search-strategy

Decompose natural language queries into parallel source-specific searches and return ranked results.

1|Updated Feb 25, 2026
One-click install
npx skills add https://github.com/mattmacleod16-svg/freedomforge-max --skill search-strategy-mattmacleod16-svg
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: search-strategy
Source: https://github.com/mattmacleod16-svg/freedomforge-max/tree/main/.agents/skills/search-strategy
Command: npx skills add https://github.com/mattmacleod16-svg/freedomforge-max --skill search-strategy-mattmacleod16-svg

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transforms a single natural language question into parallel, source-specific searches and produces ranked, deduplicated results.

Core Features & Use Cases

  • Query Decomposition: Breaks a user query into source-targeted sub-queries.
  • Source Translation & Routing: Translates queries into source-specific syntax and routes them to each connected source.
  • Synthesis & Ranking: Merges results, deduplicates, and ranks by relevance.
  • Ambiguity Handling & Fallbacks: Detects ambiguity and applies fallback strategies to ensure coverage.

Quick Start

Provide a natural language question to decompose into per-source searches and synthesize a ranked result.

Frequently Asked Questions about search-strategy

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

FAQPage Schema
How do I search multiple enterprise knowledge bases from a single natural language query?

Query decomposition breaks a natural language question into parallel, source-specific sub-queries. These sub-queries are routed to connected enterprise knowledge bases, document stores, and chat systems simultaneously, returning synthesized results.

How does multi-source search ranking handle duplicate records across different systems?

Multi-source search ranking merges results from all queried systems and applies deduplication to remove redundant records. The remaining unique entries are then ranked by calculated relevance to the original query.

Can I route translated sub-queries to different document stores and project records?

Source translation and routing translates your natural language query into source-specific syntax. It routes these deterministic sub-queries to each connected document store and project record system for targeted retrieval.

What happens when a semantic search query is ambiguous across connected knowledge sources?

Ambiguity handling detects unclear intent within the query and applies fallback strategies to ensure coverage. This fallback mechanism guarantees the search returns functional results even when source-specific queries lack precise matches.

What's the best way to orchestrate parallel searches across enterprise chat systems and project records?

Orchestrating parallel searches uses query decomposition to generate source-targeted sub-queries for your chat systems and project records. Results are merged, deduplicated, and ranked by relevance to synthesize a unified answer.

Do I need to format natural language queries before submitting them for multi-source search?

No query formatting is required. You provide a single natural language question and the search strategy automatically decomposes it into deterministic per-source sub-queries for routing to each connected knowledge source.