agentleFS
context-dot-devcontext-dot-dev/cursor-plugin/skills/context-scrape/SKILL.md

context-scrape

Skill9 starsChanged 3 months agoMITView on GitHub

Scrape or capture one known webpage with Context.dev. Use when the user supplies a URL and wants its readable content, raw HTML, images, a screenshot, page metadata, or content revealed through explicitly requested browser actions.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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 the Context.dev web-scrape MCP tool and request only the formats the user needs:

    line 8
  2. Distinctive:

    Default to Markdown unless the task specifically needs HTML, images, or pixels.

    line 21
  3. Very specific:

    Use web-search when the URL is unknown, web-crawl for several linked pages, and submit-batch for large asynchronous collections.

    line 28

≈ “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

Scrape one page

Use the Context.dev web-scrape MCP tool and request only the formats the user needs:

NeedFormat
Clean readable content for analysis or RAGformats: { markdown: true }
Raw DOM or HTML for code-level inspectionformats: { html: true }
Images and their source metadataformats: { images: true }
Visual rendering of the pageformats: { screenshot: true }
Schema-shaped JSONformats: { json: true } with jsonParams.schema

Workflow

  1. Pass a complete http:// or https:// URL.
  2. Default to Markdown unless the task specifically needs HTML, images, or pixels.
  3. Request main content or selectors only when they improve the requested output.
  4. Set cache age to zero only when the user explicitly needs a fresh fetch.
  5. Return the requested content without adding facts that are absent from the page.

Browser actions can click or type on external sites. Run only actions required by the user's request, and never submit a form, purchase, message, or other state-changing action without explicit authorization.

Use web-search when the URL is unknown, web-crawl for several linked pages, and submit-batch for large asynchronous collections.

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.