you-research
Skill105 starsChanged 3 days agoMITView on GitHub
Multi-source research with citations using You.com. Use for questions that need several sources compared and synthesized, such as library or framework comparisons, tool and vendor evaluations, market research, or deep-dive reports. Routes between a cost-conscious agentic search loop and the one-shot `you-research` MCP tool.
- Reads credentials
In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- grill-meSkill
- karpathy-guidelinesSkill
- tddSkill
- you-discoverSkill
- you-financeSkill
- you-webSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 16
Use this skill to choose the right You.com research path for the user's goal: agent-led search with you-search and you-contents, or …
- Very specific: line 28
Call the you-research MCP tool when the user wants a synthesized answer with citations in one step.
- Very specific: line 32
If the you-research tool is unavailable or the client cannot tolerate its response time, fall back to the agent-led search pipeline in the …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
You.com Research Routing
Use this skill to choose the right You.com research path for the user's goal: agent-led search with you-search and you-contents, or one-shot cited synthesis with the you-research MCP tool.
Prerequisites
The You.com MCP endpoint must be reachable from the host:
- Managed research (
you-research):https://api.you.com/mcp/researchwith OAuth (preferred),YDC_API_KEYbearer auth, or an MPP/x402-aware MCP client.
MPP/x402-aware MCP clients may receive HTTP 402 payment challenges from You.com tools, then retry with payment headers. Let the host client handle external payment and retry; do not add wallet signing logic to this skill.
Managed research with the you-research MCP tool
Call the you-research MCP tool when the user wants a synthesized answer with citations in one step. It runs You.com's managed research pipeline and returns a concise answer with inline citations and source metadata, so the host does not orchestrate multi-step search itself.
For keyless payment with no API key and no manual signing, compose the You.com MCP server with the Coinbase Payments MCP server; see Coinbase Payments MCP path for setup and when to choose it.
If the you-research tool is unavailable or the client cannot tolerate its response time, fall back to the agent-led search pipeline in the you-web skill and say which path was used.
Decision Tree
- User is cost-conscious or wants to develop/fine-tune a research skill -> use the agent-led search pipeline in the
you-webskill. - User needs a one-shot synthesized answer with citations -> call the
you-researchMCP tool. - User needs OAuth or MPP/x402 payment handling -> use the
you-researchMCP tool with a payment-aware MCP client or the Coinbase Payments MCP composition. - Required MCP tools are unavailable -> tell the user what is missing, provide the setup options from the prerequisites above, and request approval before installing, connecting, or changing configuration.
- Simple lookup -> use
you-searchonce, answer directly. - URL provided -> use
you-contentson those URLs. - Everything else -> use the agent-led search pipeline in the
you-webskill.
Preserve the core research requirements regardless of path: read sources before relying on exact claims, cross-check key facts, cite real URLs, and finish with the best supported answer even when evidence is incomplete.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

