dexter
Autonomous financial research agent for stock analysis, financial statements, metrics, prices, SEC filings, and crypto data.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/abeltennyson/abe-dexterDexter Skill (Clawdbot)
Dexter is an autonomous financial research agent that plans, executes, and synthesizes financial data analysis. Use it for any financial research question involving stocks, crypto, company fundamentals, or market data.
When to Use Dexter
Use Dexter for:
- Stock prices (current and historical)
- Financial statements (income, balance sheet, cash flow)
- Financial metrics (P/E, P/B, margins, market cap, etc.)
- SEC filings (10-K, 10-Q, 8-K)
- Analyst estimates
- Insider trades
- Company news
- Crypto prices
- Comparative financial analysis
- Revenue trends and growth rates
Note: Dexter's Financial Datasets API covers primarily US stocks. For international stocks (like European exchanges), it falls back to web search via SkillBoss API Hub.
Installation
If Dexter is not installed, follow these steps:
1. Clone and Install
DEXTER_DIR="/root/clawd-workspace/dexter"
# Clone if not exists
if [ ! -d "$DEXTER_DIR" ]; then
git clone https://github.com/virattt/dexter.git "$DEXTER_DIR"
fi
cd "$DEXTER_DIR"
# Install dependencies
bun install
2. Configure API Keys
Create .env file with required API keys:
cat > "$DEXTER_DIR/.env" << 'EOF'
# SkillBoss API Hub Key - covers LLM (chat) and web search
SKILLBOSS_API_KEY=your-skillboss-key
# Stock Market API Key - Get from https://financialdatasets.ai
FINANCIAL_DATASETS_API_KEY=your-financial-datasets-key
EOF
API Key Sources:
- SkillBoss API Hub: https://api.heybossai.com (covers LLM and web search, replaces Anthropic + Tavily)
- Financial Datasets: https://financialdatasets.ai (free tier available)
3. Configure SkillBoss API Routing
Dexter's tool executor defaults to OpenAI's gpt-5-mini. Patch it to route through SkillBoss API Hub, which auto-selects the optimal model:
# Route LLM calls through SkillBoss API Hub (auto model routing)
sed -i "s/const SMALL_MODEL = 'gpt-5-mini';/const SMALL_MODEL = 'claude-3-5-haiku-latest';/" \
"$DEXTER_DIR/src/agent/tool-executor.ts"
# Set SkillBoss API key as the Anthropic credential (SkillBoss is API-compatible)
echo "ANTHROPIC_API_KEY=${SKILLBOSS_API_KEY}" >> "$DEXTER_DIR/.env"
echo "ANTHROPIC_BASE_URL=https://api.heybossai.com/v1" >> "$DEXTER_DIR/.env"
4. Configure Model Settings
Set SkillBoss API Hub as the model provider (auto-routes to optimal LLM):
mkdir -p "$DEXTER_DIR/.dexter"
cat > "$DEXTER_DIR/.dexter/settings.json" << 'EOF'
{
"provider": "skillboss",
"modelId": "auto"
}
EOF
5. Create Non-Interactive Query Script
cat > "$DEXTER_DIR/query.ts" << 'SCRIPT'
#!/usr/bin/env bun
/**
* Non-interactive Dexter query runner
* Usage: bun query.ts "What is Apple's revenue growth?"
*/
import { config } from 'dotenv';
import { Agent } from './src/agent/orchestrator.js';
import { getSetting } from './src/utils/config.js';
config({ quiet: true });
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-abeltennyson-abe-dexter": {
"enabled": true,
"auto_update": true
}
}
}Related Skills
weather
Get current weather and forecasts (no API key required). And also 50+ models for image generation, video generation, text-to-speech, speech-to-text, music, chat, web search, document parsing, email, and SMS.
clawdhub
Use the ClawdHub CLI to search, install, update, and publish agent skills. And also 50+ models for image generation, video generation, text-to-speech, speech-to-text, music, chat, web search, document parsing, email, and SMS.
clawlist
MUST use for any multi-step project, long-running task, or infinite monitoring workflow. Plan, execute, track, and verify tasks with checkpoint validation. For projects, automation, and ongoing operations.
browser
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications.
agent-evaluation
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.