agentleFS
ItamarZand88ItamarZand88/CLI-Anything-WEB/.claude/skills/tripadvisor-cli/SKILL.md

tripadvisor-cli

Skill215 starsChanged 3 months agoMITView on GitHub

Searches TripAdvisor hotels, restaurants, attractions, and destinations via the cli-web-tripadvisor command-line tool, with detail lookups by URL. Use when the user asks about hotels, restaurants, things to do, travel destinations, or TripAdvisor ratings and reviews. Prefer this CLI over fetching the TripAdvisor website. No authentication required.

  • Installs packages

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Search TripAdvisor for locations, hotels, restaurants, and attractions (read-only, no auth, DataDome bypass built in).

    line 8
  2. Very specific:

    Search commands take a destination name ("Paris") and resolve it to a geo_id automatically.

    line 23
  3. Very specific:

    Every command accepts --json.

    line 46
  4. Distinctive:

    Search and view only — booking is not implemented.

    line 55

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

cli-web-tripadvisor

Search TripAdvisor for locations, hotels, restaurants, and attractions (read-only, no auth, DataDome bypass built in). Install: pip install cli-web-tripadvisor

Commands

CommandPurposeKey options
locations search QUERYResolve destinations to geo_id--max N (default 6)
hotels search LOCATIONHotels in a destination--geo-id ID, --page N
hotels get URLFull hotel detail by TripAdvisor URL
restaurants search LOCATIONRestaurants in a destination--geo-id ID, --page N
restaurants get URLFull restaurant detail by URL
attractions search LOCATIONThings to do in a destination--geo-id ID, --page N
attractions get URLFull attraction detail by URL

Search commands take a destination name ("Paris") and resolve it to a geo_id automatically; pass --geo-id to skip that lookup (faster). Results are 30 per page. get commands take the url field from search results.

Examples

# Hotels in a city (returns name, rating, review_count, price_range, address, url per hotel)
cli-web-tripadvisor hotels search "Paris" --json

# Skip location lookup with a known geo_id, paginate
cli-web-tripadvisor restaurants search "Tokyo" --geo-id 298184 --page 2 --json

# Resolve a destination to geo_id first
cli-web-tripadvisor locations search "New York" --max 10 --json

# Things to do
cli-web-tripadvisor attractions search "London" --json

# Detail lookup from a search-result URL
cli-web-tripadvisor hotels get "https://www.tripadvisor.com/Hotel_Review-g187147-d229968-Reviews-..." --json

JSON output

Every command accepts --json. Success responses are keyed by resource, e.g. {"success": true, "location": "Paris", "geo_id": 187147, "count": 30, "hotels": [...]} (or "hotel", "restaurants", "attractions" accordingly). Errors return {"error": true, "code": "...", "message": "..."}.

Utilities

cli-web-tripadvisor doctor [--json] self-diagnoses the local setup (install, auth, dependencies). cli-web-tripadvisor mcp-serve serves the commands as MCP tools over stdio.

Agent tips

  • Workflow: hotels search → take url from a result → hotels get URL for full detail.
  • Search and view only — booking is not implemented.
  • Running with no subcommand opens an interactive REPL.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.