# Pricewin Hotel Deal Finder > Encuentra el hotel más barato comparando precios en vivo en Booking.com, Agoda, Google Hotels y OpenTravel para cualquier ciudad y fechas, con picks de mejor valor, más barato y calidad, y enlaces de reserva. Fuente: https://skillsagentes.com/skills/price-win/pricewin-skills-hub/pricewin-hotel-deal-finder Markdown: https://skillsagentes.com/skills/price-win/pricewin-skills-hub/pricewin-hotel-deal-finder.md Repositorio: https://github.com/Price-Win/pricewin-skills-hub Autor: Price-Win Licencia: MIT-0 Actualizado: hace 22 días Coste de contexto: 148 tok instalada, 2.9k tok al activarse, 27.1k tok con todos los archivos del bundle Bundle: 12 archivos, 106 KB Permisos que pide: ninguno declarado ## Instalación Un skill son archivos markdown: los mismos archivos valen para cualquier agente y lo único que cambia es el directorio de destino, es decir la bandera `--agent`. Añade `-g` para instalarlo en todos los proyectos de la máquina. ```bash # Claude Code npx -y skills add Price-Win/pricewin-skills-hub --skill pricewin-hotel-deal-finder --agent claude-code # Cursor npx -y skills add Price-Win/pricewin-skills-hub --skill pricewin-hotel-deal-finder --agent cursor # Codex npx -y skills add Price-Win/pricewin-skills-hub --skill pricewin-hotel-deal-finder --agent codex # Gemini CLI npx -y skills add Price-Win/pricewin-skills-hub --skill pricewin-hotel-deal-finder --agent gemini # Windsurf npx -y skills add Price-Win/pricewin-skills-hub --skill pricewin-hotel-deal-finder --agent windsurf # Cline npx -y skills add Price-Win/pricewin-skills-hub --skill pricewin-hotel-deal-finder --agent cline ``` ## Qué hace - Compara precios de hotel en vivo entre Booking.com, Agoda, Google Hotels y OpenTravel con un solo comando - Devuelve picks de mejor valor, más barato y calidad, normalizados a USD, con enlaces de reserva directos - Ejecuta un daemon Patchright con sigilo para ciudades con protección anti-bot fuerte, sin claves API ni servidor MCP - Formatea la salida en tarjetas por niveles listas para enviar al usuario tal cual ## Cuándo usarla - Preguntar por precios o chollos de hotel, la tarifa más barata o cuál OTA es más económica - Comparar precios de hotel para una ciudad y fechas concretas - Buscar un hotel bajo un presupuesto o cerca de un punto de referencia ## Qué la activa - "Encuéntrame un hotel en Tokio para el 12-15 de agosto" - "¿Es más barato Booking o Agoda para este hotel?" - "Compara precios de hotel en Bangkok bajo $100" ## Antes de instalar - Necesita `node` y `npx` instalados en la máquina; no requiere claves API ni servidor MCP. - Necesita en el PATH: node, npx - makes network requests ## Archivos - SECURITY.md — 6 KB - SKILL.md — 11 KB - bin/browse.js — 19 KB - bin/daemon.js — 24 KB - bin/search.js — 22 KB - install.sh — 963 B - lib/browser-state.js — 2 KB - lib/dom-extract.js — 5 KB - lib/selector-cache.js — 5 KB - lib/snapshot.js — 8 KB - package-lock.json — 2 KB - package.json — 920 B ## SKILL.md Reproducido tal cual desde Price-Win/pricewin-skills-hub bajo MIT-0. Esta sección es el documento original y está en inglés. # PriceWin Hotel Deal Finder > **Compare live hotel prices across Booking.com, Agoda, Google Hotels & OpenTravel in one command** — and get back ranked best-value, cheapest, and quality picks with direct booking links. Stop opening five OTA tabs to find the real cheapest rate. Ask your agent *"find me a hotel in Tokyo for 12–15 Aug, 2 guests"* and this skill returns a clean, ranked comparison in ~30–60 seconds (cached cities). **Invoke this skill for questions like:** - "What's the cheapest hotel in `` for ``?" - "Is Booking.com or Agoda cheaper for this hotel?" - "Compare hotel prices for ``, `` guests." - "Find me a hotel under $``/night in ``." - "Best-value place to stay near `` on ``?" Each returns the same one-command answer below — no clarifying round-trip needed. **What you get from one command:** - 🥇 Best value · 🥈 Cheapest · 🥉 Quality — picked side-by-side - Real per-night prices from up to **4 sources**, normalized to **USD** - **Clickable booking links** straight to the cheapest OTA for each hotel - Works for **any city worldwide** — including bot-hardened ones (Shanghai, Hangzhou, Bangkok…) via a stealth Patchright daemon - No API keys, no MCP server — `node`/`npx` is all you need **Sample result:** ``` 🏨 Tokyo • Aug 12–15 • 3 nights • 2 guests ━━━━━━━━━━━━━━━━━━━━ 🥇 BEST VALUE Shinjuku Granbell Hotel ✅ agoda 💰 $118/night booking 💰 $131/night → Save $13 vs Booking 🥈 CHEAPEST APA Hotel Shinjuku ✅ google 💰 $94/night 📊 18 hotels | agoda, booking, google, opentravel • prices in USD ``` **Install:** ```bash npx skills add https://github.com/Price-Win/pricewin-skills-hub --skill pricewin-hotel-deal-finder ``` --- ## How to use this skill **One command does the whole job — you normally won't need to ask clarifying questions first. Infer the parameters (below) and run it:** ```bash cd {baseDir} && node bin/search.js "" en-us ``` `{baseDir}` is this skill's install directory (auto-resolved by the runtime). If your runtime does not substitute it, `cd` into the folder that contains this `SKILL.md` (the one with `bin/search.js`). Avoid hardcoding a `~/.hermes/...` or `~/.openclaw/...` path — it differs per platform. Example: ```bash cd {baseDir} && node bin/search.js "Hangzhou" 2026-06-10 2026-06-13 2 en-us ``` The script handles everything automatically: daemon launch, Agoda cache lookup, Google + Booking inline search, OpenTravel API lookup (all cities), discovery for new cities, and formatted tier-card output. Run it and send the output to the user. **Infer the parameters instead of asking** (ask only if the city or dates are genuinely ambiguous): - **Year:** use the current year from today's date unless the user states otherwise. If the requested day/month has already passed this year, assume next year. (Get today's date with `date +%Y-%m-%d` if unsure.) - **"10-13/6"** → `-06-10 -06-13` — fill `` from the rule above - **"2 guests" / "2 people"** → `2` adults - **Locale:** language/region code passed to the OTAs (controls site language + region). Default `en-us`. Prices are in USD (Google Hotels is requested with `gl=us&curr=USD`); other sources follow the locale you pass. One `search.js` run is the whole workflow — no Python, curl, or ad-hoc scraping is needed on top of it. --- ## Operating rules — how to get reliable results **RULE 0 — Drive the browser only through `search.js` (via your terminal/shell tool). The native browser tools don't work here.** This skill relies on a stealth Patchright daemon. The runtime's native tools — `browser_navigate` / `browser_open`, `browser_click`, `browser_type` / `browser_fill`, `browser_snapshot`, `browser_close`, any other `browser_*`, and subagent delegation (`delegate_task` / `spawn_agent`) — will fail on this task, so don't reach for them: - Those native tools spawn a vanilla Chromium with no stealth, so Booking.com and Agoda detect the bot within seconds; the requests hang until the runtime kills them ("Command timed out after 30/60 seconds"). That burns 5+ minutes and returns nothing. The Patchright daemon that `search.js` launches survives bot-detection. - Delegated subagents start with empty history and no skill context, so they fall back to Python/curl scraping that gets bot-blocked immediately. Run the skill in the current agent. The one path that works: ``` cd {baseDir} && node bin/search.js ... ``` **RULE 1 — Let `search.js` do the scraping; don't scrape an OTA yourself.** Avoid calling `browse.js` directly, doing `goto`/`click`/`type` in the browser, building Agoda/Booking/Google URLs by hand, calling the OpenTravel API separately, or launching the daemon yourself. `search.js` already drives the stealth daemon through a careful flow that survives bot-detection — it handles Agoda discovery internally for EVERY city (including Chinese cities like Shanghai, Hangzhou, etc.). Manually navigating an OTA is the #1 cause of failure: it trips Agoda/Booking anti-bot ("detect automation", "redirect to homepage", "problem completing your search") and gets the IP blocked. Run `search.js` once and send its output. If a source looks "missing", see RULE 4 rather than fetching it by hand. **RULE 2 — First-time city discovery takes 2–4 minutes.** If `search.js` output contains `"discovering"` or `"launching"` messages, tell the user: "First time searching this city — discovering selectors, this takes about 2–4 minutes..." and wait for the result rather than retrying or aborting. **RULE 3 — Send the output exactly.** `search.js` outputs formatted tier cards ready to send. Copy the output directly into your response. Do not reformat, summarize, or abbreviate it. **RULE 3a — Preserve the markdown hyperlinks.** Every hotel name in the output is already wrapped as `[Hotel Name](https://booking-url...)` — a clickable hyperlink. Keep it intact: don't split the URL onto a separate `🔗 https://...` line, don't replace `[Hotel Name](url)` with plain text, keep OTA names lowercase ("google", not "Google"), and keep section titles as-is ("📋 More good deals"). The output is Telegram-MarkdownV2-ready; sending it verbatim gives the user clickable hotel names with hidden URLs (clean UI). **RULE 3b — Hyperlink hotel names in your own commentary too.** If you add a suggestion or commentary section after the output, wrap every hotel name you mention as `[Hotel Name](url)` using the same URL the script printed for that hotel, rather than plain text. **RULE 4 — Partial results are normal — send them as-is rather than fixing by hand.** A source can be absent from a run (e.g. Agoda blocked this run, or OpenTravel has no inventory for the city). That's fine — send the tier cards with whatever sources are present; the footer (`📊 N hotels | • prices in USD`) lists exactly what was found. Fetching the missing source via the browser or a direct URL tends to trip anti-bot and make things worse, so avoid it. If `search.js` errors out entirely, tell the user what failed in one line and show any partial output it printed above the error. For more coverage, the one reliable retry is running the same `search.js` command again (anti-bot is often transient). --- ## Output Format Reference `search.js` prints tier cards in this format — you send this directly to the user: The hotel name is a Markdown link to its cheapest OTA. Price rows carry NO links and the OTA key is shown lowercase (`agoda`/`booking`/`google`/`opentravel`). There are no star ratings or area lines — the script does not have that data. ``` 🏨 • – • nights • guests ━━━━━━━━━━━━━━━━━━━━ 🥇 BEST VALUE []() ✅ agoda 💰 /night booking 💰 /night opentravel 💰 /night → Save vs Booking 🥈 CHEAPEST []() ✅ google 💰 /night agoda 💰 /night 🥉 QUALITY []() ✅ booking 💰 /night agoda 💰 /night 📋 More good deals — Agoda — • []() — agoda: | booking: — Booking — • []() — booking: — Google — • []() — google: — OpenTravel — • []() — opentravel: 💡 Tip: [Book on ]() — /night 📊 hotels | • prices in USD ``` All prices are shown in USD. Agoda, Google and OpenTravel geo-lock to VND by IP and are converted via a live FX rate; Booking returns USD natively. Only sources that actually returned data are listed in the footer. --- ## Limitations - First search per city pays the Agoda discovery cost (2–4 minutes). Google and Booking are inline (no discovery); OpenTravel is a direct API call. - Subsequent searches reuse the Agoda cache and complete in ~30–60 seconds. ## Security & data handling Runs locally, needs no API keys, and collects no personal data — the only data sent out is the search query (city, dates, guests). Scraped hotel text is treated as untrusted: `sanitizeText()` in `bin/search.js` strips control/zero-width/bidi and markdown-control characters before any of it reaches model output, and booking links are restricted to `http(s)`. The local browser daemon is **loopback-only, token-authenticated** (a per-run token in a `0600` state file), rejects non-loopback `Host` headers against DNS rebinding, and keeps the **Chromium sandbox enabled** — `--no-sandbox` is used only where it cannot work (root on Linux, or explicit `PRICEWIN_NO_SANDBOX=1`). Full disclosure of commands run, downloads, and network egress is in [`SECURITY.md`](./SECURITY.md). ## Dónde encaja - Categoría: [Automatización](https://skillsagentes.com/categorias/automatizacion.md) — Flujos de varios pasos que se ejecutan sin supervisión. - Creador: [Price-Win](https://skillsagentes.com/creators/price-win.md) — 0 skills en el directorio - [Todas las skills](https://skillsagentes.com/skills.md) - [Ranking de instalaciones](https://skillsagentes.com/ranking.md) ## Otras skills del mismo repositorio - [Pricewin Hotel Search](https://skillsagentes.com/skills/price-win/pricewin-skills-hub/pricewin-hotel-search.md): Busca hoteles en vivo en Agoda, Booking.com, Traveloka y OpenTravel con precios en tiempo real para fechas concretas. Para consultar precios de hotel, comparar OTAs o encontrar habitaciones. - [Pricewin Booking Assistant](https://skillsagentes.com/skills/price-win/pricewin-skills-hub/pricewin-booking-assistant.md): Recomienda habitaciones y completa una reserva real de principio a fin en OpenTravel direct: enlace de pago (QR, tarjeta o PayPal), estado del pago, reenvío o cancelación. Para hoteles solo-OTA, da el enlace directo. - [Pricewin Price Comparison](https://skillsagentes.com/skills/price-win/pricewin-skills-hub/pricewin-price-comparison.md): Compara tarifas de habitación en vivo entre Booking.com, Agoda, Traveloka y OpenTravel para fechas concretas: qué OTA es más barata, precio por habitación y condiciones de cancelación gratuita. - [Pricewin Flight Search](https://skillsagentes.com/skills/price-win/pricewin-skills-hub/pricewin-flight-search.md): Busca tarifas de vuelo en vivo por ruta y fecha en Agoda, Trip.com y Traveloka, ida o ida y vuelta, con aerolínea, horarios, escalas, duración y enlace directo de reserva. Para precios de vuelos o comparar aerolíneas. --- Skills Agentes · [Índice de páginas en markdown](https://skillsagentes.com/sitemap.md) · [Inicio](https://skillsagentes.com/index.md)