markdown-extract Skill

Extract clean markdown from any URL using the markdown.new API.

3,891 stars

Best use case

markdown-extract Skill is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Extract clean markdown from any URL using the markdown.new API.

Teams using markdown-extract Skill should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/markdown-extract/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/aviclaw/markdown-extract/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/markdown-extract/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How markdown-extract Skill Compares

Feature / Agentmarkdown-extract SkillStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Extract clean markdown from any URL using the markdown.new API.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# markdown-extract Skill

Extract clean markdown from any URL using the markdown.new API.

## Description

This skill converts web pages to clean markdown format using the markdown.new API. It supports multiple extraction methods and handles errors gracefully.

## Usage

```
!markdown-extract <url> [method]
```

### Arguments

- `url` (required): The URL to extract markdown from
- `method` (optional): Extraction method - `auto`, `ai`, or `browser`. Default: `auto`

### Examples

```bash
# Extract using default method (auto)
!markdown-extract https://example.com

# Extract using AI method
!markdown-extract https://example.com ai

# Extract using browser method
!markdown-extract https://example.com browser
```

## API

- GET `https://markdown.new/<url>` - Returns clean markdown (auto method)
- POST with JSON body `{url: "...", method: "browser|ai"}` - Specific extraction method

## Methods

- **auto**: Content negotiation with `Accept: text/markdown` header (fastest, default)
- **ai**: Cloudflare Workers AI `toMarkdown()` conversion
- **browser**: Headless browser rendering for JS-heavy pages (slowest but most complete)

## Error Handling

- Invalid URL: Returns error message
- Network failure: Returns retryable error
- API error: Returns error details
- Cloudflare block detection and fallback handling

Related Skills

recipe-video-extractor

3891
from openclaw/skills

Extract a structured cooking recipe from a shared video URL when the user sends `recipe <url>`. Prioritize caption/description and comments via browser automation, then use web search/fetch as fallback with clear source attribution.

keyword-extract

3891
from openclaw/skills

"Extract keywords and key phrases from text for SEO, tagging, and indexing"

markdown-sync-pro

3891
from openclaw/skills

Markdown 一键同步到 Notion、GitHub Wiki、Medium 等平台

adr-decision-extraction

3891
from openclaw/skills

Extract architectural decisions from conversations. Identifies problem-solution pairs, trade-off discussions, and explicit choices. Use when analyzing session transcripts for ADR generation.

saved-markdown

3891
from openclaw/skills

Publish Markdown, HTML, and Slides pages, reports, and documents anonymously to https://saved.md. **TRIGGER THIS SKILL when ANY of the following are true:** 1. User asks to CREATE content that is naturally document-like (reports, summaries, guides, docs, pages, tables, analysis) 2. User mentions markdown, publishing, sharing, or making something public 3. The response you're about to generate is structured text with headers, tables, or formatted sections 4. User asks for anything that could be a "page" or "document" output 5. User asks for slides, a slide deck, a presentation, or a "deck" output **When in doubt: TRIGGER.** (User can always choose local-only) **ALWAYS offer four options:** (1) one-shot publish, (2) interactive edit-before-publish, (3) local-only, (4) enhance.

YouTube Transcript Extraction

3891
from openclaw/skills

Extract high-quality transcripts from YouTube videos using multiple methods.

markdown-to-pdf

3891
from openclaw/skills

Convert Markdown files to beautiful PDF documents. Supports custom styling, code highlighting, and multiple output options. Use when users need to convert MD to PDF for documentation, notes, reports, or sharing.

extract

3891
from openclaw/skills

Turn a proven pattern or debugging solution into a standalone reusable skill with SKILL.md, reference docs, and examples.

File to Markdown — Skill

3891
from openclaw/skills

## Overview

invoice-extractor

3891
from openclaw/skills

Extract invoice information from images and PDF files using Baidu OCR API, export to Excel. Supports single file, multiple files, or entire directory processing. Use when the user mentions invoices, invoice recognition, extracting invoice data, processing receipts, converting invoices to Excel, or batch processing invoice files.

methodology-extractor

3891
from openclaw/skills

Batch extraction of experimental methods from multiple papers for protocol.

markdown-anything

3891
from openclaw/skills

Convert PDF, DOCX, XLSX, PPTX, images, audio, and 25+ file formats to clean Markdown using the Markdown Anything API.