fangnetz for Claude Code (signed mod)

Get UI designs for your app ideas. Get HTML + TailwindCSS code and a full screenshot of the design in output data. You will need a Anthropic Claude API Key to add in environment variables.

AI Web Scraper with Playwright Browser (No-Code, MCP)

data_rig/ai-web-scraper

Run a real Playwright browser as an AI web scraper. Extract structured data from any site using natural language—no selectors or scripts. Handles JS-heavy pages, pagination, and interactions. Built for MCP agents like OpenCode and Claude Code.

Broken Link Checker & Bulk URL Status Code Checker

kilndata/broken-link-checker

Check the HTTP status of thousands of URLs, or crawl a site and test every link on it. Status code, full redirect chain, final URL, response time, error type (DNS, SSL, timeout, 4xx, 5xx) and the page each broken link sits on. HEAD with GET fallback, polite per-domain limits.

Assess a proposed tool replacement against declared schemas, semantic identifiers, side effects and supplied paired fixtures. Auditable JSON; no tool execution.

LLM JSON Repair & Schema Validator

kadev-code/llm-json-repair

Fast, deterministic repair and schema validation for broken or malformed JSON from ChatGPT, Claude, DeepSeek, and local LLMs.

Shein Trending Fashion & Reviews Scraper

litezero/shein-trending-fashion-scraper

Extract trending fashion clothing, flash sales, customer review ratings, review volumes, SKUs, and discount pricing from Shein global marketplace.

Name, brand, price, currency, stock, rating, images, SKU/GTIN and variants from a product page's schema.org JSON-LD, microdata or Open Graph tags. One JSON record per URL. Product Data Extractor API.

Pre-flight check for Shopify and WooCommerce product import CSV/XLSX files. Replays ~40 importer rules (Default Title trap, variation linking, duplicate SKUs, prices, image links, Excel mangling, mojibake), auto-fixes safe issues with a change log and splits importer-safe chunks.

Check structured evidence against source, freshness and confidence requirements. Return SUPPORTED, CONTRADICTED or INSUFFICIENT with auditable reasons. No LLM calls.

Trust check before your AI agent calls or pays another agent: validates A2A Agent Cards (v1.0/v0.3), performs a real MCP handshake (tools, latency, OAuth) and decodes x402 payment offers (network, USDC, price, payTo, red flags). No payment made. Pay per check.