agentleFS
claude-worldclaude-world/claude-agent/.claude/skills/places/SKILL.md

places

Skill5 starsChanged 8 months agoMITView on GitHub

Search nearby places, get details, and read reviews via the goplaces CLI and Google Places API. Use when user asks "find a restaurant near me", "what coffee shops are nearby", "get details for a place", or "show reviews".

  • Reads credentials
  • Installs packages

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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 places and get details using goplaces CLI backed by the Google Places API.

    line 22
  2. Distinctive:

    Create Credentials → API Key.

    line 38
  3. Very specific:

    Always check if CLI is installed first: which goplaces

    line 75
  4. Distinctive:

    If not installed, show the install command and stop

    line 76
  5. Very specific:

    Always check that GOOGLE_PLACES_API_KEY is set: [[ -z "$GOOGLE_PLACES_API_KEY" ]] && echo "API key not set"

    line 77
  6. Distinctive:

    Never print the API key value in output

    line 78
  7. Distinctive:

    When listing results, show: name, rating, address, open status — limit to top 5 results by default

    line 79
  8. Distinctive:

    If location is ambiguous, ask the user to clarify before searching

    line 82

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Places

Search places and get details using goplaces CLI backed by the Google Places API. Requires a GOOGLE_PLACES_API_KEY environment variable.

Prerequisites

brew install steipete/tap/goplaces

Set up your API key:

export GOOGLE_PLACES_API_KEY="AIza..."
# Or add to ~/.zshrc / ~/.bashrc for persistence

Get a key: https://console.cloud.google.com → APIs & Services → Enable "Places API" → Create Credentials → API Key.

Commands

CommandDescription
goplaces search "<query>" --near "<location>"Search places by type/name near a location
goplaces search "<query>" --lat 25.0478 --lng 121.5319Search by coordinates
goplaces details "<place_id>"Get full details for a place (hours, phone, address)
goplaces reviews "<place_id>"List top reviews for a place
goplaces search "<query>" --open-nowFilter to currently open places
goplaces search "<query>" --radius 500Limit search radius in meters

Usage Examples

Find coffee shops nearby:

goplaces search "coffee shop" --near "Taipei 101" --open-now

Get full details for a place:

goplaces details "ChIJN1t_tDeuEmsRUsoyG83frY4"

Read reviews:

goplaces reviews "ChIJN1t_tDeuEmsRUsoyG83frY4"

Search with coordinates:

goplaces search "ramen" --lat 25.0478 --lng 121.5319 --radius 1000

Rules

  • Always check if CLI is installed first: which goplaces
  • If not installed, show the install command and stop
  • Always check that GOOGLE_PLACES_API_KEY is set: [[ -z "$GOOGLE_PLACES_API_KEY" ]] && echo "API key not set"
  • Never print the API key value in output
  • When listing results, show: name, rating, address, open status — limit to top 5 results by default
  • For details, summarize: address, phone, hours, website, rating
  • For reviews, show top 3 reviews (author, rating, snippet) — save full reviews to workspace/ if requested
  • If location is ambiguous, ask the user to clarify before searching

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.