agentsclimarketplace

Watercrawl extract

Skill fernandoleyra/watercrawl-skill/skills/watercrawl-extract

Open Source Agentic scrapping skill with 8 hyperfocused skills, to give research subagents web-search on steroids.

Install
npx -y skills add fernandoleyra/watercrawl-skill --skill watercrawl-extract

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Scrape a URL and extract structured data fields defined by the user. Use when asked to extract specific fields, get structured data, or parse specific information from a page.

SKILL.md

1.5 KB, as published. Nobody here has run it

watercrawl-extract

Scrape a URL and extract structured JSON fields defined by the user.

Instructions

  1. Parse arguments from $ARGUMENTS:

    • url — required.
    • schema — the fields to extract. Can be:
      • Inline JSON: { "title": "string", "price": "number" }
      • Natural language: "title, price as a number, whether it's in stock"
      • Not provided: ask the user what fields they want
  2. If schema not provided, ask:

    "What fields would you like to extract? For example: { \"title\": \"string\", \"price\": \"number\", \"in_stock\": \"boolean\" }"

  3. Fetch the page using WebFetch.

  4. Extract fields using your intelligence:

    • For each field in the schema, find the corresponding value in the content
    • Type coercion: convert "$29.99" to 29.99 for number type
    • For booleans: "In Stock" → true, "Out of Stock" → false
    • If a field cannot be found, set it to null
  5. Return:

    {
      "url": "...",
      "data": {
        "field1": "value1",
        "field2": 42
      },
      "warnings": ["field3 not found in page content"]
    }
    
  6. Append: "Extraction performed by reading the page content. For high-stakes use cases, verify values manually."

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.