paper-figures

3,516 curated Figure 1 / teasers from ICLR, ICML, NeurIPS, CVPR, ACL, AAAI (2023-2026), with tier badges and FigureForge retrieval-augmented figure drafting

An Automated AI Agent Tool for Plotting Your Data in Any Paper's Figure Style.

三个 skill 画论文图：fig-analyze 看材料，fig-draw 先看 6 种风格再出图。交付后询问要不要做成可编辑 PPT，同意后 fig-pptx 才做。npx skills add Azhi-ss/academic-figure-skills

Codex skill that turns paper text into editable draw.io academic figures: drafts a visual reference with image_gen, then rebuilds it as native .drawio XML with editable labels, shapes, arrows, and icons.

Agent skill for turning weekly research into editable PowerPoint, Manim method-explainer videos with narration/subtitles, and publication-quality draw.io figures.

PyTorch model architecture diagram generator: neural network diagram, SVG, PNG, TikZ, LaTeX

Publication-grade pipeline, framework and teaser figures for AI conference papers — natively editable in Visio and PowerPoint. A Claude Code / Codex skill with a measured house style, 11 archetypes and an anti-AI-slop auditor.

The last mile of the academic figure toolchain — a Claude Code skill that draws editable, paper-exact vector figures directly in Figma via MCP. 学术绘图工具链的最后一公里

AgInTi LabCanvas: agentic studio for editable scientific figures, CAD devices, and experiment design.

研图 Figure Atlas：289 张经典深度学习论文原图（附原文图注、出处与许可）与 28,102 个开源科研图标，中英文检索、改色下载。Original figures from 227 papers + research icons from 10 open-source packs.

Publication-quality, hierarchical figures of model architectures & training methods — an agent reads the code, then draws the figures

An agentic skill framework to generate publication-ready academic diagrams from methodology text. Open source implementation of Google PaperBanana (arXiv:2601.23265).

Visual, constraint-based layout designer for Matplotlib figures.

Agent Skill for turning papers or reference figures into editable PowerPoint diagrams with reusable assets and visual verification.

Bilingual SCI paper plotting skill with Matplotlib templates for publication-ready figures, nonlinear dynamics, and machine learning

爬文章图片专用，分成一个skill更稳定。Extract real figures from scientific papers with strict provenance and non-hallucination guarantees.

Paper-grounded research framework figures with human checkpoints, source-traceable examples, and regression tests.

Bilingual mathematical-modeling plot skill with 100 native Matplotlib notebooks, datasets, and paper-ready examples

Agent-native, evidence-grounded, editable scientific figure engineering for top-tier papers.

Recreate paper figures as fully editable PowerPoint (.pptx) using python-pptx, with a hybrid chroma-key mode for cartoons. Ships with a Cursor Skill.