Deep Research Swarm
- 17 installs
- 869 repo stars
- Updated June 8, 2026
- beita6969/scienceclaw
deep-research-swarm is a Claude skill that coordinates a swarm of agents to run parallelized deep research over biomedical literature and aggregate cited reports.
About
This skill coordinates a swarm of agents to run parallelized deep research over biomedical literature. A researcher uses it for exhaustive reviews, connecting evidence across many papers and generating hypotheses. It aggregates findings into reports and verifies that claims are backed by sources.
- Coordinates a swarm of agents for parallelized biomedical literature research
- Runs an agent_coordinator script with topic and depth options
- Aggregates evidence into reports with citation verification
Deep Research Swarm by the numbers
- 17 all-time installs (skills.sh)
- Ranked #10,813 of 16,556 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 2, 2026 (Skillselion catalog sync)
deep-research-swarm capabilities & compatibility
- Capabilities
- multi agent research · literature review · hypothesis generation
- Use cases
- research · orchestration · web search
- Runs
- Runs locally
- Pricing
- Free
What deep-research-swarm says it does
A coordinated swarm of agents designed to perform deep, parallelized research into biomedical literature, aggregating findings into comprehensive reports.
Generates comprehensive literature review with >50 citations in <5 minutes.
npx skills add https://github.com/beita6969/scienceclaw --skill deep-research-swarmAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 17 |
|---|---|
| repo stars | ★ 869 |
| Last updated | June 8, 2026 |
| Repository | beita6969/scienceclaw ↗ |
What it does
Run a multi-agent swarm that parallel-searches biomedical literature and aggregates cited review reports.
Who is it for?
Exhaustive multi-agent reviews across many biomedical papers with hypothesis generation.
Skip if: Single quick lookups that do not need a parallel agent swarm.
When should I use this skill?
You need an exhaustive, parallelized review connecting evidence across many biomedical papers.
What you get
An aggregated, citation-verified literature review with generated hypotheses.
- Aggregated literature review report
- Generated hypotheses
By the numbers
- Stated outcome: literature review with >50 citations in <5 minutes
- 3 core capabilities (parallel search, synthesis, citation verification)
Files
<!--
COPYRIGHT NOTICE
This file is part of the "Universal Biomedical Skills" project.
Copyright (c) 2026 MD BABU MIA, PhD <md.babu.mia@mssm.edu>
All Rights Reserved.
#
This code is proprietary and confidential.
Unauthorized copying of this file, via any medium is strictly prohibited.
#
Provenance: Authenticated by MD BABU MIA
-->
--- name: deep-research-swarm description: Multi-agent research literature analysis keywords:
- research
- literature
- swarm
- multi-agent
- hypothesis
measurable_outcome: Generates comprehensive literature review with >50 citations in <5 minutes. license: MIT metadata: author: Biomedical OS Team version: "1.0.0" compatibility:
- system: Python 3.10+
allowed-tools:
- run_shell_command
- read_file
- google_web_search
---
DeepResearch Swarm
A coordinated swarm of agents designed to perform deep, parallelized research into biomedical literature, aggregating findings into comprehensive reports.
When to Use This Skill
- When you need an exhaustive review of a specific medical topic.
- When connecting disparate pieces of evidence across thousands of papers.
- When generating hypotheses based on recent literature.
Core Capabilities
1. Parallel Search: Querying multiple databases simultaneously. 2. Evidence Synthesis: Combining facts into a coherent narrative. 3. Citation Verification: Ensuring all claims are backed by sources.
Example Usage
User: "Research the latest advancements in mRNA cancer vaccines."
Agent Action:
python3 src/research/agents/agent_coordinator.py --topic "mRNA cancer vaccines" --depth "deep"<!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE -->
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10FAQ
What are its core capabilities?
Parallel search across databases, evidence synthesis into a narrative, and citation verification of every claim.
How is it invoked?
It runs agent_coordinator.py with a topic and depth, for example --topic and --depth deep.