Agent skill · Code Review & Quality

deeppapernote

Generate a high-quality deep-reading note for a single paper and write it into an Obsidian-style vault. Use when the user gives a paper title, DOI, URL, arXiv ID, Zotero item, or local PDF and wants a polished Markdown note with strong structure, evidence-based analysis, and figure placeholders.

917Dhjgithub.com/917DhjGitHub ↗
claude-codecodexcopilotcursorships scriptsMIT
Install
npx skills add 917Dhj/DeepPaperNote --skill deeppapernote --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 35
SKILL.md size: 18 KB
Bundled scripts: yes
Path: skills/deeppapernote/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 575
Language: Python

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# DeepPaperNote Use this skill when the user wants one outcome: - read one paper carefully - generate a high-quality Markdown note - save the note into an Obsidian-style vault when configured, or into the current workspace when no vault is configured Chinese trigger examples: - `给这篇论文生成深度笔记` - `写一篇高质量论文精读笔记` - `把这篇文章整理成 obsidian 笔记` - `读这篇论文并生成 md 笔记` This skill is intentionally narrow: - it handles one paper at a time - it does not update daily reading lists - it does not treat a shallow abstract rewrite as a successful output - it does not split the public entrypoint into separate setup, troubleshooting, or start commands ## Core Standard The finished note must be more than a summary. It should reconstruct the paper's argument: - what problem it solves - how the task is defined - what data or materials it uses - how the method or analysis actually works - what results matter most - what the paper does not prove - why the paper is worth keeping Default writer persona: - a top-tier researcher or algorithm engineer - writing a replication-oriented lab note - not writing a popular-science explanation - assuming the reader can follow Python, PyTorch, training loops, and evaluation log

What's inside
Steps it walks through
  1. Core Standard
  2. Workflow
  3. Core Execution Contract
  4. Tool and Source Priority
  5. Output Rules
  6. Scripts
  7. Limits
Ships with 24 files
  • agents/openai.yaml
  • references/architecture.md
  • references/deep-analysis.md
  • references/domain_rules.yaml
  • references/evidence-first.md
  • references/figure-placement.md
  • references/final-writing.md
  • references/metadata-sources.md
  • references/note-quality.md
  • references/obsidian-format.md
  • references/paper-types.md
  • scripts/_zotero_local.py
  • scripts/build_identity_contract.py
  • scripts/build_synthesis_bundle.py
  • scripts/check_environment.py
  • scripts/citation_links.py
  • scripts/collect_metadata.py
  • scripts/common.py
  • scripts/contracts.py
  • scripts/create_input_record.py
  • scripts/extract_evidence.py
  • scripts/extract_pdf_assets.py
  • scripts/extract_source_text.py
  • scripts/fetch_pdf.py
first 24 of 35
More from DeepPaperNote
All skills →
About this skill
What does the deeppapernote skill do?

Generate a high-quality deep-reading note for a single paper and write it into an Obsidian-style vault. Use when the user gives a paper title, DOI, URL, arXiv ID, Zotero item, or local PDF and wants a polished Markdown note with strong structure, evidence-based analysis, and figure placeholders.

How do I install it?

Run `npx skills add 917Dhj/DeepPaperNote --skill deeppapernote --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From 917Dhj/DeepPaperNote, a repository with 575 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going