agentleFS
Sign inStart free
phanghonghaophanghonghao/THU-Awesome-Skills/skills/html2tex/SKILL.md

html2tex

Skill8 starsChanged 3 months agoMITView on GitHub

Convert HTML, especially HTML generated from Word or `word2html`, into LaTeX and optionally PDF via XeLaTeX. Use when the user mentions `html2tex`, wants to convert HTML to LaTeX or PDF, or needs support for merged tables, embedded images, inline formatting, or MathJax formulas.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill especially for HTML produced by a Word-to-HTML workflow.

    line 30
  2. Very specific:

    If --output-dir is omitted, write output next to the input file.

    line 38
  3. Very specific:

    If the user asked for PDF and compilation succeeds, report both .tex and .pdf.

    line 44
  4. Very specific:

    If XeLaTeX is missing or compilation fails, rerun with --no-compile only when needed and report that only .tex was generated.

    line 45
  5. Distinctive:

    If XeLaTeX is unavailable, do not pretend PDF generation succeeded.

    line 53
  6. Distinctive:

    Prefer reporting the generated file paths instead of pasting LaTeX output into the response.

    line 58
  7. Distinctive:

    If the HTML appears broken, mention that the converter can only preserve structure that exists in the source HTML.

    line 59

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

html2tex

Convert HTML files to LaTeX and PDF with the bundled html2tex.py script.

Run

From this skill directory, run:

python html2tex.py <input.html> [--output-dir DIR] [--no-compile]

Inputs

Assume the input HTML may contain:

  • tables with colspan and rowspan
  • embedded images
  • bold, italic, underline, and strikethrough
  • MathJax-style formulas

Use this skill especially for HTML produced by a Word-to-HTML workflow.

Outputs

Produce:

  • <input>.tex
  • <input>.pdf when compilation is enabled

If --output-dir is omitted, write output next to the input file.

Workflow

  1. Confirm the input file exists.
  2. Run html2tex.py.
  3. If the user asked for PDF and compilation succeeds, report both .tex and .pdf.
  4. If XeLaTeX is missing or compilation fails, rerun with --no-compile only when needed and report that only .tex was generated.

Dependencies

Require:

  • Python 3
  • XeLaTeX for PDF compilation

If XeLaTeX is unavailable, do not pretend PDF generation succeeded.

Notes

  • Preserve tables and images where possible.
  • Prefer reporting the generated file paths instead of pasting LaTeX output into the response.
  • If the HTML appears broken, mention that the converter can only preserve structure that exists in the source HTML.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free