skills.rest
swarm-ai-research
swarm-ai-researchOFFICIAL
Explore all skills by this author →
Website𝕏@ResearchSwarmAIGitHub

sanity-check

Validate multi-agent system scenarios with minimal seeds and epochs.

39|4|Updated Feb 3, 2026
Search Tags:#multi-agent systems#sanity test#agent validation#quick check#SWARM framework
One-click install
npx skills add https://github.com/swarm-ai-research/swarm --skill sanity-check-swarm-ai-research
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sanity-check
Source: https://github.com/swarm-ai-research/swarm/tree/main/.skills/sanity-check
Command: npx skills add https://github.com/swarm-ai-research/swarm --skill sanity-check-swarm-ai-research

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill provides a quick validation run before committing to a full sweep, ensuring that scenarios with minimal seeds/epochs run correctly without crashes and metric anomalies.

Core Features & Use Cases

  • Scenario Validation: Runs a scenario with minimal seeds/epochs to check for crashes and metric sanity.
  • Minimal Run: Uses a small number of seeds and epochs to validate the scenario quickly.
  • Report: Generates a go/no-go report based on runtime and metric checks.

Quick Start

Run the sanity-check for a scenario with 'python -m swarm run scenarios/your_scenario --seed 42 --epochs 5 --steps 5'.

Frequently Asked Questions about sanity-check

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

FAQPage Schema
How do I validate multi-agent system scenarios for crashes before a full sweep?▼

You can validate multi-agent system scenarios by running them with minimal seeds and epochs to quickly check for crashes and metric anomalies before committing to a full sweep.

What is a quick sanity test for agent validation in the SWARM framework?▼

A quick sanity test for agent validation runs your scenario with a small number of seeds and epochs, generating a go/no-go report based on runtime and metric checks.

Does the SWARM framework require Python to run a quick scenario check?▼

Yes, running a quick scenario check requires Python and the SWARM framework to execute the validation scripts and generate the runtime report.

How do I run a minimal validation check for a multi-agent scenario?▼

Run a minimal validation check by executing 'python -m swarm run scenarios/your_scenario --seed 42 --epochs 5 --steps 5' to test runtime correctness quickly.

When should I not use a minimal seed run for agent validation?▼

You should not use a minimal seed run when you need final performance metrics, as it only checks for initial correctness, crashes, and metric anomalies before a full sweep.

Related Skills

Explore More Software Engineering Skills→
swarm-ai-researchswarm-ai-research
39

experiment-loop

Automate multi-agent experiment design, execution, and result synthesis.

Official
Advanced
TobiasWooldridgeTobiasWooldridge
1

harness-runner

Automates WaveCap-SDR regression testing and parameter sweeps, outputting JSON/text reports.

Community
Intermediate
Agentic-Engineering-AgencyAgentic-Engineering-Agency
3

specsafe-qa

Validate AI-generated code against specifications and generate GO/NO-GO reports.

Official
Intermediate
swarm-ai-researchswarm-ai-research
39

run-scenario

Execute predefined SWARM simulation scenarios and export standardized results.

Official
Intermediate