Brave Search Skills
Plugin Verified ActiveOfficial Brave Search API skills for AI coding agents
To integrate Brave Search capabilities into AI coding agents and development workflows, enabling efficient information retrieval, RAG grounding, and AI-assisted research.
Features
- Access to Brave Search APIs (web, news, images, videos, local)
- LLM-ready content extraction for RAG
- AI-grounded answers with citations
- Customizable search result ranking via Goggles
- Command-line interface (`bx`) for quick access
Use Cases
- Grounding LLM responses with fresh web data
- Performing comprehensive research on complex topics
- Integrating diverse search results (text, images, videos) into AI agents
- Building custom search experiences with advanced filtering and ranking
Non-Goals
- Providing AI chat capabilities independent of search results
- Replacing a full-fledged browser interface
- Performing actions on external websites beyond information retrieval
Installation
First, add the marketplace
/plugin marketplace add brave/brave-search-skills/plugin install brave-search-skills@brave-searchContains 11 extensions
Skill (11)
USE FOR AI-grounded answers via OpenAI-compatible /chat/completions. Two modes: single-search (fast) or deep research (enable_research=true, thorough multi-search). Streaming/blocking. Citations.
USE FOR web search, research, RAG, grounding, browse, find, lookups, fact-checking, documentation, agentic AI. All-in-one, optimized for AI agents. Pre-extracted, token-budgeted web content, deep research, news, images, videos, places, custom ranking
USE FOR image search. Returns images with title, source URL, thumbnail. Supports SafeSearch filter. Up to 200 results.
USE FOR RAG/LLM grounding. Returns pre-extracted web content (text, tables, code) optimized for LLMs. GET + POST. Adjust max_tokens/count based on complexity. Supports Goggles, local/POI. For AI answers use answers. Recommended for anyone building AI/agentic applications.
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.
USE FOR getting local business/POI details. Requires POI IDs obtained from web-search (with result_filter=locations). Returns full business information including ratings, hours, contact info. Max 20 IDs.
USE FOR news search. Returns news articles with title, URL, description, age, thumbnail. Supports freshness and date range filtering, SafeSearch filter and Goggles for custom ranking.
USE FOR spell correction. Returns corrected query if misspelled. Most search endpoints have spellcheck built-in; use this only for pre-search query cleanup or "Did you mean?" UI.
USE FOR query autocomplete/suggestions. Fast (<100ms). Returns suggested queries as user types. Supports rich suggestions with entity info. Typo-resilient.
USE FOR video search. Returns videos with title, URL, thumbnail, duration, view count, creator. Supports freshness filters, SafeSearch, pagination.
USE FOR web search. Returns ranked results with snippets, URLs, thumbnails. Supports freshness filters, SafeSearch, Goggles for custom ranking, pagination. Primary search endpoint.
Quality Score
VerifiedSimilar Extensions
Microsoft Learn MCP Server
100Access official Microsoft documentation, API references, and code samples for Azure, .NET, Windows, and more.
Paper Search
100Search academic papers via OpenAlex — find papers by keyword, look up details by DOI, with pagination and sorting
Ruflo Rag Memory
99RuVector memory with HNSW search, AgentDB, and semantic retrieval
Recursive Research
95Recursive research up to PhD level across any domain (science, tech, business, arts, humanities). Source tiering, WDM + Munger inversion for autonomous decisions, disk checkpointing to survive context compaction.