USE FOR getting AI-generated POI text descriptions. Requires POI IDs obtained from web-search (with result_filter=locations). Returns markdown descriptions grounded in web search context. Max 20 IDs per request.
npx skills add https://github.com/brave/brave-search-skills --skill local-descriptions
> Requires API Key: Get one at https://api.search.brave.com
>
> Plan: Included in the Search plan. See https://api-dashboard.search.brave.com/app/subscriptions/subscribe
>
> Two-step flow: This endpoint requires POI IDs from a prior web search.
>
> 1. Call web-search with result_filter=locations to get POI IDs from locations.results[].id
> 2. Pass those IDs to this endpoint to get AI-generated descriptions
curl -s "https://api.search.brave.com/res/v1/local/descriptions?ids=loc4CQWMJWLD4VBEBZ62XQLJTGK6YCJEEJDNAAAAAAA%3D" \
-H "Accept: application/json" \
-H "Accept-Encoding: gzip" \
-H "X-Subscription-Token: ${BRAVE_SEARCH_API_KEY}"
curl -s "https://api.search.brave.com/res/v1/local/descriptions" \
-H "Accept: application/json" \
-H "Accept-Encoding: gzip" \
-H "X-Subscription-Token: ${BRAVE_SEARCH_API_KEY}" \
-G \
--data-urlencode "ids=loc4CQWMJWLD4VBEBZ62XQLJTGK6YCJEEJDNAAAAAAA=" \
--data-urlencode "ids=loc4HTAVTJKP4RBEBZCEMBI3NG26YD4II4PATIHPDYI="
Note: POI IDs are opaque strings returned in web search locations.results[].id. They are valid for approximately 8 hours. The example IDs above are for illustration — fetch fresh IDs via web-search with result_filter=locations.
GET https://api.search.brave.com/res/v1/local/descriptions
Authentication: X-Subscription-Token: <API_KEY> header
| Parameter | Type | Required | Default | Description |
|--|--|--|--|--|
| ids | string[] | Yes | — | POI IDs from web search locations.results[].id (1-20, repeated: ?ids=a&ids=b) |
| Field | Type | Description |
|--|--|--|
| type | string | Always "local_descriptions" |
| results | array | List of description objects (entries may be null) |
| results[].type | string | Always "local_description" |
| results[].id | string | POI identifier matching the request |
| results[].description | string? | AI-generated markdown description, or null if unavailable |
{
"type": "local_descriptions",
"results": [
{
"type": "local_description",
"id": "loc4CQWMJWLD4VBEBZ62XQLJTGK6YCJEEJDNAAAAAAA=",
"description": "### Overview\nA cozy neighborhood cafe known for its **artisanal coffee**..."
}
]
}
POI IDs come from the Web Search API (web-search) with result_filter=locations:
# 1. Search for local businesses
curl -s "https://api.search.brave.com/res/v1/web/search?q=restaurants+san+francisco&result_filter=locations" \
-H "Accept: application/json" \
-H "X-Subscription-Token: ${BRAVE_SEARCH_API_KEY}"
# 2. Extract POI IDs from locations.results[].id
# 3. Use those IDs with local/pois and local/descriptions
local-pois to get both structured data (hours, ratings) and narrative descriptions### headings, bullet lists, bold/*italics* — always formatted as markdowndescription may be nullIntegration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
Take brave/local-descriptions from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.