What does this skill do, and when should you use it?
This skill provides a complete workflow for downloading academic papers, supporting open access (OA), publisher APIs (Elsevier, Springer Nature, IEEE), and institutional access (CNKI, Web Access). It emphasizes reusing the user's existing library login and Chrome session, without bypassing paywalls or DRM. The skill includes an SI confirmation gate, API-first with OA fallback logic, a status classification list, and a batch download script, ensuring compliant and auditable downloads. It is part of the nature-skills repository and requires Node.js 22+ and Python 3.
Reads input as DOI, title, or PDF URL, normalizes metadata, identifies language and publisher; Chinese literature routes to CNKI, English ones attempt publisher API first (if credentials configured), then automatically search OA sources (PMC, Unpaywall, arXiv, etc.) on failure, and fall back to institutional Web Access if OA is unavailable. Runs a batch script (batch_download.mjs) with SI/No-SI flags, generates manifest.json with route, OA status, and file verification details. Configures school and credentials via Python scripts, reuses authenticated Chrome via CDP, handles verification challenges (e.g., sliders, CAPTCHAs) up to a bounded number of attempts, and outputs PDFs/HTML/CAJ/SI to specified folders.
- A graduate student needs a PDF of a Chinese article from CNKI, leveraging their university's institutional subscription.
- A researcher wants legitimate full-text access to an Elsevier paper, using an API key, with automatic fallback to OA copies on failure.
- An academic wants to batch-download a list of DOIs with and without Supporting Information (SI) for a systematic review.
- A user without institutional access needs an OA paper; the skill fetches it from PMC or arXiv directly.
- When the user's institution lacks permission for a paper, the skill clearly reports no permission instead of retrying in vain.
How do you install this skill?
- The skill relies on the user's logged-in browser and CDP proxy; ensure the user explicitly consents and understands the scope of browser control to avoid overreach.
- Core functionality depends on overseas services (e.g., CNKI, Web of Science) that may not be directly accessible from mainland China or may require specific network setups; verify accessibility before use.
- API keys and login states are sensitive; follow documented secure storage and transmission requirements to avoid leakage.
- This static review did not execute actual tests; actual reliability, effectiveness, and security require further verification.
- Shell / CLI
- Network access
- Local filesystem
Node.js 22+Python 3Chrome CDP for CNKI/Web Access/SI routes
Install via npx: npx skills add Yuan1z0825/nature-skills --skill nature-downloader --agent codex --global --yes --copy. Alternatively, manually copy the skills/nature-downloader directory into ~/.claude/skills/ or ~/.codex/skills/. Ensure Node.js 22+ and Python 3 are available. After installation, configure the library resource URL (configure_school.py) and publisher API credentials (configure_credentials.py) as needed.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/Yuan1z0825/nature-skills.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/skills/nature-downloader" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Once installed, send your agent any of these to trigger it:
- Download the PDF for DOI 10.1007/s00122-021-03957-1, no SI.
Describe the task to your agent, e.g., “Download the PDF for DOI 10.1007/s00122-021-03957-1, no SI.” Or run the batch script directly: node scripts/batch_download.mjs --dois "10.1007/s00122-021-03957-1" --no-si --out "<project_dir>". On first use, configure your school's resource URL (python3 scripts/configure_school.py url "https://library.example.edu") and any needed API keys (python3 scripts/configure_credentials.py set elsevier). The skill will guide you through enabling browser remote debugging (chrome://inspect) to reuse your logged-in session.
What are this skill's strengths and limitations?
- Strictly follows legal download paths, avoiding paywall circumvention
- Supports multiple English publisher APIs and OA sources with automatic fallback
- Provides batch downloading and an audit trail for multi-paper workflows
- Reuses user login state to reduce repeated authentication
- Clear status categories for diagnosing download issues
- Requires Node.js 22+ and Python 3, with a non-trivial setup
- CNKI, Web Access, and SI downloads require Chrome remote debugging configuration, adding technical complexity
- No built-in school presets; users must provide their resource URL on first configuration
- No test suite or cross-platform validation explicitly mentioned
- Some publisher APIs require separate key registration and may have limited support
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Nature Literature Downloader this page | 59 · Recommended | ★ 47k | 3d ago | Apache-2.0 |
| Paper Search | 51 · Use with care | ★ 61 | 6mo ago | MIT |
| RAGAS RAG Quality Evaluator ✓ NVIDIA · Official | 45 · Not recommended | ★ 3.5k | 3d ago | Apache-2.0 |
| DICOM Series Preflight ✓ NVIDIA · Official | 60 · Recommended | ★ 3.5k | 3d ago | Apache-2.0 |
| DeepTutor XLSX Skill | 60 · Recommended | ★ 41k | 3d ago | Apache-2.0 |
Compared to nature-academic-search in the same repository, this skill focuses on downloading, while the former handles search and citation analysis; they can be used together, but this one's download capability is separate.
How did FollowSkills review this skill?
The skill demonstrates strong security awareness at the documentation level: it explicitly prohibits bypassing paywalls, DRM, or captchas; does not read or export cookies, passwords, localStorage, or session files; API keys are passed via stdin and stored with 0600 permissions, avoiding echo in command arguments, logs, replies, and manifests; requires SI confirmation to prevent unintended downloads; and includes provider-friendly pacing and audit trails. However, the core functionality relies on the user's logged-in browser and CDP proxy, involving operation on the user's browser environment, while permission control, session isolation, and rollback mechanisms are not fully specified; the docs mention limitations but lack implementation details such as the scope, restrictions, and failure recovery of browser control. Deductions: incomplete permission and isolation, and lack of recovery mechanisms.
The skill provides detailed workflows, status codes, and failure handling, but key scripts (e.g., batch_download.mjs, configure_school.py, browser_pdf_downloader.mjs) and their test suites were not reviewed, so correctness cannot be verified. The docs explicitly require Node 22+ and Python 3, but dependency lists and installation instructions are missing, which may cause environmental issues. Moreover, many failure statuses (e.g., verification_auto_failed, carsi_waiting_user) depend on browser state, and their implementation cannot be confirmed from static review. Deductions: static review only, tests not executed, and dependence on external services (CNKI, Web of Science) that may not be directly accessible from mainland China, potentially affecting reliability.
The skill has clear target audience (users needing lawful access to academic full texts) and scenarios (CNKI institutional access, OA retrieval, publisher APIs), but capability boundaries and trigger conditions are clear in the docs, yet actual triggering depends on user input and configuration. Chinese language support is good, but the core functionality depends on overseas services like CNKI and Web of Science, which may be restricted or require specific access methods in mainland China, affecting adaptability. Deductions: environmental fit and accessibility not verified, and reliance on overseas services may hinder use in mainland China.
The skill has a complete information architecture: SKILL.md, README.md, README_EN.md, references/, and data/. The docs provide configuration, installation, examples, and boundaries, but lack explicit known limitations (e.g., compatibility with specific schools) and version/changelog. The publisher is unverified, but the docs provide clear maintainer information, so responsibility is mostly clear. Deductions: missing known limitations and change history.
The skill claims to complete download tasks, but static review cannot verify actual output quality. The docs specify clear output formats (manifest.json, PDF, HTML, etc.) and detailed example commands, but lack independent verification of output usability. Deductions: static review cannot confirm whether outputs are directly usable, and dependence on browser state and external services may affect actual effectiveness.
The docs provide test commands (python3 -m unittest discover -s tests/python and node --test tests/unit/*.test.mjs), but test files and results were not reviewed, so authenticity cannot be confirmed. An internal design doc (docs/nature-downloader-reference-research-2026-07-15.md) provides external references, but no specific validation data is seen. Deductions: tests not executed, insufficient external validation data, only static documentation evidence.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →