paper2htmllisted

# Paper2HTML ## Overview Create one self-contained Chinese `index.html` that lets the user read the page and understand the paper without reopening the PDF. Default style: clear Cheat-Sheet page, focused evidence, KaTeX formulas, no decorative complexity. Use scripts first. Keep this skill as workflow/quality gates, not a long prompt. ## Scripted Path ```bash cd /path/to/paper2html # 1) Create workspace + source-boundary note + starter index.html python scripts/bootstrap_paper2html.py \ --title "Paper Title" \ --slug paper-slug \ --out /path/to/output/paper-slug-html-YYYYMMDD \ --arxiv 2504.07952 \ --github https://github.com/org/repo \ --publish-to self-evolving-agent/topic/paper-slug # 2) If TeX/source exists, create a structural inventory python scripts/tex_inventory.py \ /path/to/output/source/unpacked \ --out /path/to/output/notes/tex-inventory.md \ --json /path/to/output/notes/tex-inventory.json # 3) Optimize figures and get data URIs for single-file HTML python scripts/optimize_paper_images.py \ paper_figures/*.pdf paper_figures/*.png \ --out-dir /path/to/output/assets/optimized \ --width 1600 \ --data-uri-json /path/to/output/assets/data-uris.json # 4) Optional but preferred: ask Gemini for a visual draft on a copy scripts/gemini_frontend_pass.sh \ /path/to/output/index.html \ --reference /path/to/good-reference.html \ --timeout 240 # To inspect the exact Gemini prompt and attached materials without spending a model call: scri