A sophisticated engine that converts rough research topics into fully-configured, multi-agent USACF swarm protocols for deep analysis.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install research-reprompter
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install research-reprompter using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Researcher v2.0: USACF Research Generator?
Researcher v2.0 is a specialized tool designed to bridge the gap between abstract research inquiries and structured, executable multi-agent workflows. By leveraging the USACF framework, it automates the creation of complex research environments within Claude Code, ensuring that every investigation includes professional-grade components like adversarial review and fact-checking. This skill is a cornerstone for users of Openclaw Skills who require high-fidelity data synthesis and rigorous analysis without the manual overhead of configuring individual agent roles and memory namespaces.
The system goes beyond simple prompting by generating a complete swarm configuration. It intelligently maps your requirements to specific agent architectures, ensuring that the resulting research is balanced, challenged by red-teaming, and backed by systematic memory operations. Whether you are conducting market due diligence or a technical deep dive, this skill provides the infrastructure needed for autonomous, high-quality discovery.
Researcher v2.0: USACF Research Generator Use Cases
- Transforming vague requests like "look into this" into structured multi-agent research plans.
- Conducting competitive intelligence or market gap analysis with automated red-teaming and adversarial review.
- Performing technical due diligence or deep-dive investigations into complex software architectures using Openclaw Skills.
- Generating executable claude-flow configurations for parallel discovery and synthesis phases without manual setup.
How Researcher v2.0: USACF Research Generator Works
- Receive a raw research prompt or trigger word such as research, investigate, or deep dive.
- Analyze the input complexity to automatically select the optimal algorithm: Chain-of-Thought (CoT), Tree-of-Thought (ToT), or Graph-of-Thought (GoT).
- Conduct a smart interview to capture essential details such as objectives, subject type, research depth, and desired output format.
- Generate a comprehensive USACF super-prompt including initialization commands, agent definitions (Discovery, Analysis, Adversarial, Synthesis), and memory operations.
- Present a quality score comparison showing the improvement in prompt engineering and provide the final executable configuration for immediate deployment.
Researcher v2.0: USACF Research Generator Setup
To utilize the full capabilities of this skill within the Openclaw Skills ecosystem, ensure you have Claude Code and the claude-flow extension installed.
# Initialize claude-flow if not already present
npx claude-flow@alpha init --force
# Trigger the researcher skill within your agent environment
research "Your research topic here"
The skill will then guide you through the smart interview process to generate your swarm configuration.
Researcher v2.0: USACF Research Generator Data Schema & Taxonomy
Researcher v2.0 implements a strict memory namespace convention to ensure data integrity across multiple agents in the swarm:
| Namespace | Data Type | Description |
|---|---|---|
session/config |
JSON | Core research configuration and metadata |
meta/research-plan |
List | Decomposed questions and planned task lists |
discovery/* |
Markdown | Parallel findings from component, hierarchy, and flow analysis |
gaps/* |
Markdown | Identified quality, performance, and security gaps |
adversarial/* |
Reports | Red team critiques and RAG-verified fact-checks |
output/final-report |
Report | The synthesized executive summary and action plan |
Researcher v2.0: USACF Research Generator Advanced Features
- Automated Algorithm Selection: Dynamically chooses between CoT, ToT (4-8 agents), and GoT (9-15+ agents) based on query complexity indicators.
- Adversarial Review Loop: Integrates dedicated red-team agents and fact-checkers to challenge findings and improve confidence scores before final synthesis.
- Parallel Processing Swarms: Orchestrates multiple parallel agents across discovery and analysis phases to maximize research breadth within Openclaw Skills.
- Strategic Synthesis: Generates multi-horizon recommendations (Quick Wins, Strategic, Transformational) and Pareto-optimized portfolios.
- Quality Metric Benchmarking: Provides a before-and-after scoring matrix to visualize the enhancement in research clarity and agent design.
SKILL.md
Loading
Related Openclaw Skills
Ralph Ultra
A high-intensity, 1,000-iteration security audit engine designed for deep-dive code reviews, compliance prep, and infrastructure hardening.
Ralph Security
A rigorous security auditing agent that performs a structured 100-iteration deep dive into codebases, infrastructure, and secrets.
Ralph Quick Security Auditor
A high-speed security auditor that performs a 10-step spot-check for vulnerabilities in under 10 minutes.
Humanizer Enhanced
A professional-grade content refinement tool that detects and eliminates 34 distinct AI writing patterns while injecting personality and soul into drafts.
Skeall
Skeall is a professional CLI-based toolset for scaffolding, auditing, and optimizing high-performance Openclaw Skills.
Traktor Web Asset Extractor
Traktor is a high-performance web asset extraction tool designed to scrape images, videos, fonts, and page architecture using multi-agent parallel processing.
Featured*
