paper2assetslisted
Install: claude install-skill wookat/ai-research-skills
# paper2assets — paper PDF → reusable assets
One paper PDF in, a single `<outdir>/` of poster-agnostic assets out, ready for any downstream renderer.
## Output Contract (the shared layout every paper2* skill follows)
paper2assets defines the on-disk shape of **every** deliverable bundle in the pipeline. paper2poster, html2pptx, paper2blog, paper2video, and paper2reel all read from and write to a bundle laid out this way — a teammate adding or changing a downstream skill conforms to this contract.
**Rules**
1. The bundle directory is named after the paper.
2. The bundle's **top level holds ONLY that skill's deliverable FILES** — no loose intermediates, and as few folders as possible.
3. **Every** dependency and intermediate (figures, logos, qr, audio, fonts, captions, slides, the spec / json / txt) lives under one **`assets/`** container.
**Layout**
```
<paper-name>/
|-- <deliverable files> # see the per-skill table below
|-- manifest.json # package index (root-relative paths); the one allowed top-level non-deliverable
`-- assets/
|-- figures/ logos/ qr/ audio/ fonts/ # runtime deps the deliverables reference
`-- meta/ # build intermediates
|-- paper_spec.md sections.json narration.json
`-- captions.json figures.json metadata.json text.txt
```
Deliverables reference assets with **root-relative** `src` paths -- `assets/figures/...`, `assets/logos/...`, `assets/qr/...`, `assets/a