agentleFS
Sign inStart free
claude-worldclaude-world/cf-browser/skills/content-extractor/SKILL.md

content-extractor

Skill9 starsChanged 8 months agoMITView on GitHub

Extract structured content from web pages using CF Browser MCP tools

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. wulaosiji/skills★ 28same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Call browser_markdown with the URL

    line 23
  2. Very specific:

    Call browser_json with URL and extraction prompt

    line 32
  3. Very specific:

    Call browser_scrape with URL and selectors array

    line 40
  4. Very specific:

    Call browser_screenshot with URL and optional viewport dimensions

    line 55
  5. Distinctive:

    Read the returned private temporary PNG path to inspect/show the image

    line 56
  6. Distinctive:

    If persistence is requested, copy it to the requested output before the MCP process exits

    line 57

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Content Extractor

Extract content from JavaScript-rendered web pages using CF Browser MCP tools.

Prerequisites

CF Browser MCP server must be configured (see the CF Browser quick start).

Modes

Analyze the user's intent and select the appropriate mode:

Mode 1: Read Page Content

Trigger: "read this page", "get content from", "what does X say" Tool: browser_markdown Workflow:

  1. Call browser_markdown with the URL
  2. Clean the markdown (remove navigation, footer boilerplate)
  3. Return formatted content with source attribution

Mode 2: Extract Structured Data

Trigger: "extract products", "get prices", "pull data from" Tool: browser_json Workflow:

  1. Determine extraction prompt from user intent
  2. Call browser_json with URL and extraction prompt
  3. Format and return structured JSON

Mode 3: Scrape Specific Elements

Trigger: "get the headlines", "extract article titles", "find all images" Tool: browser_scrape Workflow:

  1. Determine CSS selectors from user intent
  2. Call browser_scrape with URL and selectors array
  3. Post-process and return results

Mode 4: Discover Links

Trigger: "find all links", "list pages on", "discover URLs" Tool: browser_links Workflow:

  1. Call browser_links with the URL
  2. Filter/categorize links (internal, external, resource)
  3. Return organized link list

Mode 5: Visual Capture

Trigger: "screenshot", "show me what X looks like", "capture page" Tool: browser_screenshot Workflow:

  1. Call browser_screenshot with URL and optional viewport dimensions
  2. Read the returned private temporary PNG path to inspect/show the image
  3. If persistence is requested, copy it to the requested output before the MCP process exits

Output Format

  • For text: Clean markdown with source URL attribution
  • For data: JSON with clear field names
  • For images: File path + display
  • Truncate if output exceeds 50K characters

Examples

"Read the Hono documentation homepage"
→ browser_markdown("https://hono.dev")

"Extract all pricing tiers from Vercel"
→ browser_json("https://vercel.com/pricing", prompt="Extract all pricing tiers with name, price, and features")

"Get all h2 headings from this blog post"
→ browser_scrape("https://example.com/blog/post", selectors=["h2"])

"Screenshot the landing page at mobile width"
→ browser_screenshot("https://example.com", width=375, height=812)

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.

Check your setup, free