pricewin-deal-finder
Perbandingan harga hotel & penawaran di Booking, Agoda, Google Hotels, dan OpenTravel untuk tanggal perjalanan dan jumlah tamu tertentu. Gunakan untuk harga hotel, penawaran, atau membandingkan tarif OTA.
npx skills add https://github.com/price-win/pricewin-skills-hub --skill pricewin-deal-finderPriceWin Deal Finder
π¨ IMPORTANT β HOW TO USE THIS SKILL
ONE command does everything. Run this as your FIRST action β 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 β 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" β
<year>-06-10 <year>-06-13β fill<year>from the rule above - "2 guests" / "2 people" β
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.
π¨ CRITICAL RULES β FOLLOW EVERY TIME
RULE 0 β 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:
β browser_navigate / browser_open β FORBIDDEN
β browser_click β FORBIDDEN
β browser_type / browser_fill β FORBIDDEN
β browser_snapshot β FORBIDDEN
β browser_close β FORBIDDEN
β Any other browser_* native tool β FORBIDDEN
β delegate_task / spawn_agent / sub-agent delegation β 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 β 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.
β
The ONLY allowed way to drive a browser in this skill is via terminal:
terminal: cd {baseDir} && node bin/search.js ...
RULE 1 β 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 β 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 β do NOT go fetch it by hand.
RULE 2 β First-time city discovery takes 2β4 minutes. If search.js output contains "discovering" or "launching" messages, tell the user: "First time searching this city β discovering selectors, this takes about 2β4 minutes..." and wait for the result. Do NOT retry or abort.
RULE 3 β 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 β PRESERVE MARKDOWN HYPERLINKS. Every hotel name in the output is already wrapped as [Hotel Name](https://booking-url...). This is a clickable hyperlink β DO NOT:
- Strip the markdown and show the URL on a separate
π https://...line - Replace
[Hotel Name](url)with plain text - Capitalize OTA names ("google" stays "google", not "Google")
- Rename sections β "π 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 β 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 β 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 β send the tier cards with whatever sources are present. The footer (π N hotels | <sources> β’ 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 β 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 β 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 β the script does not have that data.
π¨ <city> β’ <d1>β<d2> β’ <N> nights β’ <adults> guests
ββββββββββββββββββββ
π₯ BEST VALUE
[<Hotel Name>](<cheapest_link>)
β
agoda π° <price>/night
booking π° <price>/night
opentravel π° <price>/night
β Save <diff> vs Booking
π₯ CHEAPEST
[<Hotel Name>](<cheapest_link>)
β
google π° <price>/night
agoda π° <price>/night
π₯ QUALITY
[<Hotel Name>](<cheapest_link>)
β
booking π° <price>/night
agoda π° <price>/night
π More good deals
β Agoda β
β’ [<Hotel>](<agoda_link>) β agoda: <price> | booking: <price>
β Booking β
β’ [<Hotel>](<booking_link>) β booking: <price>
β Google β
β’ [<Hotel>](<google_link>) β google: <price>
β OpenTravel β
β’ [<Hotel>](<opentravel_link>) β opentravel: <price>
π‘ Tip: <best Hotel Name>
[Book on <OTA>](<link>) β <price>/night
π <N> hotels | <sources with data> β’ 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 (2β4 minutes). Google and Booking are inline (no discovery); OpenTravel is a direct API call.
- Subsequent searches reuse the Agoda cache and complete in ~30β60 seconds.