# QQnote Input Boundary

Use this file when QQsci needs literature-note inputs from QQnote.

QQnote is only the tool for summarizing papers into Zotero child notes or
compact Markdown comparison tables. QQsci owns the top-level DeepSeek/Zotero
configuration for manuscript workflows and all manuscript-facing reasoning:
keyword extraction, strong/weak related-paper screening, target-journal
positioning, comparative review, submission-package audit, figure/format
checks, terminology checks, and DOI-only Word citation comments.

Do not ask QQnote to decide whether a paper is strongly related, weakly related,
necessary for citation, or sufficient as reviewer evidence. QQnote supplies
structured paper information; QQsci makes the manuscript decision.

## Core order

1. QQsci identifies what literature input is needed from the manuscript topic,
   draft, figures, target journal, or missing evidence.
2. QQnote generates or refreshes Zotero child-note summaries for selected papers
   when the notes are missing or stale.
3. QQnote may summarize selected papers into a Markdown comparison table when
   QQsci needs compact data for side-by-side comparison.
4. QQsci performs relevance classification, manuscript comparison, audit,
   rewriting, and Word DOI-comment placement.

Do not default to creating standalone Obsidian markdown notes when the user says
`文献笔记`; the default input source is Zotero child notes generated by QQnote.

## QQnote entrypoints

Use the installed `QQnote-skill` scripts only for note/table generation:

```powershell
py "$env:USERPROFILE\.codex\skills\qqsci\scripts\run_qqnote_with_qqsci_config.py" --script generate_zotero_ai_note -- --vault "C:\Users\qyh15\Documents\Obsidian Vault" --item-key SXAIQUJT --skip-existing
py "$env:USERPROFILE\.codex\skills\qqsci\scripts\run_qqnote_with_qqsci_config.py" --script summarize_zotero_table -- --vault "C:\Users\qyh15\Documents\Obsidian Vault" --item-keys "SXAIQUJT X7GJZ627" --batch-size 3 --out "C:\Users\qyh15\Documents\Obsidian Vault\99 misc\literature-comparison-table.md"
```

Use `generate_zotero_ai_note.py` when new or selected papers need Zotero child
notes.

Use `summarize_zotero_table.py` when QQsci needs a compact comparison table for
papers it has already selected or is about to classify.

Do not use QQnote's audit, cleanup, or Dataview workflows as QQsci decision
logic unless the user explicitly asks for QQnote maintenance.

## Safety and config

- Do not ask the user to paste API keys into chat.
- For QQsci manuscript workflows, load DeepSeek/AwesomeGPT and Zotero
  credentials from QQsci `config/config.local.json` and inject them into QQnote
  with `scripts/run_qqnote_with_qqsci_config.py`.
- QQnote must still be able to run standalone using its own environment
  variables, vault `.env`, or AwesomeGPT/Zotero preferences.
- Keep private config ignored and local-only.
- Do not print secret-bearing config or preference lines.
- Treat Zotero local API at `127.0.0.1:23119` as read-oriented.
- For child-note writes, use QQnote's configured write path.

## When to call QQnote

Call QQnote when:

- a candidate paper has no generated Zotero child note
- the user imports new papers and wants note generation
- QQsci needs a compact table for a selected set of papers
- the existing notes are too thin and the user asks for deeper notes

Do not call QQnote when:

- the task is only to classify strong/weak related papers from existing notes
- the task is target-journal positioning
- the task is manuscript/package audit
- the task is Word DOI-only citation comments
- the task is figure, format, spelling, or terminology checking

## QQsci-owned manuscript integration

After QQnote outputs notes or a table:

1. QQsci extracts the manuscript keyword pack.
2. QQsci uses `literature-routing.md` to classify strong and weak papers.
3. QQsci builds a source map linking paper -> useful claim -> manuscript
   section.
4. QQsci uses `comparative-review-audit.md` and
   `submission-package-audit.md` for missing-evidence and package checks.
5. QQsci adds Word native comments containing DOI strings only when requested.

## Output template

`QQnote input used:`

`Generated or refreshed notes:`

`QQnote table path:`

`QQsci screening/audit next step:`