English | 中文
Turn academic papers into polished method figures, visual slide decks, and in-depth articles — zero config, one command.
From arxiv link to publication-ready visuals, AIGC slide decks, and deep-dive articles.
Drop a paper, pick a style, get output that looks like a human expert made it.
Copy this into Codex or Claude Code:
Please install zsyggg/paper-craft-skills for me.
GitHub: https://github.com/zsyggg/paper-craft-skills
That's it. The agent handles clone, symlink, and registration. No API keys. No accounts. If you prefer a terminal:
npx skills add zsyggg/paper-craft-skillsWorks with: Codex · Claude Code · Cursor · Windsurf
|
Paper → Method Figures
Reads your paper → proposes what to draw → you confirm → generates.
|
Paper → Deep Articles
Reads the full paper → searches GitHub for code → writes in your chosen style.
|
||||||||||||||||
|
Paper → Visual Slide Deck
Reads your paper → plans the deck → generates slide images → exports PPTX/PDF.
|
paper-deck turns a paper, article, or technical note into a designed slide deck. It first builds a deck brief and slide-by-slide outline, then writes reproducible visual prompts, generates polished 16:9 slide images, and merges them into .pptx and .pdf.
It is built for iteration: every page has its own prompt, so you can ask for precise changes like “make slide 5 more journal-like”, “replace slide 8 with a real benchmark chart”, or “keep the layout but switch the cover to liquid glass”.
Four compact style presets for the same paper topic
| Style | Best for |
|---|---|
| journal-minimal | Nature/IEEE-inspired academic decks and thesis defenses |
| business-research | Strategy memos, industry research, investor/client briefings |
| warm-notes | Study-note explanations, teaching, approachable paper walkthroughs |
| liquid-glass | Apple-inspired visual chapters, covers, and high-impact section pages |
It also supports real source visuals. When a PDF contains strong figures, tables, plots, or screenshots, the skill plans which slides should use them, where they should be cropped, and how they should be framed. Real visuals can be mounted into clean academic panels, evidence blocks, or glass-style layouts instead of being hallucinated from scratch.
/paper-deck https://arxiv.org/abs/1706.03762
/paper-deck /path/to/paper.pdf --style journal-minimal --slides 12
/paper-deck notes.md --style liquid-glass/paper-comic https://arxiv.org/abs/1706.03762
Reads the paper, then recommends:
I suggest 6 figures:
1. Cover: one-line contribution + visual anchor
2. Transformer architecture overview
3. Self-attention mechanism
4. Multi-head attention detail
5. Encoder / Decoder Block
6. Key results
Or generate only 1 overview figure, or expand to 8 detailed mechanism figures.
Language? [Chinese / English] Style? [sketchnote / paper-figure] Scope and count?
paper-figure — clean, publication-grade
sketchnote — bright, warm, approachable
Full walkthrough: examples/paper-illustrated/attention-is-all-you-need
Not a paper translator — a re-interpreter. It reads the full paper, searches GitHub for open-source implementations, cross-references code with the paper, and writes in your chosen style.
| Style | Reads like | Use it for |
|---|---|---|
| storytelling | A viral blog post — hooks, analogies, golden takeaway | WeChat, Twitter, blogs |
| academic | A peer-reviewed deep dive — KaTeX formulas, comparison tables | Lab meetings, lit reviews |
| concise | A cheat sheet — Mermaid diagram + key data table | Quick understanding |
 Formula Explanation Extracted paper formulas with symbol-by-symbol breakdown |
 Code Analysis Aligns paper concepts with the GitHub source code |
/paper-analyzer https://arxiv.org/abs/1706.03762 # arxiv link
/paper-analyzer /path/to/paper.pdf # local PDF
/paper-analyzer # then paste textMIT