my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	{
#2	"skillId": "local-places",
#3	"name": "local-places",
#4	"description": "Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.",
#5	"category": "pump-protocol",
#6	"path": "local-places/SKILL.md",
#7	"url": "https://x402.wtf/api/skills/local-places",
#8	"tags": [
#9	"local",
#10	"solana",
#11	"places"
#12	],
#13	"requiredEnv": [],
#14	"homepage": null,
#15	"attestation": {
#16	"status": "pending",
#17	"isFormallyVerified": false,
#18	"attestationPda": null,
#19	"verificationTimestamp": null
#20	},
#21	"markdown": "---\nname: local-places\ndescription: Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.\nhomepage: https://github.com/Hyaxia/local_places\nmetadata: {\"clawdbot\":{\"emoji\":\"📍\",\"requires\":{\"bins\":[\"uv\"],\"env\":[\"GOOGLE_PLACES_API_KEY\"]},\"primaryEnv\":\"GOOGLE_PLACES_API_KEY\"}}\n---\n\n# 📍 Local Places\n\nFind places, Go fast\n\nSearch for nearby places using a local Google Places API proxy. Two-step flow: resolve location first, then search.\n\n## Setup\n\n```bash\ncd {baseDir}\necho \"GOOGLE_PLACES_API_KEY=your-key\" > .env\nuv venv && uv pip install -e \".[dev]\"\nuv run --env-file .env uvicorn local_places.main:app --host 127.0.0.1 --port 8000\n```\n\nRequires `GOOGLE_PLACES_API_KEY` in `.env` or environment.\n\n## Quick Start\n\n1. Check server: `curl http://127.0.0.1:8000/ping`\n\n2. Resolve location:\n```bash\ncurl -X POST http://127.0.0.1:8000/locations/resolve \\\n -H \"Content-Type: application/json\" \\\n -d '{\"location_text\": \"Soho, London\", \"limit\": 5}'\n```\n\n3. Search places:\n```bash\ncurl -X POST http://127.0.0.1:8000/places/search \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"query\": \"coffee shop\",\n \"location_bias\": {\"lat\": 51.5137, \"lng\": -0.1366, \"radius_m\": 1000},\n \"filters\": {\"open_now\": true, \"min_rating\": 4.0},\n \"limit\": 10\n }'\n```\n\n4. Get details:\n```bash\ncurl http://127.0.0.1:8000/places/{place_id}\n```\n\n## Conversation Flow\n\n1. If user says \"near me\" or gives vague location → resolve it first\n2. If multiple results → show numbered list, ask user to pick\n3. Ask for preferences: type, open now, rating, price level\n4. Search with `location_bias` from chosen location\n5. Present results with name, rating, address, open status\n6. Offer to fetch details or refine search\n\n## Filter Constraints\n\n- `filters.types`: exactly ONE type (e.g., \"restaurant\", \"cafe\", \"gym\")\n- `filters.price_levels`: integers 0-4 (0=free, 4=very expensive)\n- `filters.min_rating`: 0-5 in 0.5 increments\n- `filters.open_now`: boolean\n- `limit`: 1-20 for search, 1-10 for resolve\n- `location_bias.radius_m`: must be > 0\n\n## Response Format\n\n```json\n{\n \"results\": [\n {\n \"place_id\": \"ChIJ...\",\n \"name\": \"Coffee Shop\",\n \"address\": \"123 Main St\",\n \"location\": {\"lat\": 51.5, \"lng\": -0.1},\n \"rating\": 4.6,\n \"price_level\": 2,\n \"types\": [\"cafe\", \"food\"],\n \"open_now\": true\n }\n ],\n \"next_page_token\": \"...\" \n}\n```\n\nUse `next_page_token` as `page_token` in next request for more results.\n"
#22	}
#23

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public