Dexter is an autonomous agent designed to plan and execute complex financial data analysis for stocks, crypto, and company fundamentals.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install dexter
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 dexter 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 Dexter?
Dexter is a specialized autonomous financial research agent integrated into the Openclaw Skills ecosystem. It streamlines the process of gathering and synthesizing market data, financial statements, and regulatory filings. By leveraging advanced LLMs and dedicated financial APIs, Dexter can handle everything from simple price checks to deep-dive comparative analyses between major corporations.
This skill is particularly valuable for developers and analysts who need to automate the retrieval of high-fidelity financial information. Whether you are tracking US equity markets or monitoring cryptocurrency trends, Dexter acts as a tireless researcher. It effectively bridges the gap between raw data sources like Financial Datasets and actionable insights, making it a cornerstone for those building financial tools or performing market due diligence using Openclaw Skills.
Dexter Use Cases
- Retrieving real-time and historical stock prices for US-based equities.
- Analyzing comprehensive financial statements including income sheets, balance sheets, and cash flow reports.
- Conducting deep dives into SEC filings such as 10-K, 10-Q, and 8-K reports to identify risk factors or material changes.
- Comparing financial metrics like P/E ratios, revenue growth, and profit margins across multiple companies.
- Monitoring cryptocurrency price trends and historical data for major pairs like BTC-USD.
- Tracking insider trading activities and analyst earnings estimates for market sentiment analysis.
How Dexter Works
- Understand: The agent extracts intent, ticker symbols, and specific time periods from the user's natural language query.
- Plan: Dexter creates a detailed task list with logical dependencies to ensure all necessary data points are gathered.
- Execute: It runs multiple data retrieval tasks in parallel, calling specific financial or web search APIs.
- Reflect: The agent evaluates the gathered data and determines if more information is needed, iterating up to five times to ensure completeness.
- Answer: Finally, it synthesizes the findings into a comprehensive response with cited sources.
Dexter Setup
First, clone the repository and install dependencies using Bun to begin using this part of the Openclaw Skills collection:
DEXTER_DIR="/root/clawd-workspace/dexter"
git clone https://github.com/virattt/dexter.git "$DEXTER_DIR"
cd "$DEXTER_DIR"
bun install
Configure your .env file with required API keys for Anthropic and Financial Datasets. You can also add a Tavily key for web search fallback:
cat > "$DEXTER_DIR/.env" << 'EOF'
ANTHROPIC_API_KEY=your-anthropic-key
FINANCIAL_DATASETS_API_KEY=your-financial-datasets-key
TAVILY_API_KEY=your-tavily-key
EOF
If using Anthropic, apply the patch to update the default tool executor model and set the provider in settings.json to ensure compatibility with your Openclaw Skills workflow:
sed -i "s/const SMALL_MODEL = 'gpt-5-mini';/const SMALL_MODEL = 'claude-3-5-haiku-latest';/" "$DEXTER_DIR/src/agent/tool-executor.ts"
Dexter Data Schema & Taxonomy
Dexter organizes its financial research through structured tool outputs and configuration files to maintain high data integrity within Openclaw Skills.
| Component | Description |
|---|---|
| .env | Stores sensitive API credentials for LLMs and financial data providers. |
| .dexter/settings.json | Defines the model provider and specific LLM ID for the agent. |
| Financial Statements | JSON-structured data covering Income, Balance, and Cash Flow metrics. |
| SEC Filings | Parsed sections of 10-K, 10-Q, and 8-K documents. |
| Crypto Data | Ticker-based snapshots and historical price arrays. |
Dexter Advanced Features
- Multi-phase autonomous planning and reflection for complex, multi-step financial inquiries.
- Automatic fallback to web search via Tavily for international stocks not covered by primary financial APIs.
- Non-interactive query mode for quick CLI-based data retrieval and automation scripts.
- Interactive multi-turn research sessions supported via tmux integration for deep analysis within the Openclaw Skills environment.
- Parallel task execution to minimize latency during high-volume data gathering.
SKILL.md
Loading
Related Openclaw Skills
x-cli
A comprehensive X/Twitter CLI toolkit for AI agents that enables full platform interaction via cookie-based authentication without requiring official API keys.
Alexa Remote Control
A command-line interface skill for controlling Amazon Echo devices and smart home integrations using shell scripts.
SwiftUI Empty App Init
A lightweight skill to bootstrap a single-target SwiftUI iOS application using XcodeGen for version-control-friendly project management.
Image OCR Reader
A robust OCR utility that extracts Chinese and English text from images using the Tesseract engine for AI-driven workflows.
Context Builder
An agentic CLI tool that converts entire directories into structured, relevance-sorted markdown files optimized for LLM ingestion and token efficiency.
Fanvue API Skill
A robust integration for managing Fanvue creator workflows including messaging, media posts, and subscriber analytics through OAuth 2.0.
Featured*
