synthesize

Parse SWARM run metadata and summary files into structured vault notes.

39|4|Updated Feb 3, 2026
One-click install
npx skills add https://github.com/swarm-ai-safety/swarm --skill synthesize-swarm-ai-safety
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: synthesize
Source: https://github.com/swarm-ai-safety/swarm/tree/main/.skills/synthesize
Command: npx skills add https://github.com/swarm-ai-safety/swarm --skill synthesize-swarm-ai-safety

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the process of transforming raw simulation run data into structured, human-readable experiment notes and updates the central knowledge base, ensuring research findings are consistently documented and discoverable.

Core Features & Use Cases

  • Automated Documentation: Generates experiment notes from run.yaml and summary files.
  • Evidence Linking: Scans existing claims for supporting or weakening evidence from new runs.
  • Knowledge Base Updates: Rebuilds the master index (run-index.yaml and vault/_index.md) for comprehensive research tracking.
  • Use Case: After running a new multi-agent simulation, use this Skill to automatically create a detailed experiment note, link it to relevant prior research claims, and update the project's central knowledge index.

Quick Start

Use the synthesize skill to process the latest run in the runs directory.

Frequently Asked Questions about synthesize

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

FAQPage Schema
How do I automate documentation for multi-agent simulation runs?

To automate documentation for multi-agent simulation runs, this skill parses run.yaml and summary files to generate structured experiment notes and updates the central knowledge base index for consistent research tracking.

How do I link new simulation evidence to existing research claims?

Link new simulation evidence to existing research claims by scanning vault claim data against new run results. The synthesis process checks for new evidence supporting or weakening existing claims and rebuilds the master index for comprehensive tracking.

Do I need Python to synthesize simulation run data into vault notes?

Yes, Python is required to synthesize simulation run data into vault notes. The skill depends on Python to parse run metadata, generate experiment notes, and rebuild the research knowledge base index.

What's the best way to rebuild a research knowledge base index after new simulation runs?

The best way to rebuild a research knowledge base index after new simulation runs is to synthesize run metadata and summary data. This process updates run-index.yaml and vault/_index.md to ensure research findings remain consistently documented and discoverable.

Can I use this synthesis skill without existing vault claim data?

Using this synthesis skill without existing vault claim data limits its core functionality. The skill requires access to run configuration, results, and vault claim data to perform evidence linking and generate complete experiment notes for the knowledge base.