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

run-query

Query the run index and vault for experiment history by tags, dates, types, or claims.

39|4|Updated Feb 3, 2026
Search Tags:#multi-agent systems#query#metadata retrieval#experiment history#run index
One-click install
npx skills add https://github.com/swarm-ai-research/swarm --skill run-query-swarm-ai-research
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: run-query
Source: https://github.com/swarm-ai-research/swarm/tree/main/.skills/run-query
Command: npx skills add https://github.com/swarm-ai-research/swarm --skill run-query-swarm-ai-research

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The run-query Skill simplifies the process of retrieving experiment history by enabling targeted searches based on tags, dates, types, or claims.

Core Features & Use Cases

  • Targeted Search: Find runs quickly by specifying tags, dates, types, or claims.
  • Metadata Retrieval: Access run metadata and pointers without downloading raw data.
  • Use Case: Suppose you need to review all experiments related to a specific claim. Use the run-query Skill to filter by claim and retrieve the relevant information in seconds.

Quick Start

Query the run index and vault for experiment history by tag, date, type, or claim. Example: run-query tag <tag>.

Frequently Asked Questions about run-query

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

FAQPage Schema
How do I retrieve experiment history metadata without downloading raw data?▼

Filter experiment history by querying the run index and vault using tags, dates, types, or claims. This retrieves run metadata and pointers directly without downloading raw data.

What is the best way to search multi-agent system experiment runs by claim?▼

The best way to search runs by claim in multi-agent systems is to use a targeted query filtering the run index. This retrieves all relevant experiment information related to that specific claim in seconds.

How do I query runs in a vault directory by date and tag?▼

To query runs by date and tag, execute a targeted search against the run index and vault directories. This filters your experiment history precisely, returning matching run metadata for your specified criteria.

Can I use this query approach for large-scale multi-agent experiments?▼

Yes, this querying approach is specifically designed for researchers and developers managing large-scale experiments in multi-agent systems. It requires access to existing run index and vault directories to function.

Do I need access to the run index and vault directories to search experiment history?▼

Yes, you need access to the run index and vault directories to search experiment history. The query mechanism depends on these directories to filter and retrieve run metadata based on your specified tags or dates.

Related Skills

Explore More Software Engineering Skills→
swarm-ai-safetyswarm-ai-safety
39

run-query

Query run-index.yaml and vault claims for experiment metadata by tag, date, type, or claim.

Official
Intermediate
Driving-TeacherDriving-Teacher
1

experiment-share

Fetch Hackle MCP experiment data, compare with snapshots, and share insights via Slack.

Official
Advanced
swarm-ai-safetyswarm-ai-safety
39

synthesize

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

Official
Advanced
ccfccf

similarity-search-patterns

Detail distance metrics and index types for vector similarity search across Pinecone, Qdrant, pgvector, and Weaviate.

Community
Advanced