Broad Location Entity Query

Search for places using natural language with Camino AI's location intelligence API. Returns relevant results with coordinates, distances, and metadata. Use...

Security Scan

The skill's requests and instructions are consistent with a location-query integration that calls Camino's API using a single API key; nothing in the included script or SKILL.md indicates hidden exfiltration or unrelated credential requests.

Purpose & Capability

Name/description, required environment variable (CAMINO_API_KEY), and code (scripts/query.sh) all align: the skill simply calls https://api.getcamino.ai/query with the API key. One minor inconsistency: the registry metadata at the top lists no required binaries, while the SKILL.md metadata and the script both require curl and jq. Functionally the binaries are necessary and used by the script.

Instruction Scope

SKILL.md and scripts limit actions to building a URL-encoded query and calling Camino's API; the script validates JSON, checks for jq/curl, and sends the CAMINO_API_KEY in a request header. The instructions do tell the user to store the API key in ~/.claude/settings.json (a plaintext config), which is a usability/sensitivity note but not malicious. The skill does not instruct reading other unrelated files or transmitting data to unexpected endpoints.

Install Mechanism

This is instruction-only with an included shell script (no automatic install spec). SKILL.md suggests installing via npx (pulling from a GitHub repo) or clawhub; using npx installs remote code and has the usual supply-chain considerations. The repository is a GitHub URL (reasonable), and there are no opaque archive downloads or extract steps in the provided files.

Credentials

Only CAMINO_API_KEY is required and is declared as the primary credential. No unrelated secrets or multiple credentials are requested. Reminder: storing the key in ~/.claude/settings.json or other plaintext configs can expose it if that file is shared or backed up.

Persistence & Privilege

The skill does not request always:true and does not modify other skills or system-wide settings in the provided files. Autonomous invocation is allowed by default (platform behavior) but the skill itself does not escalate privileges or persist beyond its normal files.

Assessment

This skill appears to do what it says: it builds a query and calls Camino's API using CAMINO_API_KEY. Before installing or using it, verify you trust api.getcamino.ai and the repository owner. Prefer giving it a limited-scope or trial API key (the SKILL.md documents a trial endpoint). Be cautious storing the API key in plaintext (~/.claude/settings.json); consider using a secret store or environment variable limited to the process. If you plan to run the npx install command, inspect the remote repo first (or clone it) rather than running arbitrary install scripts directly. Finally, note the small inconsistency where registry metadata omitted required binaries (curl, jq) — ensure those tools are available and review scripts locally before running them.

Installation

Companion Skills: This is part of the Camino AI location intelligence suite. Install all available skills (query, places, relationship, context, route, journey, real-estate, hotel-finder, ev-charger, school-finder, parking-finder, fitness-finder, safety-checker, travel-planner) for comprehensive coverage.

# Install all skills from repo
npx skills add https://github.com/barneyjm/camino-skills

# Or install specific skills
npx skills add https://github.com/barneyjm/camino-skills --skill query

Via clawhub:

npx clawhub@latest install query
# or: pnpm dlx clawhub@latest install query
# or: bunx clawhub@latest install query

Query - Natural Language Place Search

Search for places using natural language. The AI automatically generates coordinates for known locations when not provided.

Setup

Instant Trial (no signup required): Get a temporary API key with 25 calls:

curl -s -X POST -H "Content-Type: application/json" \
  -d '{"email": "[e-mail]"}' \
  https://api.getcamino.ai/trial/start

Returns: {"api_key": "camino-xxx...", "calls_remaining": 25, ...}

For 1,000 free calls/month, sign up at https://app.getcamino.ai/skills/activate.

Add your key to Claude Code:

Add to your ~/.claude/settings.json:

{
  "env": {
    "CAMINO_API_KEY": "your-api-key-here"
  }
}

Restart Claude Code.

Usage

Via Shell Script

# Search for coffee shops near Times Square
./scripts/query.sh '{"query": "coffee shops near Times Square", "limit": 5}'

# Search with specific coordinates
./scripts/query.sh '{"query": "quiet cafes with wifi", "lat": 40.7589, "lon": -73.9851, "radius": 500}'

# Get AI-generated answer with results
./scripts/query.sh '{"query": "best pizza in Manhattan", "answer": true, "rank": true}'

Via curl

curl -H "X-API-Key: $CAMINO_API_KEY" \
  "https://api.getcamino.ai/query?query=coffee+shops+near+Times+Square&limit=5"

Parameters

Parameter	Type	Required	Default	Description
query	string	Yes*	-	Natural language query (e.g., "coffee shops near Times Square")
lat	float	No	-	Latitude for search center. AI generates if omitted for known locations.
lon	float	No	-	Longitude for search center. AI generates if omitted for known locations.
radius	int	No	1000	Search radius in meters (100-50000)
rank	bool	No	true	Use AI to rank results by relevance
limit	int	No	20	Maximum results (1-100)
offset	int	No	0	Pagination offset
answer	bool	No	false	Generate human-readable summary
time	string	No	-	Temporal query: "2020-01-01", "2020..", or "2020..2024"
osm_ids	string	No	-	Comma-separated OSM IDs (e.g., "node/123,way/456")
mode	string	No	"basic"	"basic" (OSM only) or "advanced" (web enrichment)

*Either query or osm_ids is required.

Response Format

{
  "query": "quiet coffee shops with wifi",
  "results": [
    {
      "name": "Blue Bottle Coffee",
      "lat": 40.7601,
      "lon": -73.9847,
      "type": "cafe",
      "distance_m": 150,
      "relevance_score": 0.95,
      "address": "..."
    }
  ],
  "ai_ranked": true,
  "pagination": {
    "total_results": 23,
    "limit": 5,
    "offset": 0,
    "has_more": true
  },
  "answer": "I found several quiet coffee shops with wifi near Times Square..."
}

Examples

Find nearby restaurants

./scripts/query.sh '{"query": "Italian restaurants", "lat": 40.7128, "lon": -74.0060, "limit": 10}'

Search with AI answer

./scripts/query.sh '{"query": "best brunch spots in Brooklyn", "answer": true}'

Historical data query

./scripts/query.sh '{"query": "restaurants", "lat": 40.7589, "lon": -73.9851, "time": "2020-01-01"}'

Best Practices

• For known locations (cities, landmarks), you can omit lat/lon and let the AI generate coordinates
• Use rank: true for more relevant results when searching by attributes (e.g., "quiet", "cheap")
• Enable answer: true when you need a natural language summary of results
• Use mode: "advanced" for richer place data from web sources
• Keep queries descriptive but concise for best AI interpretation