nature-reader

Name: nature-reader
Author: Yuan1z0825

3.5kinstalls1.8kforks

How to install nature-reader?

yuan1z0825/nature-skills/nature-reader

$npx -y skills add Yuan1z0825/nature-skills --skill nature-reader

Installs into the current project.

Summary

Build full-paper Chinese-English side-by-side, figure/table-aware, source-grounded Markdown readers for journal or conference papers from PDF, DOI, arXiv, publisher HTML, or pasted text. Use whenever the user asks to translate or read a paper, make 中英文对照/原文对照/全文翻译解读, extract figu

Files · 1

View on GitHub

SKILL.md

1	# Full-Paper Markdown Reader — Router
2
3	This skill is split into two layers:
4
5	- A static layer under `static/` that holds versioned, reusable content fragments (core principles, the reading workflow, the output contract, and per-source-format extraction guidance).
6	- A dynamic layer (this file plus `manifest.yaml`) that detects the request's source format and loads only the fragments needed for the current job.
7
8	Do not try to apply the reading logic from memory or from this router. Always load fragments from disk as described below.
9
10	## Routing protocol
11
12	Follow these five steps every time the skill is invoked.
13
14	### 1. Load the manifest and the core layer
15
16	Read [manifest.yaml](manifest.yaml). It declares the `source_format` axis, the allowed values, and the file paths each value maps to.
17
18	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.
19
20	### 2. Detect the source format
21
22	Decide the `source_format` value using the manifest's `detect:` hint and the user's input:
23
24	- `pdf-text` — selectable-text PDF. Default.
25	- `scanned-pdf` — image-only or OCR-required PDF.
26	- `html` — publisher or preprint HTML page.
27	- `doi-arxiv` — a bare DOI or arXiv link that must be resolved first.
28	- `pasted-text` — pasted prose or notes with no retrievable original layout.
29
30	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.
31
32	### 3. Load the matching fragment(s)
33
34	Read the file mapped for the detected `source_format`. Do not read every fragment in `static/`. Load only what step 2 selected.
35
36	### 4. Build the reader using the loaded material
37
38	Apply the loaded fragments in this priority order:
39
40	1. Core principles (`core/principles.md`) — bilingual reader by default, translate for meaning, never degrade to a summary, copyright caution.
41	2. Source-format fragment — how to extract text, figures, and tables for this input.
42	3. Reading workflow (`core/workflow.md`) — the six-step source-map-first process.
43	4. Output contract (`core/output-contract.md`) — required files and the pre-response verification checklist.
44
45	Build the Terminology Ledger as you translate (`../nature-shared/core/terminology-ledger.md`); it becomes the `paper.md` recurring-term table and the `source_map.json` glossary.
46
47	If constraints prevent full processing, still create a draft reader and label missing pages, figures, or low-confidence crops in `translation_notes.md`. Do not switch to summary mode.
48
49	### 5. Reach for references only when needed
50
51	The files under `references/` are deep references, not defaults. Open them on demand per the `references.on_demand` table in the manifest:
52
53	- detailed figure/table cropping and placement → `references/figure-extraction.md`.
54	- exact field schema for `paper.md` / `source_map.json` → `references/output-spec.md`.
55	- answering follow-up questions with source citations → `references/grounding-rules.md`.
56
57	## Why this split
58
59	- The static layer is versioned and reviewable. Adding a new source format is one new fragment plus one manifest line.
60	- The dynamic layer keeps each invocation cheap: only the fragment relevant to this input enters context.
61	- The router itself is short on purpose. Update fragments, not this file, when adding scope.
62	- This structure mirrors `nature-writing` and `nature-polishing` so shared content lives in `nature-shared/`.

People who liked this also viewed

6 picks

Type

nature-reader

3.5kinstalls1.8kforks

View on GitHub

How to install nature-reader?

yuan1z0825/nature-skills/nature-reader

$npx -y skills add Yuan1z0825/nature-skills --skill nature-reader

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Full-Paper Markdown Reader — Router
2
3	This skill is split into two layers:
4
5	- A static layer under `static/` that holds versioned, reusable content fragments (core principles, the reading workflow, the output contract, and per-source-format extraction guidance).
6	- A dynamic layer (this file plus `manifest.yaml`) that detects the request's source format and loads only the fragments needed for the current job.
7
8	Do not try to apply the reading logic from memory or from this router. Always load fragments from disk as described below.
9
10	## Routing protocol
11
12	Follow these five steps every time the skill is invoked.
13
14	### 1. Load the manifest and the core layer
15
16	Read [manifest.yaml](manifest.yaml). It declares the `source_format` axis, the allowed values, and the file paths each value maps to.
17
18	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.
19
20	### 2. Detect the source format
21
22	Decide the `source_format` value using the manifest's `detect:` hint and the user's input:
23
24	- `pdf-text` — selectable-text PDF. Default.
25	- `scanned-pdf` — image-only or OCR-required PDF.
26	- `html` — publisher or preprint HTML page.
27	- `doi-arxiv` — a bare DOI or arXiv link that must be resolved first.
28	- `pasted-text` — pasted prose or notes with no retrievable original layout.
29
30	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.
31
32	### 3. Load the matching fragment(s)
33
34	Read the file mapped for the detected `source_format`. Do not read every fragment in `static/`. Load only what step 2 selected.
35
36	### 4. Build the reader using the loaded material
37
38	Apply the loaded fragments in this priority order:
39
40	1. Core principles (`core/principles.md`) — bilingual reader by default, translate for meaning, never degrade to a summary, copyright caution.
41	2. Source-format fragment — how to extract text, figures, and tables for this input.
42	3. Reading workflow (`core/workflow.md`) — the six-step source-map-first process.
43	4. Output contract (`core/output-contract.md`) — required files and the pre-response verification checklist.
44
45	Build the Terminology Ledger as you translate (`../nature-shared/core/terminology-ledger.md`); it becomes the `paper.md` recurring-term table and the `source_map.json` glossary.
46
47	If constraints prevent full processing, still create a draft reader and label missing pages, figures, or low-confidence crops in `translation_notes.md`. Do not switch to summary mode.
48
49	### 5. Reach for references only when needed
50
51	The files under `references/` are deep references, not defaults. Open them on demand per the `references.on_demand` table in the manifest:
52
53	- detailed figure/table cropping and placement → `references/figure-extraction.md`.
54	- exact field schema for `paper.md` / `source_map.json` → `references/output-spec.md`.
55	- answering follow-up questions with source citations → `references/grounding-rules.md`.
56
57	## Why this split
58
59	- The static layer is versioned and reviewable. Adding a new source format is one new fragment plus one manifest line.
60	- The dynamic layer keeps each invocation cheap: only the fragment relevant to this input enters context.
61	- The router itself is short on purpose. Update fragments, not this file, when adding scope.
62	- This structure mirrors `nature-writing` and `nature-polishing` so shared content lives in `nature-shared/`.

People who liked this also viewed

6 picks

Type