agentleFS
kreuzberg-devkreuzberg-dev/html-to-markdown/skills/html-to-markdown-fetching-and-converting-urls/SKILL.md

html-to-markdown-fetching-and-converting-urls

Skill881 starsChanged 4 months agoMITView on GitHub

Use when fetching a live URL and converting it to Markdown. Covers --url, custom user agents, preprocessing for noisy pages, and the --json ConversionResult shape.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this when the user gives a URL instead of HTML and wants the page as Markdown (or its metadata/tables).

    line 15
  2. Very specific:

    Add --json to get the full structured result instead of plain Markdown:

    line 54

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
<!-- AI-RULEZ :: GENERATED FILE — DO NOT EDIT Content-Hash: blake3:f46c6d2411f814c68ba4f0cb91b2efe2104f01ae7129dd2b84e0fa6ef94169e2 Source-Hash: blake3:993543f9225ea202d6e97003900394a417d430ff4e7e1a9412b8f7a844713c9f Schema-Version: v1 -->

Fetching and converting URLs

Use this when the user gives a URL instead of HTML and wants the page as Markdown (or its metadata/tables). The CLI fetches the page over HTTP and converts it in one step via --url. --url conflicts with a positional FILE.

For crawling many pages or following links, use crawlberg instead — this skill is for a single URL.

Fetch and convert

# Fetch a URL, print Markdown to stdout
html-to-markdown --url https://example.com

# Save to a file
html-to-markdown --url https://example.com -o page.md

# Custom User-Agent (default mimics a real browser)
html-to-markdown --url https://example.com --user-agent "MyBot/1.0"

--user-agent requires --url.

Clean noisy pages

Real web pages carry navigation, ads, cookie banners, and forms. Preprocess before converting:

html-to-markdown --url https://example.com/article --preprocess --preset aggressive

# Keep the nav or forms if the page content lives there
html-to-markdown --url https://example.com --preprocess --keep-navigation

Presets: minimal, standard (default), aggressive. --preset and the --keep-* flags require --preprocess.

JSON output (ConversionResult)

Add --json to get the full structured result instead of plain Markdown:

html-to-markdown --url https://example.com --json
{
  "content": "# Title\n\nContent\n",
  "metadata": {
    "document": { "title": "...", "language": "en" },
    "headers": [],
    "links": [],
    "images": [],
    "structured_data": []
  },
  "tables": [],
  "images": [],
  "warnings": []
}

Useful combinations (all require --json):

# Page title + outline, no Markdown body
html-to-markdown --url https://example.com --json --no-content \
  | jq '{title: .metadata.document.title, headings: [.metadata.headers[].text]}'

# Include the document-structure tree
html-to-markdown --url https://example.com --json --include-structure | jq '.document'

# Extract inline image data
html-to-markdown --url https://example.com --json --extract-inline-images | jq '.images | length'

Surface warnings

html-to-markdown --url https://example.com --show-warnings > page.md
# non-fatal warnings (truncation, malformed markup) go to stderr

Exit codes

CodeMeaning
0Success
1Conversion or I/O error (including a failed fetch)
2Invalid arguments

See references/cli-reference.md for the full flag set and JSON shape.

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.