A router-based system that builds full-length Chinese-English side-by-side translations of academic papers from PDFs, DOIs, arXiv links, or HTML. Instead of holding all extraction logic in memory, it loads only the fragments it needs for your source format: one set of instructions for scanned PDFs, another for publisher HTML, and so on. The static layer is versioned, the dynamic layer stays light, and the output is always a complete bilingual Markdown document with figures and tables placed near the relevant text, never a summary unless you ask for one. Builds a terminology ledger as it translates so recurring terms stay consistent. Ships with source grounding rules for follow-up questions.

skills.sh installs
15.9K
GitHub stars
52.9K
last updated
Aug 21, 2026

Install

$ npx -y skills add yuan1z0825/nature-skills --skill nature-reader --agent claude-code

Installs into .claude/skills of the current project.

Files

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

Sponsors

Details

Repository
github.com/yuan1z0825/nature-skills
Categories
Frontend Development, DevOps & CI/CD, Data Science & ML, Automation & Workflows, Office & Documents
First seen
Jun 3, 2026

More from yuan1z0825/nature-skills

All 11
1vercel avatarbuilding-componentsvercel/components.buildGuide for building modern, accessible, and composable UI components. Use when building new components, implementing accessibility, creating composable APIs, set15.1Kskills.sh installs
2clerk avatarclerk-swiftclerk/skillsImplement Clerk authentication for native Swift and iOS apps using ClerkKit and ClerkKitUI source-guided patterns. Use for prebuilt AuthView or custom native fl15Kskills.sh installs
3fastapi avatarfastapifastapi/fastapiFastAPI best practices and conventions. Use when working with FastAPI APIs, Pydantic models, dependencies, streaming responses including Server-Sent Events (SSE14.9Kskills.sh installs
4clerk avatarclerk-androidclerk/skillsImplement Clerk authentication for native Android apps using Kotlin and Jetpack Compose with clerk-android source-guided patterns. Use for prebuilt AuthView/Use14.9Kskills.sh installs
5clerk avatarclerk-expoclerk/skillsAdd Clerk authentication to Expo and React Native apps using @clerk/expo. Use for Expo setup, prebuilt native components (AuthView, UserButton), custom sign-in/14.8Kskills.sh installs
6vuejs-ai avatarcreate-adaptable-composablevuejs-ai/skillsCreate a library-grade Vue composable that accepts maybe-reactive inputs (MaybeRef / MaybeRefOrGetter) so callers can pass a plain value, ref, or getter. Normal14.8Kskills.sh installs