Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

PDF to HTML

Converts a PDF into one self-contained, readable HTML file that preserves images, tables, charts and reading order — with optional translation.

Docs & OfficeIntermediate★ 1,323⑂ 212AI score 9/10Last updated: Aug 8, 2026

What it does

It runs a five-step pipeline: extract → look → (translate) → build → verify. PyMuPDF pulls out text blocks with font sizes plus images (flagging decorative ones), the builder infers heading levels from font size, drops decoration, and inlines content images as compressed base64 so you end up with one portable HTML file that opens on a double-click.

The "look" step is mandatory: page renders are read as PNGs so the real layout, charts and tables are understood before building. The final verification re-renders the HTML through headless Chrome and inspects segment images for tofu boxes, clipped tables and missing figures.

Optional translation runs a Dynamic Workflow that translates pages in parallel, captions data charts and reconciles terminology, with strict fidelity rules — numbers and proper nouns copied verbatim, never inventing a translated personal name.

Limits: scanned/image-only PDFs need OCR first (e.g. ocrmypdf); complex multi-column tables lose their grid; the output is a clean re-flow, not a pixel-perfect facsimile.

Who it's for

  • Anyone who just wants to read a dense PDF comfortably in a browser or on a phone
  • Researchers and analysts translating foreign-language reports without losing figures
  • Teams that need to share a document as a single attachment
  • People who want styled output rather than plain Markdown

Examples

  1. Translate a report: drop in a 50-page English whitepaper and ask for a Chinese version — you get one HTML with all charts intact and consistent terminology.
  2. Mobile reading: convert a tiny-print academic paper into reflowed HTML that reads well on a phone.
  3. Single-file sharing: turn an image-heavy product deck PDF into one base64-inlined HTML you can send over chat with no broken assets.

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the daymade-docs/pdf-to-html folder from the GitHub repo daymade/claude-code-skills into my ~/.claude/skills/pdf-to-html/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/daymade/claude-code-skills.git && mkdir -p ~/.claude/skills && cp -r claude-code-skills/daymade-docs/pdf-to-html ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Prerequisites: install uv (Python runner) and Google Chrome or Chromium (needed for visual verification).
  2. Clone the repo: run git clone https://github.com/daymade/claude-code-skills.git.
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r claude-code-skills/daymade-docs/pdf-to-html ~/.claude/skills/
  5. Verify: restart Claude Code and say "convert this PDF to HTML" — the skill should trigger automatically.
  6. First run: point it at a PDF path. Python packages (PyMuPDF, Pillow, numpy) are fetched on demand by uv run --with, so nothing else to pre-install.
View source on GitHub ↗License: MIT