- Home
- Skills
- Agents & Orchestration
- AutoHedge
Works with the AI Agents you already use
AutoHedge
Autonomous multi-agent hedge-fund framework (Director, Quant, Risk Manager, Execution agents) for market analysis and structured trading theses.
$5
AutoHedge
Example session with this skill installed
Analyze the sentiment of the Solana ecosystem and provide a structured thesis on a potential 10 SOL allocation for long-term growth.
- Read your context and instructions
- Compiled the autohedge
I have initiated the AutoHedge pipeline. The Director agent identified SOL as the primary asset, the Quant agent analyzed recent price action and Jupiter volume, and the Risk Manager evaluated the 10 SOL allocation relative to current volatility.
Market Thesis: Solana Growth Position
| Agent | Output Summary |
|---|---|
| Director | Focused on Solana (SOL) ecosystem health, specifically DEX volume and developer activity. |
| Quant | Technicals show a bullish divergence on the 4H chart. Relative Strength Index (RSI) is at 58. Volume on Jupiter is up 12% week-over-week. |
| Risk Manager | 10 SOL allocation is deemed Low-Medium risk. Recommended stop-loss at 15% below entry. Risk/Reward ratio calculated at 1:3.4. |
| Execution | Recommendation: Market Buy. The structured thesis suggests accumulating in the current price range for a 6-12 month horizon. |
Next steps
- Review the technical indicators in the
outputsdirectory for specific entry triggers. - Ensure your
JUPITER_API_KEYis active if you require real-time price slippage data. - If you decide to proceed, you can execute the trade manually or via the AutoHedge CLI if your wallet is configured.
Connects securely to your tools. The creator never sees your data.
About this skill
Market analysis often suffers from fragmentation, where technical data, sentiment, and risk assessment live in silos. This skill implements the AutoHedge framework to coordinate a specialized multi-agent pipeline that produces unified, actionable trading theses.
What it does
- Multi-agent orchestration coordinates a Director, Quant, Risk Manager, and Execution agent in a sequential pipeline.
- Automated ticker selection uses the Director agent to derive relevant assets and tickers directly from natural language tasks.
- Technical analysis employs the Quant agent to evaluate market data and technical indicators.
- Risk assessment forces every thesis through a Risk Manager agent to determine position sizing and risk profiles.
- Structured output returns final recommendations as list, dict, or string formats for programmatic consumption.
How it works
- Environment setup requires installing the
autohedgepackage and configuring LLM and Jupiter API keys in a.envfile. - Initialization involves creating an
AutoHedgeinstance with a defined fund name, description, and output format. - Task execution occurs by passing a natural language prompt to the
run()method or the interactive CLI. - Pipeline processing moves the task from strategy selection to technical audit, then risk filtering, before generating the final thesis.
Frameworks & tools
Built on the swarms library using swarm-models, pydantic, and fastapi. It utilizes the Jupiter API for Solana market data and supports OpenAI or Anthropic LLMs for agent intelligence.
Why this beats prompting it yourself
Standard prompts often ignore risk constraints or fail to bridge the gap between technical indicators and execution logic. This skill enforces a strict agent-based hierarchy where the Risk Manager can veto or adjust Quant findings, ensuring a balanced thesis that mimics professional fund operations.
Use cases
- Generate structured sentiment analysis for specific market sectors or assets.
- Build a custom autonomous fund pipeline for Solana-based tokens.
- Perform risk-adjusted technical audits on portfolio allocations.
- Automate market research tasks via a CLI-based interactive REPL.
Known limitations
Currently targets Solana via Jupiter for live data, with other integrations planned. Requires Python 3.10 or higher. Live trade execution is disabled by default and requires manual wallet configuration.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
Requires Python 3.10+. Native live data support is currently focused on Solana via Jupiter. Live execution requires manual WALLET_PRIVATE_KEY setup.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 5 days ago
- Software
Python