Skill Claude CodeCodex
Solve CAPTCHAs using the 2Captcha API — reCAPTCHA v2/v3, Cloudflare Turnstile, hCaptcha, image captchas, Geetest, FunCaptcha. Use when a scraper hits a visible CAPTCHA that stealth/headed mode cannot bypass (Layer 5+ in anti-blocking escalation). Requires TWOCAPTCHAAPIKEY env var. Human-backed workers, $1/1000 solves…
Skill Claude CodeCodex
Give AI agents their own email inboxes using the AgentMail API. Use when building email agents, sending/receiving emails programmatically, managing inboxes, handling attachments, organizing with labels, creating drafts for human approval, or setting up real-time notifications via webhooks/websockets. Supports…
Skill Claude CodeCodex
Use Camoufox — a Firefox fork with C++-level fingerprint spoofing — for browser scraping when the user's real Chrome profile is not available. Activate on VMs, headless CI servers, remote machines without a GUI, or when torch needs multiple concurrent personas with rotated fingerprints. Detects via…
Skill Claude CodeCodex
Solve CAPTCHAs using CapMonster Cloud — reCAPTCHA v2/v3, Cloudflare Turnstile (including cfclearance cookies), GeeTest v3/v4, FunCaptcha, DataDome, AWS WAF, Imperva. AI-based solver, $0.60/1K reCAPTCHA (cheaper than 2Captcha), 10-30s latency. Use for cost-sensitive scraping or when 2Captcha fails. Requires…
Skill Claude CodeCodex
How to contribute to torch — the PR workflow, quality bar, skill authoring conventions, and what not to contribute. Activate when the user asks "how do I contribute / upstream / share / PR this", wants to submit a new skill, or needs the contribution guidelines for any kind of change to the repo. Covers site skills…
Skill Claude CodeCodex
Use authenticated residential, datacenter, or mobile proxies with Puppeteer to bypass IP-based rate limiting, geo-blocks, and bot-detection. Covers Bright Data, Oxylabs, Smartproxy, and generic proxy-chain usage. Use when getting 403/429 from the target's IP reputation system, when stealth/CAPTCHA solving alone isn't…
Skill Claude CodeCodex
Reverse-engineer a website's internal APIs, encrypted endpoints, WebSocket streams, and obfuscated JavaScript. Activates when the target data isn't in the HTML, when the site uses encrypted CloudFront/CDN payloads, when real-time streaming data is needed, or when the scrape skill's Phase 0-1 finds API calls that are…
Skill Claude CodeCodex
Scrape a website. Activates when user provides a URL to scrape, asks to extract data from a site, hits 403/blocking errors, or needs anti-bot evasion.
Skill Claude CodeCodex
Proven scraping playbook for airbnb.com search result pages (/s/ /homes). Server-streamed React app — listing data is in a JSON blob inside (or data-injector-instances on cached responses). No anti-bot, no captcha, no proxy, no browser needed. Plain Node fetch + a UA header works. Pagination is a flat ?cursor= param…
Skill Claude CodeCodex
Proven scraping playbook for amazon.com search result pages (/s?k=...). CloudFront + CAPTCHA wall blocks bare curl with HTTP 503, but a real Chrome session via the real Chrome debug port walks right through — no stealth, no proxy, no captcha. HTML is server-rendered; cheerio parses 22 results per page with stable…
Skill Claude CodeCodex
Proven scraping playbook for apple.com /shop/buy- configurator pages (Mac, iPhone, iPad, Watch). Server-rendered HTML with all product, pricing and configuration data embedded as JS object literals on window.PRODUCTSELECTIONBOOTSTRAP (and friends). Plain fetch — no anti-bot, no browser, no auth — but the blob is a JS…
Skill Claude CodeCodex
Proven scraping playbook for arxiv.org listing pages (e.g. /list/ /recent). Plain server-rendered HTML, no anti-bot, no JS needed — just fetch + cheerio. Use ?show=2000 to get every entry on a single page. Activate for any arxiv.org /list/ or /abs/ URL.
Skill Claude CodeCodex
Proven scraping playbook for booking.com searchresults.html pages. CloudFront-fronted JS challenge blocks bare curl (HTTP 202 with a script-only interstitial), but a real Chrome session via the real Chrome debug port walks through on first navigation — no captcha, no proxy, no login. Listings are rendered client-side…
Skill Claude CodeCodex
Proven scraping playbook for costco.com category listings (e.g. /laptops.html, /computers.html). Akamai Bot Manager hard-blocks bare curl with HTTP 403 on the HTML pages, but Costco's internal catalog API at gdx-api.costco.com/catalog/search/api/v1/search is a public JSON POST endpoint with no auth, no cookies, and no…
Skill Claude CodeCodex
Proven scraping playbook for digikey.com /en/products/category/ listings. Cloudflare challenge (cf-mitigated: challenge) blocks bare curl with HTTP 403, but a puppeteer connection to the user's real Chrome via the real Chrome debug port walks straight through with zero stealth, no captcha, no proxy, no auth. Listings…
Skill Claude CodeCodex
Proven scraping playbook for doordash.com. React SPA behind Cloudflare with server-rendered deal carousels on /browse/deals. Cloudflare challenge clears automatically with puppeteer-extra stealth (no captcha, no proxies, no login needed). Activate for any doordash.com target. Covers carousel selectors, price-token…
Skill Claude CodeCodex
Proven scraping playbook for ebay.com search result pages (/sch/i.html?nkw=...). eBay gates first requests with a "Pardon Our Interruption" splash challenge, but it clears automatically in a real Chrome session via the real Chrome debug port — no 2Captcha, no proxies, no login needed. Activate for any ebay.com /sch/…
Skill Claude CodeCodex
Proven scraping playbook for etsy.com search result pages (/search?q=...). DataDome protects the HTML edge (bare curl gets HTTP 403 with x-datadome: protected and a JS captcha shell), but a puppeteer-core connection to the user's real Chrome via 127.0.0.1:9222 walks through on first navigation — no 2Captcha, no proxy…
Skill Claude CodeCodex
Proven scraping playbook for github.com. Server-rendered HTML, no anti-bot on public pages (trending, repos, users). Plain fetch + cheerio works — no browser, no headers, no auth. Activate for any github.com scrape that doesn't need the REST/GraphQL API.
Skill Claude CodeCodex
Proven scraping playbook for news.ycombinator.com. Server-rendered static HTML (Arc/CL app), no CDN, no anti-bot, no JS required. Plain fetch + cheerio parses the front page in milliseconds. Activate for any news.ycombinator.com target. Covers front-page selectors, pagination, and the official Firebase API alternative.
Skill Claude CodeCodex
Proven scraping playbook for homedepot.com search results (/s/ ). Akamai Bot Manager hard-blocks raw curl with HTTP 403 (AkamaiGHost), but a puppeteer connection to the user's real Chrome via the real Chrome debug port walks straight through with zero challenges — no stealth plugin, no proxy, no captcha. Products are…
Skill Claude CodeCodex
Proven scraping playbook for huggingface.co model/dataset/space listings. Skip the browser entirely — Hugging Face exposes a public, unauthenticated JSON API at /api/models, /api/datasets, /api/spaces that mirrors every filter and sort on the HTML listing pages. No cookies, no tokens, no anti-bot. Cursor pagination…
Skill Claude CodeCodex
Proven scraping playbook for ikea.com /cat/ category pages (PLP). Server-rendered HTML with 24 products per page embedded as [data-testid="plp-product-card"] blocks, each carrying data-ref-id, data-product-name, data-price, data-currency attributes — no JSON blob needed, cheerio parses them straight. Cloudflare fronts…
Skill Claude CodeCodex
Proven scraping playbook for imdb.com. Next.js SPA behind CloudFront + AWS WAF (x-amzn-waf-action challenge on raw curl). Real Chrome via the real Chrome debug port sails past the challenge on first navigation — no captcha, no proxy. The clean path is NEXTDATA JSON on chart/list pages. Activate for any imdb.com target.