How to install pricewin-deal-finder
npx skills add https://github.com/price-win/pricewin-skills-hub --skill pricewin-deal-finderFull instructions (SKILL.md)
Source of truth, from price-win/pricewin-skills-hub.
name: pricewin-deal-finder description: "Hotel price comparison & deals across Booking, Agoda, Google Hotels, and OpenTravel for given travel dates and guest count. Use for hotel prices, deals, or comparing OTA rates." version: 0.8.3 author: PriceWin platforms: [linux, macos, windows] tags: [hotel, travel, booking, agoda, google, opentravel, price-comparison, deals, ota] metadata: openclaw: requires: bins: [node, npx] envVars: - name: OPENTRAVEL_API_BASE_URL required: false description: Override the OpenTravel API host (default https://api.opentravel.one). emoji: "๐จ" homepage: https://github.com/Price-Win/pricewin-skills-hub
PriceWin Deal Finder
๐จ IMPORTANT โ HOW TO USE THIS SKILL
ONE command does everything. Run this as your FIRST action โ no clarifying questions first:
cd {baseDir} && node bin/search.js "<city>" <checkInYYYY-MM-DD> <checkOutYYYY-MM-DD> <adults> 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). Do NOT hardcode a ~/.hermes/... or ~/.openclaw/... path โ it differs per platform.
Example:
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. Just run it and send the output to the user.
DO NOT ask clarifying questions first. Just run the command. Infer all parameters:
- 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-%dif unsure.) - "10-13/6" โ
<year>-06-10 <year>-06-13โ fill<year>from the rule above - "2 guests" / "2 people" โ
2adults - Locale: language/region code passed to the OTAs (controls site language + region). Default
en-us. Prices are in USD (Google Hotels is requested withgl=us&curr=USD); other sources follow the locale you pass.
DO NOT use any other approach. No Python scripts, no curl, no browser tools, no subagents. This one command is all you need.
๐จ CRITICAL RULES โ FOLLOW EVERY TIME
RULE 0 โ FORBIDDEN TOOLS. Read this twice. This skill drives a long-running Patchright daemon via the terminal tool ONLY. Your runtime exposes several other tools that LOOK convenient but are STRICTLY FORBIDDEN inside this skill:
โ browser_navigate / browser_open โ FORBIDDEN
โ browser_click โ FORBIDDEN
โ browser_type / browser_fill โ FORBIDDEN
โ browser_snapshot โ FORBIDDEN
โ browser_close โ FORBIDDEN
โ Any other browser_* native tool โ FORBIDDEN
โ delegate_task / spawn_agent / sub-agent delegation โ FORBIDDEN
Why: those native tools spawn a vanilla Chromium without stealth, so Booking.com and Agoda detect the bot within seconds and the requests just hang until the runtime kills them with "Command timed out after 30/60 seconds". You will burn 5+ minutes on timeouts and the user will get nothing. The Patchright daemon launched via terminal survives bot-detection.
Delegated subagents start with empty history and no skill context โ they will always fall back to Python/curl scraping, which gets bot-blocked immediately. This skill must run entirely in the current agent, using only the terminal tool.
โ
The ONLY allowed way to drive a browser in this skill is via terminal:
terminal: cd {baseDir} && node bin/search.js ...
RULE 1 โ search.js handles everything. NEVER scrape an OTA yourself. Do not manually call browse.js commands, do not goto/click/type in the browser, do not build Agoda/Booking/Google URLs by hand, do not call the OpenTravel API separately, do not try to launch the daemon yourself. search.js already drives the stealth daemon through a careful flow that survives bot-detection โ 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. Your ONLY job is to run search.js once and send its output. If you think a source is "missing", re-read RULE 4 โ do NOT go fetch it by hand.
RULE 2 โ First-time city discovery takes 2โ4 minutes. If search.js output contains "discovering" or "launching" messages, tell the user: "First time searching this city โ discovering selectors, this takes about 2โ4 minutes..." and wait for the result. Do NOT retry or abort.
RULE 3 โ 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 โ PRESERVE MARKDOWN HYPERLINKS. Every hotel name in the output is already wrapped as [Hotel Name](https://booking-url...). This is a clickable hyperlink โ DO NOT:
- Strip the markdown and show the URL on a separate
๐ https://...line - Replace
[Hotel Name](url)with plain text - Capitalize OTA names ("google" stays "google", not "Google")
- Rename sections โ "๐ More good deals" stays exactly
The output is Telegram-MarkdownV2-ready. Sending it as-is gives the user clickable hotel names with hidden URLs (clean UI).
RULE 3b โ If you DO add a suggestion / commentary section after the output, every hotel name you mention MUST also be a markdown hyperlink [Hotel Name](url) using the SAME URL the script printed for that hotel. Never write a hotel name as plain text in your own commentary.
RULE 4 โ Partial results are NORMAL and acceptable. Never "fix" them by hand. A source can be absent from the output (e.g. Agoda blocked this run, or OpenTravel has no inventory for the city). That is FINE โ send the tier cards with whatever sources are present. The footer (๐ N hotels | <sources> โข prices in USD) lists exactly what was found. Do NOT try to fetch the missing source via the browser, a direct URL, or any other tool โ that triggers anti-bot and makes things worse. If search.js errors out entirely, tell the user what failed in 1 line and show any partial output it printed above the error. If you want more coverage, the only valid 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 โ 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 โ the script does not have that data.
๐จ <city> โข <d1>โ<d2> โข <N> nights โข <adults> guests
โโโโโโโโโโโโโโโโโโโโ
๐ฅ BEST VALUE
[<Hotel Name>](<cheapest_link>)
โ
agoda ๐ฐ <price>/night
booking ๐ฐ <price>/night
opentravel ๐ฐ <price>/night
โ Save <diff> vs Booking
๐ฅ CHEAPEST
[<Hotel Name>](<cheapest_link>)
โ
google ๐ฐ <price>/night
agoda ๐ฐ <price>/night
๐ฅ QUALITY
[<Hotel Name>](<cheapest_link>)
โ
booking ๐ฐ <price>/night
agoda ๐ฐ <price>/night
๐ More good deals
โ Agoda โ
โข [<Hotel>](<agoda_link>) โ agoda: <price> | booking: <price>
โ Booking โ
โข [<Hotel>](<booking_link>) โ booking: <price>
โ Google โ
โข [<Hotel>](<google_link>) โ google: <price>
โ OpenTravel โ
โข [<Hotel>](<opentravel_link>) โ opentravel: <price>
๐ก Tip: <best Hotel Name>
[Book on <OTA>](<link>) โ <price>/night
๐ <N> hotels | <sources with data> โข 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 (2โ4 minutes). Google and Booking are inline (no discovery); OpenTravel is a direct API call.
- Subsequent searches reuse the Agoda cache and complete in ~30โ60 seconds.
Related skills
More from price-win/pricewin-skills-hub and the wider catalog.
find-skills
Discover and install agent skills to extend your coding agent's capabilities on demand
frontend-design
Build visually distinctive UI with opinionated aesthetic direction, typography, and layout choices that avoid templated defaults.
vercel-react-best-practices
70 React/Next.js performance rules from Vercel Engineering, prioritized by impact for writing, reviewing, and refactoring code.
agent-browser
Fast browser automation CLI for AI agents โ navigate, click, scrape, screenshot, and test via Chrome CDP
web-design-guidelines
Review UI code against Web Interface Guidelines for accessibility, UX, and design best practices
finetuning
Fine-tune models on Azure AI Foundry with SFT, DPO, or RFT training methods.