discover-api

Return intent-ranked web discovery results with relevance scores and optional parsed content.

Updated Jul 18, 2026

Search Tags:#research #rag #web search #relevance scoring #intent ranking #discovery api

Ready to run

npx skills add https://github.com/farzanmrz/beat-radar-agent --skill discover-api-farzanmrz

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: discover-api
Source: https://github.com/farzanmrz/beat-radar-agent/tree/main/.claude/skills/discover-api
Command: npx skills add https://github.com/farzanmrz/beat-radar-agent --skill discover-api-farzanmrz

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you find web pages that match a user's goal, not just a keyword string, so research and retrieval are more accurate and less noisy.

Core Features & Use Cases

Intent-ranked discovery: Search the web with a clear purpose and receive results scored by relevance.
RAG and research workflows: Retrieve pages with optional parsed content for grounding, knowledge base building, and cited briefs.
Multi-surface support: Use the REST API, CLI, or SDKs depending on whether you are scripting, prototyping, or integrating into an app.
Use Case: A researcher wants vendor pages about enterprise LLM pricing and uses this Skill to collect ranked, content-rich results for analysis.

Quick Start

Ask for intent-ranked web discovery on a topic and include the goal, desired result count, and whether parsed page content is needed.

Frequently Asked Questions about discover-api

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

FAQPage Schema

How does intent-ranked web discovery improve RAG workflows over standard keyword search?▼

Intent-ranked web discovery improves RAG workflows by returning AI-scored results that match a user's search goal rather than a keyword string, reducing noise and providing more accurate retrieval for grounding and cited briefs.

How do I retrieve parsed page content for research using a discovery API?▼

You retrieve parsed page content for research by requesting optional parsed content through the discovery API, enabling the collection of content-rich, ranked web results for analysis and knowledge base building.

Can I use a discovery API with REST, CLI, and SDK workflows?▼

Yes, you can use the discovery API across REST, CLI, and SDK workflows, allowing flexible integration whether you are scripting, prototyping, or building retrieval-augmented generation into an application.

Do I need async trigger-and-poll handling to get relevance scoring from web search?▼

Yes, async trigger-and-poll handling is required to retrieve AI-scored relevance results, as the discovery API processes intent ranking and optional parsed content asynchronously before returning the final web search payload.

What is the best way to filter vendor comparison results by relevance scoring?▼

The best way to filter vendor comparison results is using parameter-aware modes and filters with specified result limits, ensuring the discovery API returns only the most relevant, AI-scored pages for your search goal.

Why does web search return irrelevant results when doing topic coverage research?▼

Web search returns irrelevant results during topic coverage because standard keyword matching lacks intent ranking, a problem solved by applying AI-scored relevance filtering to match the actual research goal.