Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Runs multi-agent research workflows via the dr.eamer.dev API. Supports two modes: Dream Swarm dispatches parallel agents across multiple data sources simultaneously, and Dream Cascade runs a three-tier hierarchical pipeline where agents gather, synthesize, and summarize in stages.
Parallelizing across specialized agents compresses what would be many sequential queries into a single API call with a unified synthesized result.
When to use it
- Researching a medical topic across PubMed and academic sources
- Synthesizing competitive landscape analysis from multiple domains
- Summarizing the state of a technical field with an executive briefing
- Cross-domain policy research requiring perspectives from multiple disciplines
- Deep-dive analysis on a scientific question that would take many sequential queries
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: What are the most effective treatments for Type 2 diabetes?
- 1Send POST request to /v1/orchestrate/swarm with the query and sources [pubmed, semantic_scholar, wikipedia]
- 2API spawns 5 parallel agents, each querying a subset of the specified sources
- 3Agents return domain-specific findings to the orchestrator
- 4Orchestrator synthesizes all findings into a unified response
A single synthesized answer with source attribution and metadata including agent count and duration
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.