query

Query prioritized sources and tag claims with citations and confidence levels.

34|2|Updated Feb 24, 2026
One-click install
npx skills add https://github.com/retran/meowary --skill query-retran
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: query
Source: https://github.com/retran/meowary/tree/main/.shared/skills/query
Command: npx skills add https://github.com/retran/meowary --skill query-retran

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the need for comprehensive information retrieval by querying multiple sources and providing sourced, confident answers to ensure accuracy.

Core Features & Use Cases

  • Multi-source retrieval: Combines data from QMD, file reads, Confluence, Jira, and web to deliver thorough answers.
  • Source citation and confidence tagging: Annotates each claim with its source and a confidence level to support transparency.
  • Use Case: When researching architectural decisions, this Skill gathers information from internal documentation and external websites, tagging each fact for clarity.

Quick Start

Ask the AI a question like "What is the current system architecture?" to retrieve and cite relevant information across multiple knowledge tiers.

Frequently Asked Questions about query

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

FAQPage Schema
How do I retrieve information across multiple sources with citations?

Multi-source information retrieval works by querying prioritized knowledge bases, tagging claims with source citations, and assigning confidence levels. It combines internal tools and web access to deliver transparent, accountable responses for complex queries.

What is the best way to search Confluence and Jira for architectural decisions?

Searching Confluence and Jira for architectural decisions is best handled by querying multiple knowledge tiers simultaneously. This approach aggregates internal documentation, tags each fact with its origin, and reports gaps when information is insufficient.

Can I use multi-source search to find gaps in my internal knowledge base?

Yes, you can use multi-source search to find gaps in your internal knowledge base. The mechanism queries prioritized sources and explicitly reports information gaps when data is insufficient, ensuring you know exactly where documentation is lacking.

How does confidence tagging work for extracted knowledge claims?

Confidence tagging works by annotating each extracted claim with a specific confidence level and its source citation. This transparency mechanism ensures accountability in complex information environments by validating the reliability of retrieved facts.

Do I need qmd query and web access to perform multi-layered knowledge extraction?

Yes, you need qmd query, Confluence, Jira, and web access to function fully. Multi-layered knowledge extraction requires these tools to query prioritized sources, read files, and gather comprehensive data for accurate information retrieval.