# Nature Reader

Create source-grounded Chinese-English paper readers with aligned text, figures...

- Repository: https://github.com/Yuan1z0825/nature-skills (51695 stars)
- Category: Engineering
- License: Apache-2.0
- Last updated: 2026-11-01
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add Yuan1z0825/nature-skills --skill nature-reader -g -a claude-code -y`
Codex: `npx skills add Yuan1z0825/nature-skills --skill nature-reader -g -a codex -y`
Cursor: `npx skills add Yuan1z0825/nature-skills --skill nature-reader -g -a cursor -y`
Gemini CLI: `npx skills add Yuan1z0825/nature-skills --skill nature-reader -g -a gemini-cli -y`

## Description

Create source-grounded Chinese-English paper readers with aligned text, figures, tables, and equations. Use for 全文翻译、中英文对照、论文精读 or source-linked questions about a paper; respect a requested excerpt or question without generating a full reader.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Full-Paper Markdown Reader, Router

## Routing protocol

First distinguish creating a reader from answering a question or translating an excerpt.
For a source-linked question, read `references/grounding-rules.md` and inspect only the relevant
source material; reuse existing source-map IDs when available. Do not regenerate the reader or
require a full source map before answering. For an explicit excerpt request, apply extraction,
translation, and grounding rules to that excerpt. The full-artifact workflow below applies when
the user requests a reader or full-paper translation.

For a new task, load the core and matching resources below. Reuse already loaded guidance on follow-ups; load more only when the task needs it.

### 1. Load the manifest and the core layer

Read [manifest.yaml](manifest.yaml). It declares the `source_format` axis, the allowed values, and the file paths each value maps to.

Also read every file listed under `always_load`. These hold the core principles, the reading workflow, and the output contract that apply to every reading job, plus the shared Terminology Ledger used to build the recurring-term table.

### 2. Detect the source format

Decide the `source_format` value using the manifest's `detect:` hint and the user's input:

- `pdf-text`, selectable-text PDF. Default.
- `scanned-pdf`, image-only or OCR-required PDF.
- `html`, publisher or preprint HTML page.
- `doi-arxiv`, a bare DOI or arXiv link that must be resolved first.
- `pasted-text`, pasted prose or notes with no retrievable original layout.

State the detected value in one short line to the user before processing, so they can correct you cheaply. A source may map to more than one value (for example a DOI that resolves to a PDF); load the resolution fragment first, then the fragment for the resolved artifact.

### 3. Load the matching fragment(s)

The rest: https://github.com/Yuan1z0825/nature-skills/blob/HEAD/skills/nature-reader/SKILL.md