Markdown.New Crawl for Openclaw

A high-performance recursive crawler that transforms entire website sections into clean Markdown via a local-first API approach.

ctxinf
v1.0.0
Mar 21, 2026
0
735
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install markdown-new-crawl

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install markdown-new-crawl using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Markdown.New Crawl?

Markdown.New Crawl is an advanced tool within the Openclaw Skills ecosystem designed for deep data extraction. It enables developers and AI agents to recursively crawl specific site sections, converting HTML content into structured Markdown. By prioritizing a local-first access model via curl, it provides a robust alternative to standard browser-based scraping.

This skill is particularly effective for documentation harvesting and knowledge base construction. It handles complex tasks like asynchronous job polling, JavaScript rendering for SPAs, and granular URL filtering, ensuring that the resulting data is clean, formatted, and ready for LLM consumption or static site generation.

Markdown.New Crawl Use Cases

  • Extracting entire documentation sites for local LLM training or RAG pipelines.
  • Automating recursive site audits to gather content in a unified Markdown format.
  • Performing job-based crawl polling to monitor long-running extraction tasks.
  • Converting complex single-page applications (SPAs) into readable text using JS rendering.

How Markdown.New Crawl Works

  1. Initiate a crawl by sending a POST request to the API with a target URL and optional parameters like depth or page limits.
  2. Receive a unique Job ID from the service to track the progress of the asynchronous operation.
  3. Poll the status endpoint using the Job ID to monitor the crawl until completion.
  4. Retrieve the final payload, which defaults to concatenated Markdown or structured JSON if requested.
  5. Optionally cancel ongoing jobs or manage cached results through dedicated management endpoints.

Markdown.New Crawl Setup

To integrate this into your Openclaw Skills workflow, use standard terminal utilities. No complex authentication is required for basic operations.

# Start a new crawl job
curl -X POST "https://markdown.new/crawl" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://docs.example.com","limit":50}'

# Check job status
curl "https://markdown.new/crawl/status/<jobId>"

Markdown.New Crawl Data Schema & Taxonomy

The skill organizes data based on crawl jobs, offering flexible output formats for different integration needs.

Feature Specification
Default Format Concatenated Markdown documents
Structured Format JSON per-page records (via ?format=json)
Retention 14 days for job IDs and associated data
Page Limit 1-500 pages per individual crawl job
Depth 1-10 levels of recursive link following

Markdown.New Crawl Advanced Features

  • JavaScript Rendering: Support for dynamic content extraction in modern web apps.
  • Granular Filtering: Use includePatterns and excludePatterns wildcards to target specific site sections.
  • Cache Management: Control freshness with maxAge parameters (0 to 604,800 seconds).
  • Source Strategies: Choose between link following, sitemap discovery, or a hybrid approach.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*