Is the Deeppapernote skill free?

Yes. The skill itself is free from 917Dhj/DeepPaperNote. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Deeppapernote SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install Deeppapernote?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Deeppapernote with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Deeppapernote

Turns one paper (arXiv/DOI/PDF) into a structured, evidence-grounded Obsidian reading note

by 917Dhj · 917Dhj/DeepPaperNote

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · ad0f18f

Cloned the repo and ran scripts/run_pipeline.py on arXiv:1508.06576 under Python 3.13 with PyMuPDF installed; it resolved identity, fetched the real 16-page PDF, extracted 393 lines of full text, and built an 80KB paper_bundle.json with a writing_contract requiring 12 Chinese sections. For OUTPUT I wrote two notes and ran scripts/lint_note.py on both: my free-form baseline failed passes_basic_structure, passes_style_gate and passes_substantive_content with all 12 required sections reported missing; the skill-structured note (YAML frontmatter, 核心信息 metadata block, faithful 原文摘要翻译, 创新点, 机制流程, 局限) passed all three gates with missing_sections=[]. Both failed passes_plan_gate because I did not author the separate note_plan JSON that the workflow expects. Security scan found no curl|sh, base64 blobs, or exfiltration; network calls target only arXiv/Crossref/OpenAlex/Semantic Scholar and the Semantic Scholar key is read from env.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 5/5

What Deeppapernote does

Runs a deterministic Python pipeline that resolves a paper's identity, fetches the PDF, extracts full-text sections and figures, and builds a synthesis bundle the model uses to write a deep Chinese-language Markdown note with a fixed section contract, then lints it against structure and style gates. Triggers when the user gives a paper title, DOI, URL, arXiv ID, Zotero item, or local PDF and wants a polished Obsidian note rather than an abstract rewrite. Handles one paper at a time; not for multi-paper literature reviews or reading lists.

How to install Deeppapernote

git clone --depth 1 https://github.com/917Dhj/DeepPaperNote.git /tmp/deeppapernote-src
mkdir -p ~/.claude/skills
cp -R /tmp/deeppapernote-src/skills/deeppapernote ~/.claude/skills/deeppapernote
# Deps: Python >=3.10, plus `pip install PyMuPDF certifi` (PyMuPDF/fitz does the PDF text+figure extraction).
# Optional: pytesseract+Pillow for OCR of scanned PDFs; a local Zotero desktop (Local API) for library-first resolution.
# Plugin alternative: `npx skills add 917Dhj/DeepPaperNote` (installs as a multi-agent plugin; also bundles companion skill `paper-glossary`).
# Run the deterministic pipeline: python3 ~/.claude/skills/deeppapernote/scripts/run_pipeline.py --input "arXiv:1508.06576" --workdir /tmp/dpn-run --zotero-mode off
# Output note (zh-CN) requires the model to write from the generated synthesis_bundle.json; lint with scripts/lint_note.py.

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Deeppapernote

/deeppapernote Turns one paper (arXiv/DOI/PDF) into a structured, evidence-grounded Obsidian reading note

It also activates on plain-language prompts like these:

Create a deep-reading note for this arXiv paper
Summarize this paper's DOI into my Obsidian vault
Write an evidence-based note on this PDF paper

Frequently asked questions

Is the Deeppapernote skill free?: Yes. The skill itself is free from 917Dhj/DeepPaperNote. SkillProof publishes the install command and an independent test verdict at no cost.
Does Deeppapernote work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Cloned the repo and ran scripts/run_pipeline.py on arXiv:1508.06576 under Python 3.13 with PyMuPDF installed; it resolved identity, fetched the real 16-page PDF, extracted 393 lines of full text, and built an 80KB paper_bundle.json with a writing_contract requiring 12 Chinese sections. For OUTPUT I wrote two notes and ran scripts/lint_note.py on both: my free-form baseline failed passes_basic_structure, passes_style_gate and passes_substantive_content with all 12 required sections reported missing; the skill-structured note (YAML frontmatter, 核心信息 metadata block, faithful 原文摘要翻译, 创新点, 机制流程, 局限) passed all three gates with missing_sections=[]. Both failed passes_plan_gate because I did not author the separate note_plan JSON that the workflow expects. Security scan found no curl|sh, base64 blobs, or exfiltration; network calls target only arXiv/Crossref/OpenAlex/Semantic Scholar and the Semantic Scholar key is read from env.
What is the Deeppapernote SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Deeppapernote?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Deeppapernote with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.