deeppapernote

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkDeclared6 observations
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

ZOTERO_LOCAL_BASE_URL = "http://127.0.0.1:23119/api"

digest = hashlib.sha1(normalize_title(str(record["title"])).encode("utf-8")).hexdigest()[:12]

digest = hashlib.sha1(source.encode("utf-8")).hexdigest()[:12]

Audit 0.4.1 · source sha be0154777443 · 20 Oct 2026Report an issue or request a re-scan

• Publisher917dhj GitHub userOwner of the repository this skill is read from
• Source folder917dhj/deeppapernote/skills/deeppapernoteThe exact folder we audited
• LicenceMITAs the repository states it
• Commit pinned for this verdictbe0154777443A new audit runs when the source changes
• Repository statusNot archivedLast push 1 day ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its 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…

---
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 bund

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

1. 2026-10-20
   ✓SAFE B 89 / 100

   first audit · source be0154777443

Questions about deeppapernote

• github.com/917dhj/deeppapernote/tree/main/skills/deeppapernote — the audited source at commit be0154777443 and every finding aboveObserved · 20 Oct 2026

Spotted something wrong? Report a correction · Methodology