SkillAgentSearch skills...

deeppapernote

Generate a high-quality deep-reading note for a single paper and write it into an Obsidian-style vault

Install / Use

npx skills add 917Dhj/DeepPaperNote --skill deeppapernote

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

83/100

Supported Platforms

Universal

Our assessment of deeppapernote

deeppapernote scores 83/100 on our quality scale, 932nd of 1,155 Content & Media skills we index.

Its SKILL.md is 23 KB long, well organised into 10 sections and no code examples: a thorough specification that gives an agent plenty to work with.

With 1,112 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
30/30
Structure
13/20
Description
12/15
Adoption
13/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so deeppapernote is actively maintained.
  • Our last check on 2026-11-07 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-07. Automated pattern scan on 2026-10-07. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

deeppapernote compared with similar skills

All 4 of these similar skills score higher than deeppapernote; compare them before choosing.

SkillScoreStarsUpdatedFormat
deeppapernote (this skill)by 917Dhj831.1k55d agoSKILL.md
siyuanby siyuan-note10047.3ktodayMCP Server
x402by browser-use100121.0k3d agoSKILL.md
algorithmic-artby anthropics100177.9k55d agoSKILL.md
pptxby anthropics100177.9k55d agoSKILL.md

Frequently asked questions

How do I install deeppapernote?
Run npx skills add 917Dhj/DeepPaperNote --skill deeppapernote. The install tabs above show the steps for each supported agent.
Which AI agents does deeppapernote work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is deeppapernote safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is deeppapernote still maintained?
The repository was last updated about 2 months ago, so deeppapernote is actively maintained.

name: deeppapernote description: 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.

DeepPaperNote

Use this skill when the user wants one outcome:

  • read one paper carefully
  • generate a high-quality Markdown note
  • save the note to the workspace or Obsidian target selected by resolved configuration

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

English trigger examples:

  • Generate a deep-reading note for this paper
  • Turn this paper into an Obsidian research note

User Configuration

Before a normal paper run, read references/user-configuration.md for configuration admission, migration, repair, Run Overrides, and Preference Changes.

Resolve Run Overrides from the explicit request, CLI, and current process environment first. When they form a complete valid configuration for the selected Save Mode, Configuration Readiness is complete without reading User Configuration. Only inspect User Configuration when those Run Overrides need fallback values.

Language Integrity Contract

After Configuration Readiness, resolve one output_language (zh-CN or en) for the run. source_manifest.language_hint describes source text only and never selects the note profile.

Bind that exact value through Save Target Admission → Figure Plan → Figure/Table Decisions → Synthesis Bundle → Note Plan → Grounding Lint → Final Note Lint → Final Quality Review → Final Readability Review → Formal Save:

  • Every JSON artifact in the chain carries a top-level output_language; the Synthesis Bundle also carries the same value at writing_contract.language.
  • Before producing its output, every adjacent consumer requires each input language and compares it with the resolved value. Missing, unsupported, or mismatched values stop the run; no stage infers or defaults an artifact language.
  • Final Quality Review and Final Readability Review each receive the resolved value and check the note against only that profile.
  • Final Note Lint records note_sha256. Any review edit invalidates the prior lint, so rerun Final Note Lint under the same language. Formal Save requires the lint language and note_sha256 to match the final note, and validates Figure/Table Decisions language before any save side effect.

This contract is complete only when every named stage is bound to the resolved value and Formal Save validates the final bytes. Read references/output-language.md for profile content while drafting or debugging either language.

This skill is intentionally narrow:

  • it is one canonical Skill and one pipeline with two output profiles
  • 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 logic

The note must adapt to the paper type. Use the same base structure, but shift emphasis for AI methods, benchmarks, clinical studies, and humanities or social-science papers.

Workflow

Follow this order:

  1. complete Configuration Readiness: resolve Run Overrides first, and inspect User Configuration only when they are incomplete; advance only after the resolved run configuration is complete and valid
  2. resolve the paper identity
  3. collect metadata
  4. acquire the best available PDF using the accepted identity and original user reference (fetch_pdf.py --reference); in Obsidian mode, verify and reuse a matching local archive before downloading, following references/paper-archive.md for version/source selection
  5. extract canonical raw source text: *_raw_sections.jsonl, *_source_manifest.json, and optional derived *_full_text.md
  6. perform Save Target Admission before drafting or domain routing:
    • for Obsidian mode, run scripts/write_obsidian_note.py --preflight with the resolved title, exact output_language, Vault, and *_source_manifest.json; this program result is authoritative, so do not replace it with prompt-only duplicate checking
    • when admission returns a reuse result, use that directory and skip domain selection; a verified PDF-only directory needs no registration confirmation. Read asset_subdir from preflight and use it for source-bound figure embeds
    • when it returns same_language_note_exists, stop before drafting and ask whether to overwrite the reported note. If the user approves, rerun preflight with --overwrite-existing-note --expected-existing-note-sha256 <reported_sha256> and carry that exact confirmation into Formal Save; if the user declines, stop without writing
    • when multiple directories or sources match, follow references/paper-archive.md: ask for the current selection and carry it through preflight and Formal Save
    • for any other blocked conflict, report the returned ambiguity and stop without creating a second directory
    • workspace mode does not scan an Obsidian Vault and continues through its normal domain routing
  7. extract structural indexes and PDF assets
  8. plan figure placement
  9. build the full figure/table decision table
  10. build the manifest synthesis bundle
  11. have the model read the bundle plus raw sections and create a short JSON note_plan that satisfies the generated bundle contract, including its exact output_language
  12. draft from the plan only after the grounding gate passes
  13. have the model write the note
  14. lint the final note against the same note_plan — this stage completes only when the lint artifact exists and every reported passes_* gate is true; otherwise revise and rerun lint. If the lint output contains passes_style_gate: false, apply the Style Gate Enforcement rule before advancing to step 15, 16, or 17
  15. perform final_quality_review after lint passes
  16. perform final_readability_review after the quality review passes
  17. perform Formal Save to the admitted target with scripts/write_obsidian_note.py, the same Source Manifest, and any user-approved overwrite hash; the script repeats admission before the first save side effect

This is the required workflow for a normal single-paper note request, not a loose suggestion. Unless this skill explicitly marks a stage as optional, required stages must not be silently skipped, reordered into a shortcut, or treated as complete just because a partial artifact already exists.

Global no-short-circuit rule:

  • do not stop after only the early stages and present the workflow as finished
  • do not treat slowness, inconvenience, or temporary uncertainty as permission to bypass a required stage
  • do not replace the declared workflow with an improvised shortcut
  • if a required stage fails, only do one of three things:
    • retry that stage
    • enter a fallback that is explicitly allowed by this skill
    • stop and report which stage is blocked and which downstream required stages remain incomplete
  • do not describe the whole task as complete while required downstream stages are still pending

Completion-language rule:

  • say 笔记已完成 only when the required workflow is actually complete
  • say 已生成草稿 when drafting is done but lint, final readability review, or save is still pending
  • say 已通过校验 only when lint has actually been run and passed
  • say 已保存到 Obsidian only when the write step has actually succeeded
  • do not treat lint 已通过 as equivalent to 整篇笔记已经润色完成
  • if final readability review is still pending, explicitly say the draft passed script lint but has not finished final language review
  • if the workflow stopped early, name the current stage and the still-missing required stages instead of using completion language
  • lint is a floor, not the writing objective

Final user report:

  • Keep the completion wording defined above. After a successful Formal Save, report in the user's conversation language.
  • Lead with the final note link or path, save mode, and actual saved domain. Read the domain from the final note path under the configured papers root in Obsidian mode or output root in workspace mode; when Save Target Admission reused an existing directory, report that directory's existing domain.
  • Then report, in order:
    1. paper title and strongest verified identifier
    2. Grounding Lint, Final Note Lint, Final Quality Review, and Final Readability Review results, plus the warning count
    3. materialized and retained-placeholder figure/table counts
    4. whether the saved note SHA-256 matches the Final Note Lint note_sha256
  • Add overwrite actions, preference changes, or user-relevant warnings only when they occurred.
  • Keep the report to these fields and derive every claim from current-run artifacts.

Core Execution Contract

SKILL.md plus the generated synthesis_bundle.json must be enough to complete a normal note-generation run. Files under references/ are optional stage-specific deep dives, not a default reading checklist.

Non-negotiable rules:

  • evidence-first: draft from the synthesis bundle, source_manifest, raw sections, coverage metadata, explicit note_plan, and inspected paper evidence; never finish from title/abstract/headings alone
  • raw-source authority: for ordinary PDFs, *_raw_sections.jsonl and *_source_manifest.json are the canonical reading material; old top-N evidence buckets, truncated section_texts, and candidate_chunks are not model-facing writing inputs
  • fail-closed: if a usable PDF or sufficient evidence cannot be obtained after supported acquisition paths, stop and ask for better source material rather than producing a finished degraded note
  • model-first: scripts structure evidence, but the model must decide emphasis, contribution, mechanism, limitations, and final prose in the configured language
  • required structure: include the localized canonical sections in the order declared by writing_contract.must_include_sections
  • abstract fidelity: preserve the original abstract's meaning without adding later evidence or model judgments; translate it in zh-CN mode and render it faithfully in English in en mode
  • mechanism depth: method, framework, and system papers should include the localized mechanism-flow subsection under the localized method section, normally as a 3 to 4 step numbered flow with input, operation, and output destination
  • placeholder-first figures: plan major figure/table placeholders first; replace one only when identity match and visual usability are both strong; otherwise keep the placeholder

Reference usage policy:

  • do not load every reference file by default
  • consult references/evidence-first.md, references/deep-analysis.md, or references/final-writing.md only when the paper is complex or the draft is too shallow
  • consult references/figure-placement.md only for ambiguous figure/table placement or image replacement decisions
  • consult references/paper-archive.md for existing Obsidian directories, local PDF version selection, or Connector handoff
  • consult references/obsidian-format.md only for Markdown, vault, frontmatter, or reference-link formatting details
  • consult references/note-quality.md or references/paper-types.md only for final review or domain adaptation
  • consult `references/metadata-source

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars1.1k
CategoryContent
Updated1mo ago
Forks78

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions