deep-research-swarm

COPYRIGHT NOTICE

564 stars

Best use case

deep-research-swarm is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

COPYRIGHT NOTICE

Teams using deep-research-swarm should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/deep-research-swarm/SKILL.md --create-dirs "https://raw.githubusercontent.com/beita6969/ScienceClaw/main/skills/deep-research-swarm/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/deep-research-swarm/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How deep-research-swarm Compares

Feature / Agentdeep-research-swarmStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

COPYRIGHT NOTICE

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

<!--
# 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**:
```bash
python3 src/research/agents/agent_coordinator.py --topic "mRNA cancer vaccines" --depth "deep"
```


<!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE -->

Related Skills

social-science-research

564
from beita6969/ScienceClaw

Orchestrates a social science research workflow from literature review through data collection, text analysis, statistical modeling, and report generation. Use when conducting empirical social science research, policy analysis, or mixed-methods studies. NOT for pure natural science analysis or clinical trial data.

research-reflection

564
from beita6969/ScienceClaw

Reflect on completed research tasks to improve future performance. Use when: a research task has just been completed and the agent should evaluate its own process, store lessons learned, or retrieve past reflections before starting new work. NOT for: active research execution or data analysis.

research-lookup

564
from beita6969/ScienceClaw

Look up current research information using the Parallel Chat API (primary) or Perplexity sonar-pro-search (academic paper searches). Automatically routes queries to the best backend. Use for finding papers, gathering research data, and verifying scientific information.

research-literature

564
from beita6969/ScienceClaw

COPYRIGHT NOTICE

research-grants

564
from beita6969/ScienceClaw

Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance with submission requirements.

research-ethics

564
from beita6969/ScienceClaw

Guides research ethics compliance including IRB protocol preparation, informed consent document drafting, research integrity standards, data management plans, and ethical considerations for human/animal subjects; trigger when users discuss IRB, ethical approval, consent forms, or responsible conduct of research.

psychology-research

564
from beita6969/ScienceClaw

Conduct psychological research analysis including mental health, cognitive science, and behavioral studies

education-research

564
from beita6969/ScienceClaw

Supports education research including pedagogical method evaluation, learning analytics, assessment design, curriculum development analysis, and educational technology evaluation; trigger when users discuss teaching effectiveness, learning outcomes, educational interventions, or student performance data.

deep-research

564
from beita6969/ScienceClaw

Execute autonomous multi-step deep research on any topic. Use when the user asks for comprehensive research, literature reviews, competitive analysis, topic deep-dives, or wants to understand a complex subject from multiple angles. Triggers on "deep research", "research on", "investigate", "literature review", "comprehensive analysis", "what do we know about", "summarize research on".

creative-thinking-for-research

564
from beita6969/ScienceClaw

Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.

academic-deep-research

564
from beita6969/ScienceClaw

Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per theme, APA 7th citations, evidence hierarchy, and 3 user checkpoints. Self-contained using native OpenClaw tools (web_search, web_fetch, sessions_spawn). Use for literature reviews, competitive intelligence, or any research requiring academic rigor and reproducibility.

xurl

564
from beita6969/ScienceClaw

A CLI tool for making authenticated requests to the X (Twitter) API. Use this skill when you need to post tweets, reply, quote, search, read posts, manage followers, send DMs, upload media, or interact with any X API v2 endpoint.