scout

Audit input links or ideas and produce fact-checked findings.

Updated Apr 14, 2026
One-click install
npx skills add https://github.com/ysgdepaula/x-deep-os --skill scout-ysgdepaula
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: scout
Source: https://github.com/ysgdepaula/x-deep-os/tree/main/.claude/skills/scout
Command: npx skills add https://github.com/ysgdepaula/x-deep-os --skill scout-ysgdepaula

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Audit deep research inputs (links or ideas) and deliver fact-checked findings aligned to curated sources and the X-DEEP architecture, plus concrete improvement proposals.

Core Features & Use Cases

  • Deep-input audit: Accepts URL, text, or reference repos/papers; runs a multi-phase scout workflow to extract context and findings.
  • Fact-check + cross-ref: Cross-checks findings against .agent knowledge articles and state knowledge for contradictions and redundancies.
  • Actionable proposals: Generates queue-ready proposals and updates the .agent/queue.md with suggested improvements.

Quick Start

Provide a URL or idea to scan, then invoke the scout to generate findings and queue proposals.

Frequently Asked Questions about scout

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

FAQPage Schema
How do I fact-check research links against existing knowledge sources?

Fact-checking research links involves auditing URLs or free-text concepts through a multi-phase workflow that cross-references extracted findings against curated knowledge articles to identify contradictions and redundancies.

Can I use deep research to generate actionable improvement proposals from a paper?

Yes, you can audit reference papers or repositories to extract context, cross-check findings, and generate queue-ready proposals that update your queue.md file with suggested improvements.

What is the best way to scan a URL for fact-checked findings and structured proposals?

The best way to scan a URL for fact-checked findings is to run a multi-phase scout workflow that extracts context, cross-checks against curated sources, and outputs structured findings with queue-ready proposals.

Does the deep research audit support free-text concepts or does it only process URLs?

The deep research audit supports free-text concepts, URLs, and reference repositories or papers, running a multi-phase workflow to extract context and produce structured findings for any accepted input type.

Are there options to run a faster research audit without generating proposals?

Yes, you can run a faster research audit without proposals by using the --quick option for speed and the --no-pr option to skip proposal generation, while still outputting structured findings.