- Home
- Skills
- Trading & Investing
- ai-quant-crypto-llm-withJev
Works with the AI Agents you already use
ai-quant-crypto-llm-withJev
A dual-layer market analysis core that validates AI directional picks with quantitative probability scoring.
$9.90
ai-quant-crypto-llm-withJev
Example session with this skill installed
Analyze the market state for ETH/USDT based on recent news and 4h price data. Provide a JEV-validated direction.
- Read your context and instructions
- Compiled the ai-quant-crypto-llm-withjev
I have completed the market analysis for ETH/USDT. I gathered news from the last 7 days and processed 1h and 4h price data. The JEV validator has scored the initial nomination, and the final decision is recorded below.
Market Analysis Report: ETH/USDT
| Metric | Value |
|---|---|
| Symbol | ETH/USDT |
| LLM Direction Pick | LONG |
| JEV Confidence Score | 0.82 |
| JEV Threshold | 0.75 |
| Adopted Direction | LONG |
| Research Window | 7 Days |
| Data Sources | Binance 1h/4h, Cointelegraph, Ethereum Foundation Blog |
Decision Review
The market shows strong accumulation near the $2,400 support level. Recent news regarding the Dencun upgrade testing on Goerli has provided a positive fundamental catalyst. The LLM nominated a LONG position based on the bullish divergence on the 4h RSI. The JEV engine returned a 0.82 probability score, which exceeds the 0.75 threshold, confirming the nomination.
Final Judgment
The convergence of technical recovery and positive protocol development support a LONG bias. The high JEV score indicates a statistically significant alignment between news sentiment and current price structure.
Next steps
- Review the specific source URLs in the
prediction_storagefor upgrade timelines. - Monitor the $2,450 resistance level for a confirmed breakout.
- Use
get_predictionin 24 hours to track how this state evolves.
Connects securely to your tools. The creator never sees your data.
About this skill
AI Quant Decision Core is an independent cryptocurrency research and directional decision engine. It integrates with Hermes through CLI or MCP, connecting news research, market data, and model analysis into a traceable decision workflow.
Hermes handles browser-based news research and task orchestration, while Core retrieves the latest 7 days of 1h / 4h market data. An LLM selects important news, analyzes the combined information, and nominates a direction. JEV acts as an auxiliary scoring model: the nomination is accepted when score ≥ JEV_SCORE_THRESHOLD; otherwise, the direction defaults to HOLD. The LLM then explains the final direction, and the result is stored in SQLite.
The project is designed solely for research and directional assessment. It does not execute real trades or provide order placement, cancellation, wallet, account, position, leverage, stop-loss, or take-profit capabilities.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Trading & Investing.
No execution capabilities. Cannot access wallets or private keys. Limited to 7-day research windows and 1h/4h candle data.
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 18 days ago
- Accounts
Cryptopanic
Coindesk
Cointelegraph
Theblock
Decrypt
Bitcoinmagazine
- Software
Python
Permissions
Allowed Hosts