Implement Paper Auto
This one takes a research paper URL and builds a complete marimo notebook implementation without asking you for input. It pulls structured paper content from AlphaXiv, then makes its own call on what concept to showcase. The real philosophy here is storytelling over completeness. Instead of trying to replicate every benchmark, it picks one core idea and builds a minimal, runnable example with a chart or two and maybe some interactive controls. No toy datasets, no endless scrolling. It's opinionated about hiding code by default and surfacing the interactive bits first. Useful when you want to quickly explore a paper's key insight rather than read through pages of methodology.
- skills.sh installs
- 2.3K
- GitHub stars
- 177
- last updated
- Aug 21, 2026
Install
$ npx -y skills add marimo-team/skills --skill implement-paper-auto --agent claude-codeInstalls into .claude/skills of the current project.
Files
You need to come up with a compelling story to tell from a paper. Do not ask the user for feedback/input. You need to apply thinking and come up with the best story yourself.
Fetching Papers via AlphaXiv
Use alphaxiv.org to get structured, LLM-friendly paper content. This is faster and more reliable than trying to read a raw PDF.
Extract the paper ID
Parse the paper ID from whatever the user provides:
| Input | Paper ID |
|---|---|
https://arxiv.org/abs/2401.12345 | 2401.12345 |
https://arxiv.org/pdf/2401.12345 | 2401.12345 |
https://alphaxiv.org/overview/2401.12345 | 2401.12345 |
2401.12345v2 | 2401.12345v2 |
2401.12345 | 2401.12345 |
Fetch the AI-generated overview (try this first)
curl -s "https://alphaxiv.org/overview/{PAPER_ID}.md"
Returns a structured, detailed analysis of the paper as plain markdown. One call, no JSON parsing.
Fetch the full paper text (fallback)
If the overview doesn't contain the specific detail you need (e.g., a particular equation, table, or proof):
curl -s "https://alphaxiv.org/abs/{PAPER_ID}.md"
Returns the full extracted text of the paper as markdown.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/marimo-team/skills
- Category
- Data Science & ML
- First seen
- May 16, 2026
More from marimo-team/skills
All 10Recommended
More Data Science & ML
latex-formattinglingzhi227/agent-research-skillsHandle LaTeX formatting, templates, and styling for academic papers. Set up conference templates (ICML, ICLR, NeurIPS, AAAI, ACL), fix formatting issues, manage2.3Kskills.sh installsmath-reasoninglingzhi227/agent-research-skillsFormal mathematical reasoning for research papers — derive equations, write proofs, formalize problem settings, select statistical tests, and generate LaTeX mat2.2Kskills.sh installs
seabornk-dense-ai/scientific-agent-skillsStatistical visualization with pandas integration. Use for quick exploration of distributions, relationships, and categorical comparisons with attractive defaul2.2Kskills.sh installs
auto-paper-demomarimo-team/skillsMake a demo of a research paper in a marimo notebook fully automatically without extra user input.2.2Kskills.sh installs
transformers-jshuggingface/skillsUse Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summariza2.2Kskills.sh installspolarsk-dense-ai/scientific-agent-skillsHigh-performance DataFrame library for Python ETL, analytics, and pandas migration. Use for expression-based data manipulation with lazy query optimization, par2.2Kskills.sh installs