New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Extract

by RealEstateWebTools in RealEstateWebTools/property_web_scraper

Run a quick extraction test against a URL or HTML file. An agent skill from RealEstateWebTools/property_web_scraper.

MITAuto-check passedBusiness, Finance & HR

Install Extract

skills CLI
$ npx skills add RealEstateWebTools/property_web_scraper --skill extract -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install RealEstateWebTools/property_web_scraper extract --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/RealEstateWebTools/property_web_scraper.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/extract .claude/skills/extract && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
extract
GitHub stars
132
Token cost
~787 tokens
SKILL.md length
283 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Run a quick extraction test against a URL or HTML file. An agent skill from RealEstateWebTools/property_web_scraper.

  • Works in 2 steps: Run the capture-fixture utility which… → Show the user the extraction results…
  • Tasks that involve Web scraping
  • SKILL.md covers Inputs, Workflow and Output format
  • Calls npx and npm; reaches rightmove.co.uk

What it does

Extract is an agent skill from RealEstateWebTools/property_web_scraper. Run a quick extraction test against a URL or HTML file. Shows extracted fields, quality grade, and diagnostics.

Its SKILL.md is about 790 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Business, Finance & HR, covering Web scraping. The repository describes itself as: Web based UI to make processing scraped data from real estate websites super simple. The licence is MIT.

When your agent uses it

  • Tasks that involve Web scraping

Example prompts

  • “/extract”

Requirements

  • Node.js

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. Run the capture-fixture utility which fetches, extracts, and previews
  2. Show the user the extraction results including

What it can do on your machine

Read from SKILL.md and the folder at commit 02088f3. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npx
    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • rightmove.co.uk

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Extract loads about 787 tokens when it runs. Until then it costs about 30 tokens; SKILL.md has 283 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~30
When it runs · the whole SKILL.md, loaded when a task matches
~787

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from RealEstateWebTools/property_web_scraper at commit 02088f3, republished under its MIT licence (© RealEstateWebTools). 283 words, ~787 tokens.

Download SKILL.mdSave it as .claude/skills/extract/SKILL.md (or your agent's skills folder).
name
extract
description
Run a quick extraction test against a URL or HTML file. Shows extracted fields, quality grade, and diagnostics.
argument-hint
url-or-file-path

Quick Extraction Test

Run the extraction pipeline against a URL or HTML file and display the results. This is the fastest way to test whether a scraper is working.

Inputs

$ARGUMENTS should be one of:

  • A property listing URL (e.g. https://www.rightmove.co.uk/properties/123456)
  • A path to a local HTML file
  • A scraper name to test against its existing fixture

If nothing is provided, ask the user what they want to extract.

Workflow

Option A: Extract from a URL (uses capture-fixture)

  1. Run the capture-fixture utility which fetches, extracts, and previews:

    bash
    cd astro-app && npm run capture-fixture -- <url>

  2. Show the user the extraction results including:

    • Quality grade and extraction rate
    • All extracted fields with values
    • Any empty fields or warnings
    • Content analysis (blocked page detection, JS-only detection)
Option B: Extract from a local HTML file

  1. Run capture-fixture with --file:

    bash
    cd astro-app && npm run capture-fixture -- --file <path> --url <source_url> --no-extract

    Note: --url is required to identify the scraper mapping. If the user didn't provide a URL, ask for the source website.

  2. Then run the extraction test:

    bash
    cd astro-app && npx vitest run test/lib/scraper-validation.test.ts -t "<scraper_name>"
Option C: Test an existing fixture

  1. Run the validation test for the specified scraper:

    bash
    cd astro-app && npx vitest run test/lib/scraper-validation.test.ts -t "<scraper_name>"

  2. Read the test output to show extraction results.

Option D: Programmatic extraction (for debugging)

If the user wants to see the raw extraction result, write a small inline script:

bash
cd astro-app && npx tsx -e "
import { readFileSync } from 'fs';
import { extractFromHtml } from './src/lib/extractor/html-extractor.js';
const html = readFileSync('<fixture_path>', 'utf-8');
const result = extractFromHtml({
  html,
  sourceUrl: '<url>',
  scraperMappingName: '<name>',
});
console.log(JSON.stringify({
  success: result.success,
  grade: result.diagnostics?.qualityGrade,
  rate: result.diagnostics?.extractionRate,
  weightedRate: result.diagnostics?.weightedExtractionRate,
  criticalMissing: result.diagnostics?.criticalFieldsMissing,
  fields: result.properties[0],
}, null, 2));
"
Option E: Extract via MCP tool

When the property-scraper MCP server is running, the extract_property tool can perform extraction directly. Pass the HTML content and source URL to get full diagnostics without needing to write inline scripts.

Output format

Present results in a clear format:

  • Quality: Grade (A/B/C/F), extraction rate, weighted rate
  • Critical fields: title, price_string, price_float — highlight if missing
  • All fields: grouped by section (text, int, float, boolean, images, features, defaults)
  • Warnings: empty fields, blocked page detection, JS-only detection

© RealEstateWebTools, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/extract of RealEstateWebTools/property_web_scraper.

Open the folder on GitHubat commit 02088f3

Compare with similar skills

Extract next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Extract compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Extract this skillRealEstateWebTools/property_web_scraper132—~787Automated safety check: PassMIT
Korean Government Grant Searchdjfksjd/ir-search392—~3.5kAutomated safety check: NotesMIT
Apify Buying Signal Detectionapify/awesome-skills262—~5.1kAutomated safety check: NotesApache-2.0
Company Hiring Intelligencetinyfish-io/tinyfish-cookbook2.2k—~3.6kAutomated safety check: PassMIT
Tradingviewgauss314/skills245—~4.7kAutomated safety check: PassMIT
Companiesmarketcapgauss314/skills245—~970Automated safety check: PassMIT

Similar skills

  • Korean Government Grant Search

    djfksjd/ir-search

    Surveys open Korean government startup and R&D support programs and sorts them by fit with your project, checking eligibility against the original notices.

    392 GitHub stars~3.5k tokensUpdated 2 mo ago
    Business, Finance & HRAuto-check: notes

  • Apify Buying Signal Detection

    apify/awesome-skills

    Official

    Set up a recurring buying-signal detection pipeline that finds companies showing buying intent across three signal types — job postings (hiring for the persona), fundraising events (recent raises)…

    262 GitHub stars~5.1k tokensUpdated 15 days ago
    Business, Finance & HRAuto-check: notes

  • Company Hiring Intelligence

    tinyfish-io/tinyfish-cookbook

    Reverse-engineer what a company is building by scraping their job postings, careers page, LinkedIn Jobs, and engineering blog using TinyFish web agents.

    2.2k GitHub stars~3.6k tokensUpdated 6 days ago
    Business, Finance & HRAuto-check passed

  • Tradingview

    gauss314/skills

    Datos de mercado de TradingView via APIs publicas internas sin auth: Scanner (~300 columnas con quote/indicadores tecnicos/financials/earnings/ratings/targets), Symbol Search v3 (ISIN/CUSIP/CIK)…

    245 GitHub stars~4.7k tokensUpdated 3 mo ago
    Business, Finance & HRAuto-check passed

  • Companiesmarketcap

    gauss314/skills

    Scraper de CompaniesMarketCap: rankings (marketcap, earnings, revenue, employees, ratios), stock history y ETF holdings.

    245 GitHub stars~970 tokensUpdated 3 mo ago
    Business, Finance & HRAuto-check passed

  • Investing

    gauss314/skills

    Investing.com via HTML scrape: cotizaciones, historico OHLCV, fundamentals (income/balance/cashflow/ratios), dividendos, earnings, perfil de empresa.

    245 GitHub stars~3.5k tokensUpdated 3 mo ago
    Business, Finance & HRAuto-check passed

More from RealEstateWebTools/property_web_scraper

  • Add Scraper

    RealEstateWebTools/property_web_scraper

    Add support for scraping property listings from a new website.

    132 GitHub stars~1.4k tokensUpdated 2 mo ago
    Auto-check passed

  • Fix Scraper

    RealEstateWebTools/property_web_scraper

    Diagnose and fix a broken scraper mapping. An agent skill from RealEstateWebTools/property_web_scraper.

    132 GitHub stars~1k tokensUpdated 2 mo ago
    Auto-check passed

  • Diagnose Extraction

    RealEstateWebTools/property_web_scraper

    Deep-dive diagnostics on a low-quality or failed extraction.

    132 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed

  • Scraper Status

    RealEstateWebTools/property_web_scraper

    Quick overview of all scrapers — quality grades, extraction rates, and coverage gaps.

    132 GitHub stars~364 tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Extract

What does Extract do?

Run a quick extraction test against a URL or HTML file. An agent skill from RealEstateWebTools/property_web_scraper. Extract is an agent skill from RealEstateWebTools/property_web_scraper. Run a quick extraction test against a URL or HTML file.

When should I use Extract?

Extract fits situations like: tasks that involve Web scraping.

How do I install Extract in Claude Code?

Run `npx skills add RealEstateWebTools/property_web_scraper --skill extract -a claude-code`. Or copy the skill folder (.claude/skills/extract in RealEstateWebTools/property_web_scraper) into .claude/skills/extract in your project. Claude Code loads it when a task matches its description.

How do I install Extract in Codex?

Run `npx skills add RealEstateWebTools/property_web_scraper --skill extract -a codex`. Or copy the skill folder (.claude/skills/extract in RealEstateWebTools/property_web_scraper) into .agents/skills/extract in your project. Codex loads it when a task matches its description.

Can I use Extract in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add RealEstateWebTools/property_web_scraper --skill extract -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/extract, .gemini/skills/extract, .github/skills/extract and .opencode/skills/extract in your project.

What does Extract need to run?

Going by SKILL.md and its folder, Extract needs the command-line tools its instructions call (npx and npm). Our summary lists: Node.js.

Does Extract access the network?

SKILL.md names 1 domain. In commands or code: rightmove.co.uk; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Extract safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Extract use?

Extract is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Extract use?

About 787 tokens (SKILL.md is roughly 3.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Extract?

Skills that share tags, products or a category with Extract: Korean Government Grant Search (djfksjd/ir-search, 392 stars), Apify Buying Signal Detection (apify/awesome-skills, 262 stars), Company Hiring Intelligence (tinyfish-io/tinyfish-cookbook, 2.2k stars) and Tradingview (gauss314/skills, 245 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Extract?

RealEstateWebTools (a GitHub organization) maintains it in RealEstateWebTools/property_web_scraper, which has 132 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on July 21, 2026.

Source: RealEstateWebTools/property_web_scraper on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.