Literature PDF OCR Library Builder
LigphiDonk/Oh-my--paper
Searches and downloads legally accessible academic PDFs, OCRs them to Markdown, and organizes the results into a traceable, AI-readable literature library.
Creates a source-grounded Chinese-English reader for a research paper, with aligned text, figures, tables and equations, or answers questions about a given passage.
Install Bilingual Paper Reader
$ npx skills add Yuan1z0825/nature-skills --skill nature-reader -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Yuan1z0825/nature-skills nature-reader --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Yuan1z0825/nature-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/nature-reader .claude/skills/nature-reader && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "nature-reader" agent skill from https://github.com/Yuan1z0825/nature-skills/tree/main/skills/nature-reader into .claude/skills/nature-reader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nature-reader", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Yuan1z0825/nature-skills/tree/main/skills/nature-readerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Yuan1z0825/nature-skills --skill nature-reader -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Yuan1z0825/nature-skills nature-reader --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Yuan1z0825/nature-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/nature-reader .agents/skills/nature-reader && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "nature-reader" agent skill from https://github.com/Yuan1z0825/nature-skills/tree/main/skills/nature-reader into .agents/skills/nature-reader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nature-reader", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Yuan1z0825/nature-skills --skill nature-reader -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Yuan1z0825/nature-skills nature-reader --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Yuan1z0825/nature-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/nature-reader .cursor/skills/nature-reader && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "nature-reader" agent skill from https://github.com/Yuan1z0825/nature-skills/tree/main/skills/nature-reader into .cursor/skills/nature-reader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nature-reader", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Yuan1z0825/nature-skills.git --path skills/nature-reader--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Yuan1z0825/nature-skills --skill nature-reader -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Yuan1z0825/nature-skills nature-reader --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Yuan1z0825/nature-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/nature-reader .gemini/skills/nature-reader && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "nature-reader" agent skill from https://github.com/Yuan1z0825/nature-skills/tree/main/skills/nature-reader into .gemini/skills/nature-reader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nature-reader", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Yuan1z0825/nature-skills nature-readerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Yuan1z0825/nature-skills --skill nature-reader -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Yuan1z0825/nature-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/nature-reader .github/skills/nature-reader && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "nature-reader" agent skill from https://github.com/Yuan1z0825/nature-skills/tree/main/skills/nature-reader into .github/skills/nature-reader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nature-reader", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Yuan1z0825/nature-skills --skill nature-reader -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Yuan1z0825/nature-skills nature-reader --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Yuan1z0825/nature-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/nature-reader .opencode/skills/nature-reader && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "nature-reader" agent skill from https://github.com/Yuan1z0825/nature-skills/tree/main/skills/nature-reader into .opencode/skills/nature-reader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nature-reader", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
nature-reader- GitHub stars
- 47k
- Token cost
- ~961 tokens
- SKILL.md length
- 462 words
- Files
- 22 (incl. scripts, references)
- Skills in repo
- 23
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Creates a source-grounded Chinese-English reader for a research paper, with aligned text, figures, tables and equations, or answers questions about a given passage.
- Works in 5 steps: Load the manifest and the core layer → Detect the source format → Load the matching fragment(s) → …
- Producing a full bilingual reading copy of a journal article
- Runs Python scripts from its folder
- Translating a single section or excerpt of a paper with source links
What it does
Before building anything, it decides what you are asking for: a full reader, an answer to a source-linked question, or the translation of one excerpt. Questions and excerpts get only the relevant source material and grounding rules, with no full reader built. A request for a reader or a full-paper translation follows a manifest-driven workflow.
It reads manifest.yaml, loads the core principles, workflow and output contract, and detects the source format: selectable-text PDF (the default), scanned PDF, publisher or preprint HTML, a bare DOI or arXiv link, or pasted text. It states the detected format in one line so you can correct it, and then loads only the matching fragment.
Core principles call for a bilingual reader that translates for meaning rather than summarizing, with caution around copyright. Reference files cover article structure, equations, figure extraction, grounding rules and the output spec, and scripts/validate_reader_math.py ships alongside them. A six-step workflow builds a source map first.
When your agent uses it
- Producing a full bilingual reading copy of a journal article
- Translating a single section or excerpt of a paper with source links
- Asking a question about a paper and getting an answer tied to the original text
- Working from a DOI or arXiv link, a scanned PDF or pasted text
Example prompts
- “Make a Chinese-English reader for the attached PDF, keeping figures and equations aligned.”
- “Translate just the methods section of this paper and link it back to the source.”
- “Where in this paper do the authors discuss limitations? Point me to the source passages.”
- “Resolve this arXiv link and build a reader from it.”
Requirements
- A paper as a PDF, HTML page, DOI or arXiv link, or pasted text
- Python to run the bundled validation script
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 163c497. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python, from the files we listed), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Bilingual Paper Reader loads about 961 tokens when it runs, and up to ~5.4k if it reads all its reference files. Until then it costs about 64 tokens; SKILL.md has 462 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from Yuan1z0825/nature-skills at commit 163c497, republished under its Apache-2.0 licence (© Yuan1z0825). 462 words, ~961 tokens.
Download SKILL.mdSave it as
.claude/skills/nature-reader/SKILL.md (or your agent's skills folder). This skill also uses 21 other files; get the full folder from GitHub.- name
- nature-reader
- 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.
- metadata.version
- 2.1.1
- metadata.author
- Community contribution, refactored into static/dynamic layers
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. 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.
Show full SKILL.md (192 more words)Show less
3. Load the matching fragment(s)
Read the file mapped for the detected source_format. Do not read every fragment in static/. Load only what step 2 selected.
4. Build the reader using the loaded material
Apply the loaded fragments in this priority order:
- Core principles (
core/principles.md) — bilingual reader by default, translate for meaning, never degrade to a summary, copyright caution. - Source-format fragment — how to extract text, figures, and tables for this input.
- Reading workflow (
core/workflow.md) — the six-step source-map-first process. - Output contract (
core/output-contract.md) — required files and the pre-response verification checklist.
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.
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.
5. Reach for references only when needed
The files under references/ are deep references, not defaults. Open them on demand per the references.on_demand table in the manifest:
- detailed figure/table cropping and placement →
references/figure-extraction.md. - exact field schema for
paper.md/source_map.json→references/output-spec.md. - equations, mathematical expressions, chemical formulae, or image-only formulae →
references/equation-handling.md. - answering follow-up questions with source citations →
references/grounding-rules.md.
© Yuan1z0825, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 21 other files (scripts, references) in skills/nature-reader of Yuan1z0825/nature-skills.
- SKILL.md
- 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
- … and 7 more
Open the folder on GitHubat commit 163c497
Compare with similar skills
Bilingual Paper Reader next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Bilingual Paper Reader this skillYuan1z0825/nature-skills | 47k | — | ~961 | Automated safety check: Pass | Apache-2.0 | |
| Literature PDF OCR Library BuilderLigphiDonk/Oh-my--paper | 739 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Paper Figure Extractorjuliye2025/evil-read-arxiv | 1.7k | — | ~298 | Automated safety check: Pass | None | |
| Daily Paper DigestGalaxy-Dawn/claude-scholar | 5.7k | — | ~1k | Automated safety check: Pass | MIT | |
| Paper AnalyzerLigphiDonk/Oh-my--paper | 739 | 1 repos | ~973 | Automated safety check: Pass | MIT | |
| Nature Readeraiskillstore/marketplace | 433 | 1 repos | ~1.1k | Automated safety check: Pass | None |
Similar skills
Paper Figure Extractor
juliye2025/evil-read-arxiv
Pulls architecture, method and result figures from an arXiv paper or PDF into an Obsidian vault and writes an index of them.
Daily Paper Digest
Galaxy-Dawn/claude-scholar
Finds recent arXiv and bioRxiv papers on a topic, narrows them in stages to one pick per field, and writes bilingual Chinese and English summaries.
Paper Analyzer
LigphiDonk/Oh-my--paper
Analyzes one research paper in depth, writing a structured note on its methods, experiments and limitations and adding it to a paper relationship graph.
Nature Reader
aiskillstore/marketplace
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.
Literature Review
neflibata-feng/MyArxiv-Agent
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.).
More from Yuan1z0825/nature-skills
All 23 skills in this repoNature Paper Card
Yuan1z0825/nature-skills
Builds a structured deep-reading card for one scientific paper, covering methods, how experiments support claims, limitations and research ideas, with a script to prepare the source.
Nature-Style Scientific Figures
Yuan1z0825/nature-skills
Creates, revises, audits and exports manuscript-ready scientific figures in Python or R, and routes AI-generated graphical abstracts to a separate workflow.
Paper to Chinese Patent Drafter
Yuan1z0825/nature-skills
Drafts Chinese invention patent applications and technical disclosures from research papers or inventor materials, tying each claim feature to source evidence.
Researchwrite Proposal Pipeline
Yuan1z0825/nature-skills
Composes, revises or audits research proposals and opening reports through an evidence-first state machine with argument maps, section contracts and dynamic expert reviewers.
Nature Literature Downloader
Yuan1z0825/nature-skills
Routes literature requests to lawful full-text sources: open access, publisher APIs, CNKI and institutional browser access, with a supporting-information gate.
Image to Editable PPTX
Yuan1z0825/nature-skills
Rebuilds slide images, screenshots, scanned PDFs or image-only PPTX files as PowerPoint with editable objects, using a local CLI with per-page manifests and QA.
Related
Works with
Categories
Questions about Bilingual Paper Reader
What does Bilingual Paper Reader do?
Creates a source-grounded Chinese-English reader for a research paper, with aligned text, figures, tables and equations, or answers questions about a given passage. Before building anything, it decides what you are asking for: a full reader, an answer to a source-linked question, or the translation of one excerpt. Questions and excerpts get only the relevant source material and grounding rules, with no full reader built.
When should I use Bilingual Paper Reader?
Bilingual Paper Reader fits situations like: producing a full bilingual reading copy of a journal article; translating a single section or excerpt of a paper with source links; asking a question about a paper and getting an answer tied to the original text; working from a DOI or arXiv link, a scanned PDF or pasted text.
How do I install Bilingual Paper Reader in Claude Code?
Run `npx skills add Yuan1z0825/nature-skills --skill nature-reader -a claude-code`. Or copy the skill folder (skills/nature-reader in Yuan1z0825/nature-skills) into .claude/skills/nature-reader in your project. Claude Code loads it when a task matches its description.
How do I install Bilingual Paper Reader in Codex?
Run `npx skills add Yuan1z0825/nature-skills --skill nature-reader -a codex`. Or copy the skill folder (skills/nature-reader in Yuan1z0825/nature-skills) into .agents/skills/nature-reader in your project. Codex loads it when a task matches its description.
Can I use Bilingual Paper Reader in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Yuan1z0825/nature-skills --skill nature-reader -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nature-reader, .gemini/skills/nature-reader, .github/skills/nature-reader and .opencode/skills/nature-reader in your project.
What does Bilingual Paper Reader need to run?
Going by SKILL.md and its folder, Bilingual Paper Reader needs Python for the scripts in its folder. Our summary lists: A paper as a PDF, HTML page, DOI or arXiv link, or pasted text; Python to run the bundled validation script.
Does Bilingual Paper Reader access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Bilingual Paper Reader safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Bilingual Paper Reader use?
Bilingual Paper Reader is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Bilingual Paper Reader use?
About 961 tokens (SKILL.md is roughly 3.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.5k tokens, read only when the agent opens those files.
What are the alternatives to Bilingual Paper Reader?
Skills that share tags, products or a category with Bilingual Paper Reader: Literature PDF OCR Library Builder (LigphiDonk/Oh-my--paper, 739 stars), Paper Figure Extractor (juliye2025/evil-read-arxiv, 1.7k stars), Daily Paper Digest (Galaxy-Dawn/claude-scholar, 5.7k stars) and Paper Analyzer (LigphiDonk/Oh-my--paper, 739 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Bilingual Paper Reader?
Yuan1z0825 (a GitHub user) maintains it in Yuan1z0825/nature-skills, which has 47,016 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on October 10, 2026.
Source: Yuan1z0825/nature-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.