synthesize

Merge multiple source analyses and claims into a coherent decision-oriented synthesis.

38|Updated Jan 20, 2026
One-click install
npx skills add https://github.com/lhl/realitycheck --skill synthesize-lhl
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: synthesize
Source: https://github.com/lhl/realitycheck/tree/main/integrations/claude/skills/synthesize
Command: npx skills add https://github.com/lhl/realitycheck --skill synthesize-lhl

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The synthesize skill provides a structured way to combine insights from multiple source analyses and claims into a single, decision-oriented view, reducing confusion and duplicative effort when reconciling evidence.

Core Features & Use Cases

  • Cross-source integration: Merge conclusions, gaps, and supporting evidence from multiple sources into a cohesive synthesis.
  • Evidence-to-decision mapping: Link synthesis conclusions to source analyses with explicit credence and provenance.
  • Iterative refinement: Update syntheses as new analyses become available or evidence changes.
  • Use Case: After evaluating several reports on a topic, run /check on the relevant sources and then generate a synthesis to present a high-level view and recommended actions.

Quick Start

Use the synthesize skill to produce a cross-source synthesis after you have gathered analyses and claims.

Frequently Asked Questions about synthesize

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

FAQPage Schema
How do I synthesize conflicting evidence from multiple reports into one decision-oriented conclusion?

Cross-source synthesis merges multiple source analyses and claims into a single coherent conclusion, reconciling conflicting evidence by mapping explicit credence and provenance to produce decision-oriented summaries.

What is the best way to merge conclusions and gaps from several analyses into a cohesive view?

Merging conclusions and gaps requires cross-source integration that links synthesis outputs to source analyses with explicit credence, reducing duplicative effort and confusion when reconciling evidence across many sources.

Do I need to store source analyses in a specific data repository before running a cross-source synthesis?

Yes, cross-source synthesis relies on source analyses being accessible in the Reality Check data repository, utilizing the rc-db / check / synthesize workflow and defined frontmatter in SKILL.md.

Can I update an existing cross-source synthesis when new analyses become available or evidence changes?

Yes, iterative refinement allows you to update syntheses as new analyses become available or evidence changes, ensuring the cross-source synthesis reflects the most current claims and credence.

How does cross-source claims analysis handle evidence-to-decision mapping for conflicting perspectives?

Evidence-to-decision mapping links synthesis conclusions directly to source analyses with explicit credence and provenance, comparing perspectives and reconciling conflicting evidence into a single decision-oriented view.