knowledge-synthesizer

Synthesize multiple agent findings into non-redundant, evidence-based outputs.

22|2|Updated Mar 24, 2026
One-click install
npx skills add https://github.com/jshsakura/awesome-opencode-skills --skill knowledge-synthesizer-jshsakura
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: knowledge-synthesizer
Source: https://github.com/jshsakura/awesome-opencode-skills/tree/main/skills/knowledge-synthesizer
Command: npx skills add https://github.com/jshsakura/awesome-opencode-skills --skill knowledge-synthesizer-jshsakura

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Distill multiple agent findings into a non-redundant, evidence-based synthesis to inform parent-agent decisions.

Core Features & Use Cases

  • Deduplicate overlapping findings while preserving nuance, confidence, and source traceability.
  • Surface explicit conflicts, open hypotheses, and data gaps to guide next steps.
  • Organize synthesized outputs by decision-relevant themes to streamline integration with higher-level goals.

Quick Start

Provide a concise synthesis of all agent findings, preserving signal and surfacing conflicts.

Frequently Asked Questions about knowledge-synthesizer

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

FAQPage Schema
How do I synthesize conflicting findings from multiple agents into a single decision-support output?

To synthesize multiple agent findings, you need a process that deduplicates overlapping data, reconciles conflicting claims, and preserves source traceability to produce a non-redundant, evidence-based synthesis for parent-agent decisions.

What is the best way to deduplicate overlapping agent outputs while preserving confidence levels and traceability?

Deduplicating agent outputs requires distilling overlapping findings into concise insights while explicitly preserving nuance, varying confidence levels, and original source traceability to ensure no critical signal is lost during integration.

How do I surface data gaps and open hypotheses when reconciling multi-agent research?

Surfacing data gaps during multi-agent synthesis involves explicitly identifying unresolved conflicts and open hypotheses, then organizing these gaps to clearly signal the need for subsequent targeted evidence gathering by the parent agent.

Does multi-agent evidence synthesis work for organizing outputs by specific decision-relevant themes?

Yes, evidence synthesis works for decision-support by organizing distilled, non-redundant agent findings into decision-relevant themes, which streamlines the integration of synthesized insights with higher-level parent-agent goals.

When should I not use an automated agent-output synthesis approach for conflicting claims?

You should avoid automated agent-output synthesis when your multi-agent findings lack the necessary source traceability metadata, as the process fundamentally requires traceable evidence to explicitly handle conflicts and signal unresolved gaps.