deep-research
Automated deep research that performs comprehensive multi-source investigation and produces detailed reports with citations. Use when user requests research, investigation, or in-depth analysis of any topic. Capabilities: generate structured research plans, and start sub agent to execute the plan.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/bird-frank/deep-research-planWhat This Skill Does
The deep-research skill transforms OpenClaw into a sophisticated research assistant capable of conducting multi-source investigations. Rather than providing quick, shallow answers, this skill employs a structured two-phase workflow that mimics professional research methodologies.
In Phase 1 (Planning), the agent collaborates with you to refine your inquiry. It breaks down broad topics into targeted sub-questions, sets research boundaries (scope), and defines specific output requirements. This ensures the agent understands your goals perfectly before it consumes tokens on actual data retrieval.
In Phase 2 (Execution), the agent enters a high-autonomy mode where it utilizes a sub-agent to navigate, scrape, and synthesize information from multiple sources. It performs iterative searches, dynamically adjusting its strategy based on initial findings, and finally compiles a comprehensive, cited, and well-structured report tailored exactly to your specified constraints.
Installation
Run the following command in your OpenClaw terminal:
clawhub install openclaw/skills/skills/bird-frank/deep-research-plan
Use Cases
- Market Research: Analyzing industry trends, identifying key players, and summarizing competitive landscapes.
- Technical Documentation: Compiling deep dives into complex technologies, programming languages, or architectural patterns.
- Academic/Fact Finding: Gathering evidence-based information for reports, essays, or decision-making processes.
- Strategic Analysis: Investigating the long-term feasibility of a new business model or project direction.
Example Prompts
- "I need a deep research report on the current state of decentralized identity solutions. Please start by helping me draft a research plan."
- "Perform an investigation into the scalability challenges of Layer 2 rollup solutions compared to sharding, focusing on technical trade-offs."
- "Conduct a deep dive into the recent advancements in sustainable agricultural technology for arid climates, including a list of the top 10 startups in this space."
Tips & Limitations
- Phase 2 involves significant data processing; ensure your session has the necessary resources enabled.
- Always review the generated JSON plan carefully; the quality of your report is directly dependent on the precision of the research questions you approve.
- The skill defaults to a minimum of 8 sources but can be configured for deeper analysis by adjusting the plan parameters.
- Respect the 'Wait for confirmation' rule: the agent will pause indefinitely until you explicitly approve the research plan file.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-bird-frank-deep-research-plan": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, network-access
Related Skills
himalaya
Expert guidance for querying, writing, and managing emails using the `himalaya` CLI. Use this skill whenever the user wants to list emails, search envelopes, compose messages, manage flags/folders, or execute any himalaya command. Also trigger when the user mentions "email CLI", "terminal email", "manage emails from command line", or references the Himalaya mail client. This skill provides the full query DSL specification, command patterns, and best practices for the himalaya email CLI.
ddgs-web-search
Use when needing to search the web in AI coding tools or OpenClaw. Uses DuckDuckGo API without API key.
deep-research-executor
Execute deep research by performing comprehensive web searches and synthesizing findings into detailed reports. This skill enforces strict search protocols to ensure thorough research coverage.