Skip to content
Agentmart
Submit a tool

web-to-md

Scrape web pages and convert them to clean Markdown using a fully-local trafilatura pipeline.

Skill by JorgeIvanJH

IndexedLicense unknown
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/jorgeivanjh-web-to-md

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Scrape web pages and convert them to clean Markdown using a fully-local trafilatura pipeline. Provides a single-page `fetch` mode (one URL → one .md plus extracted links, agent decides what to follow next) and a recursive `crawl` mode (BFS-follow links from a starting URL up to a depth/page cap). Output goes into a user-specified directory. Architecture is adapter-based; a `docsify` adapter handles JS-rendered docsify SPAs, and a `GenericHtml` adapter handles everything else. New site types can be added by dropping a file into `scripts/adapters/`. Use when the user asks to scrape, mirror, or convert a documentation site or web page to Markdown.

Use cases: documents, data, agent-building

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/web-to-md

What's inside

Skill name
web-to-md
Description
Scrape web pages and convert them to clean Markdown using a fully-local trafilatura pipeline. Provides a single-page `fetch` mode (one URL → one .md plus extracted links, agent decides what to follow next) and a recursive `crawl` mode (BFS-follow links from a starting URL up to a depth/page cap). Output goes into a user-specified directory. Architecture is adapter-based; a `docsify` adapter handles JS-rendered docsify SPAs, and a `GenericHtml` adapter handles everything else. New site types can be added by dropping a file into `scripts/adapters/`. Use when the user asks to scrape, mirror, or convert a documentation site or web page to Markdown.
License
unknown
Compatibility
Requires Python 3.9+, internet access, and ~/.pi/agent/skills/web-to-md/.venv (created by scripts/setup.sh on first use).
Instructions
127 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (13)

  • SKILL.md
  • adding-adapters.md · references/
  • _common.py · scripts/
  • _dispatch.py · scripts/
  • __init__.py · scripts/adapters/
  • base.py · scripts/adapters/
  • docsify.py · scripts/adapters/
  • generic_html.py · scripts/adapters/
  • hl7_fhir.py · scripts/adapters/
  • crawl.py · scripts/
  • fetch.py · scripts/
  • run.sh · scripts/
  • setup.sh · scripts/

The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub

More from JorgeIvanJH/IRISMiscTesting

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jun 18, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
License unknown
Repository
github.com/JorgeIvanJH/IRISMiscTesting
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from JorgeIvanJH

Cite this page

web-to-md skill. Agent Mart. https://agentmart.dev/skills/jorgeivanjh-web-to-md (last updated 2026-10-24)