nature-reader
A skill from the nature-skills collection that turns a scientific paper into a Chinese-English reading package, with the original and a meaning-based translation aligned paragraph by paragraph alongside figures, tables and equations.
What the skill teaches
A skill from the nature-skills collection that turns a scientific paper into a Chinese-English reading package, with the original and a meaning-based translation aligned paragraph by paragraph alongside figures, tables and equations. It works from a text PDF, a scanned PDF, a publisher or preprint web page, a DOI or arXiv link, or pasted text, states the format it detected so the user can correct it, and loads only the matching instructions. Output is a bilingual Markdown reader with a term table, a source map with a glossary, figure and table crops, and notes on gaps or uncertain crops. It answers a question with cited passages or translates an excerpt without building a full reader, and never falls back to a summary.
Capabilities
- Build an aligned Chinese-English paper reader
- Crop figures and tables beside the text
- Answer questions about a paper with cited passages
- Read PDFs, web pages, DOIs and arXiv links
About
- Publisher
- yuan1z0825
- Tool
- Research
Install
The project doesn't document install steps that we could confirm. See the project's own instructions
What's inside
- README.md
- README_EN.md
- agents/openai.yaml
- evals/evals.json
- manifest.yaml
- references/article-anatomy.md
- references/equation-handling.md
- references/figure-extraction.md
- references/grounding-rules.md
- references/output-spec.md
- scripts/validate_reader_math.py
- static/core/output-contract.md
- static/core/principles.md
- static/core/workflow.md
- static/fragments/source/doi-arxiv.md
- static/fragments/source/html.md
- static/fragments/source/pasted-text.md
- static/fragments/source/pdf-text.md
- static/fragments/source/scanned-pdf.md
MCP servers and skills can run code on your computer and act on your data. Review the source before installing.
Details
| Fact | Value | Source |
|---|---|---|
| Type | Skill | |
| Tool | Research | |
| Publisher | yuan1z0825 | source |
| Official status | Not stated in its documentation | |
| Needs an API key or sign-in | Not stated in its documentation | |
| Includes scripts | No | source |
| Platforms | Not stated in its documentation | |
| AI clients | Not stated in its documentation | |
| Licence | Apache-2.0 | source |
| Pricing | Not stated in its documentation | |
| Activity | Last commit Nov 10, 202653,164 GitHub starsDownload data not available (not on npm or PyPI) | source |
| Links | Repository |
More from yuan1z0825
20 skills
- nature-paper2word (Skill)
- nature-experiment-log (Skill)
- nature-figure (Skill)
- nature-literature-pipeline (Skill)
- nature-polishing (Skill)
- nature-ref-verifier (Skill)
Also listed under: Research
Sources
- Skill file (SKILL.md)github.com/yuan1z0825/nature-skillsNov 16, 2026
- GitHub repositorygithub.com/yuan1z0825/nature-skills · Backs: Licence, Publisher, ActivityNov 11, 2026
- Skill file (SKILL.md)github.com/Yuan1z0825/nature-skillsNov 10, 2026
- Folder in the repository (nature-reader)github.com/Yuan1z0825/nature-skills · Backs: Includes scriptsNov 10, 2026