Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.1 Pro Preview 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 complex scientific visualizations.

目的

To enable users to effortlessly create high-quality, publication-ready scientific diagrams using advanced AI, eliminating the need for manual drawing or complex tools.

功能

  • AI-powered diagram generation via natural language
  • Iterative refinement with quality review
  • Specialized quality thresholds for document types
  • Support for various scientific diagram types
  • Automatic output optimization for publication

使用场景

  • Creating neural network architecture diagrams for papers
  • Illustrating system architectures and data flow
  • Visualizing complex biological pathways or signaling cascades
  • Generating methodology flowcharts for study designs
  • Producing diagrams for presentations, posters, and theses

非目标

  • Manual diagram editing or drawing
  • Generating diagrams for non-scientific purposes
  • Providing a vector graphics editing suite
  • Creating diagrams without AI assistance

工作流

  1. User provides a natural language description of the desired diagram.
  2. The skill constructs a detailed prompt including scientific diagram guidelines.
  3. Nano Banana 2 AI generates an initial image.
  4. Gemini 3.1 Pro Preview reviews the image against quality thresholds.
  5. If quality is below threshold, the prompt is improved based on critique, and regeneration occurs (up to max iterations).
  6. The final, highest-quality image is saved along with a review log.

实践

  • AI-driven content generation
  • Iterative refinement workflows
  • Quality assurance via AI review

先决条件

  • OPENROUTER_API_KEY environment variable set
  • Python 3.10+ and pip
  • requests library installed

Maintenance

  • warning:Dependency ManagementThe script relies on the 'requests' library, but there's no explicit mention of lockfiles or dependency update mechanisms like dependabot.

Execution

  • warning:Pinned dependenciesThe script requires the 'requests' library, but it is not pinned via a lockfile, nor is the interpreter explicitly pinned with side-effect headers.

安装

npx skills add AlterLab-IEU/AlterLab-Academic-Skills

通过 npx 运行 Vercel skills CLI(skills.sh)— 需要本地安装 Node.js,以及至少一个兼容 skills 的智能体(Claude Code、Cursor、Codex 等)。前提是仓库遵循 agentskills.io 格式。

质量评分

93 /100
1 day ago 分析

信任信号

最近提交17 days ago
GitHub 所有者 AlterLab-IEU (opens in new tab)
星标15
下载量 0 (opens in new tab)
许可证MIT
状态
查看源代码

类似扩展

Scientific Schematics

98

Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.1 Pro Preview 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 complex scientific visualizations.

技能
K-Dense-AI

Baoyu Diagram

98

Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system, process flow, data flow, component relationship, network topology, decision tree, org chart, state machine, or any visual representation of structure/logic/process. Also trigger when the user says "画个图" "画一个架构图" "diagram" "flowchart" "sequence diagram" "draw me a ..." or uploads content and asks to visualize it. Output is always a standalone .svg file.

技能
jimliu

Trader Regime

100

Detect current market regime using npx neural-trader — bull/bear/ranging/volatile classification with recommended strategy

技能
ruvnet

Trading Memory

100

AI交易记忆的领域知识 — 结果加权记忆 (OWM) 架构、5种记忆类型、回忆评分和行为分析。用于记录交易、回忆相似的上下文、分析性能或检查行为漂移。在 "record trade"、"remember trade"、"recall"、"similar trades"、"performance"、"behavioral"、"disposition"、"affective state"、"confidence" 时触发。

技能
mnemox-ai

TradeMemory Protocol

100

Evolution Engine 的领域知识 — 支持 LLM 从原始 OHLCV 数据中自主发现策略。涵盖生成-回测-选择-进化循环、向量化回测、样本外验证和策略梯度。在发现交易模式、运行回测、进化策略或审查进化日志时使用。由“evolve”、“discover patterns”、“backtest”、“evolution”、“strategy generation”、“candidate strategy”触发。

技能
mnemox-ai

Image Transformation API

100

Transform images with resize, crop, smart crop, upscale, remove background, and 20+ operations.

技能
iterationlayer