you-research

Solid

Route research tasks between a cost-conscious agentic search workflow, You.com Research API scripts, and managed or payment-aware MCP fallback.

AI & Automation 50 stars 10 forks Updated 4 days ago MIT

Install

View on GitHub

Quality Score: 90/100

Stars 20%
57
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# You.com Research Routing Use this skill to choose the right You.com research path for the user's goal: agent-led search, Research API scripts, or managed MCP fallback. ## Prerequisites For API scripts: - Use `YDC_API_KEY` when available, or an MPP/x402-capable HTTP client for keyless paid Research API calls. - With `YDC_API_KEY`, use these API request headers: `X-API-Key: ${YDC_API_KEY}` and `User-Agent: SKILL/(@youdotcom-oss/agent-skills you-research)`. - With MPP/x402, expect Research API pricing by `research_effort` and at least a 1 cent charge; confirm the user expects a paid managed research request before sending it. For the agent-led workflow, use the `you-research-base` MCP profile with `you-search` and `you-contents` when available. Those tools and their REST endpoints should use x402 for keyless paid retries, not MPP. See the [agent-led deep-search workflow](references/agent-led-deep-search.md) for setup and workflow details. MPP/x402-aware MCP or HTTP clients may receive HTTP `402` payment challenges from You.com tools and endpoints, then retry with payment headers. Use MPP/x402 for managed Research API calls where appropriate. Let the host client handle external payment and retry; do not add wallet signing logic to this skill. ## Research API scripts When the user wants You.com managed research APIs, write a small script or direct HTTP request instead of calling `you-research` through MCP, especially for `deep`, `exhaustive`, or `frontier` work. Before ...

Details

Author
youdotcom-oss
Repository
youdotcom-oss/agent-skills
Created
6 months ago
Last Updated
4 days ago
Language
TypeScript
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category