skills.rest
brave
braveOFFICIAL
Explore all skills by this author →
WebsiteGitHub

answers

Generate AI-grounded answers via OpenAI-compatible chat completions with streaming and citations.

164|11|Updated Jan 30, 2026
Search Tags:#research#llm#web search#search#citations#answers
One-click install
npx skills add https://github.com/brave/brave-search-skills --skill answers-brave
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: answers
Source: https://github.com/brave/brave-search-skills/tree/main/skills/answers
Command: npx skills add https://github.com/brave/brave-search-skills --skill answers-brave

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides AI-generated answers grounded in real-time web search results, offering both quick factual responses and in-depth research capabilities.

Core Features & Use Cases

  • AI-Grounded Answers: Get answers directly from the web, ensuring accuracy and relevance.
  • Single-Search Mode: Fast, streaming answers with optional citations for quick queries.
  • Deep Research Mode: Iterative, multi-search approach for comprehensive topic exploration, synthesizing information from multiple sources.
  • Use Case: Ask "What are the latest advancements in renewable energy?" and receive a concise, cited answer, or enable research mode for a detailed comparison of different solar panel technologies.

Quick Start

Use the answers skill to get a streaming answer with citations for the question "What are recent breakthroughs in fusion energy?".

Frequently Asked Questions about answers

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I get AI answers with web search citations?▼

To get AI answers with web search citations, use the single-search mode to receive streaming responses grounded in real-time web results, ensuring factual accuracy. This mode provides fast answers with optional citations for quick queries.

What's the best way to conduct deep research using LLM web search?▼

The best way to conduct deep research using LLM web search is enabling the deep research mode. This mode utilizes an iterative, multi-search approach to synthesize comprehensive information from multiple sources for detailed topic exploration.

Can I use an OpenAI-compatible chat completions endpoint for grounded answers?▼

Yes, you can use an OpenAI-compatible chat completions endpoint to receive AI-grounded answers. The Skill integrates with this endpoint to provide streaming responses and detailed research parameters for information synthesis.

Does single-search mode support streaming responses?▼

Yes, single-search mode supports streaming responses. It is designed for fast, streaming answers with optional citations, making it suitable for quick factual queries directly from the web.

When do I need deep research mode for web search answers?▼

You need deep research mode when your web search answers require comprehensive topic exploration. This mode performs an iterative, multi-search approach to synthesize detailed information from multiple sources, unlike the quick single-search mode.

Related Skills

Explore More Content & Communication Skills→
cascade-protocolcascade-protocol
14

agentbox-inference

Generate chat completions via an OpenAI-compatible API with USDC micropayments.

Official
Intermediate
ARAVINDAN20ARAVINDAN20
4

parallel-web

Search the web and extract URL content via Parallel Web Systems APIs.

Community
Advanced
Kingly-AgencyKingly-Agency

rag-implementation

Build RAG pipelines that ground LLM responses with retrieved external knowledge.

Official
Advanced
julianobarbosajulianobarbosa
7

researching-web

Search the web via Perplexity AI and return citation-rich results.

Community
Intermediate