retrieval-workflow

Retrieve ranked evidence bundles from the DocMason knowledge base.

135|36|Updated Mar 21, 2026
One-click install
npx skills add https://github.com/JetXu-LLM/DocMason --skill retrieval-workflow
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: retrieval-workflow
Source: https://github.com/JetXu-LLM/DocMason/tree/main/skills/canonical/retrieval-workflow
Command: npx skills add https://github.com/JetXu-LLM/DocMason --skill retrieval-workflow

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Retrieve the strongest, publish-proven evidence bundles from the DocMason knowledge base to support trustable answers and provenance.

Core Features & Use Cases

  • Evidence ranking: fetch and rank knowledge-base bundles by relevance and coverage.
  • Targeted retrieval: surface exact artifacts for explicit questions or blended queries.
  • Use Case: When you need to validate claims across multiple documents, run this workflow to obtain provenance-rich bundles.

Quick Start

Ask the agent to retrieve the top-ranked evidence bundles for your query.

Frequently Asked Questions about retrieval-workflow

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

FAQPage Schema
How do I retrieve ranked evidence bundles from a knowledge base for cross-document validation?

To retrieve ranked evidence bundles from a knowledge base, this workflow fetches and ranks DocMason artifacts by relevance and coverage to support grounded answers and provenance for cross-document validation.

What is the best way to surface provenance-rich source bundles for audit triage?

The best way to surface provenance-rich source bundles for audit triage is retrieving the strongest published evidence bundles, ranked by relevance to provide exact artifacts for explicit questions or blended queries.

Do I need local file access and shell execution to retrieve ranked evidence bundles?

Yes, retrieving ranked evidence bundles requires local file access and shell execution to inspect the structured JSON output containing the fetched knowledge-base artifacts for grounded answers.

How does evidence ranking work when fetching knowledge-base bundles for grounded answers?

Evidence ranking works by fetching knowledge-base bundles and sorting them by relevance and coverage, ensuring you obtain provenance-rich artifacts to validate claims across multiple documents.

Can I use this evidence retrieval workflow for targeted queries across multiple documents?

Yes, you can use this evidence retrieval workflow for targeted queries across multiple documents, as it surfaces exact artifacts for explicit questions and blended queries through structured JSON output.

What are the limitations of retrieving evidence bundles from a published knowledge base?

A limitation of retrieving evidence bundles from a published knowledge base is the requirement for local file access and shell execution to inspect structured JSON output, restricting automated cloud-only environments.