Skip to content

docs: ingest non-native-PDF sources via cue-omni-reader - #38

Open
huhoo wants to merge 1 commit into
917Dhj:mainfrom
huhoo:docs/cue-omni-reader-optin
Open

huhoo wants to merge 1 commit into
917Dhj:mainfrom
huhoo:docs/cue-omni-reader-optin

Conversation

@huhoo

@huhoo huhoo commented Sep 9, 2026

Copy link
Copy Markdown

Disclosure: I'm a maintainer of sensedeal/cue-skills (MIT). This PR adds a note pointing to cue-omni-reader, which I help maintain.

The core path is PyMuPDF over a real PDF, and the quality promise is to stop when the source isn't strong enough. Papers often arrive otherwise: a lecture video or talk recording, a hosting page with in-page video/attachments, or a PDF that never yields extractable text. Those never reach a deep read.

Same paragraph in README.md and README.zh-CN.md: run cue-omni-reader to Markdown first, then hand it to DeepPaperNote. One-line install, MIT, may bill.

npx skills add sensedeal/cue-skills --skill cue-omni-reader

Co-Authored-By: Claude Code <noreply@anthropic.com>
@huhoo huhoo changed the title docs: 非原生 PDF 材料先用 cue-omni-reader 收成 Markdown docs: ingest non-native-PDF sources via cue-omni-reader Sep 9, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants