- Home
- Skills
- Trading & Investing
- BTC Kalshi Market Intel Pack
More screenshots
Works with the AI Agents you already use
BTC Kalshi Market Intel Pack
Automated BTC market intelligence collection, rule-based signaling, and Kalshi contract decision fusion.
$15
BTC Kalshi Market Intel Pack
Example session with this skill installed
Scan current Kalshi hourly BTC contracts using the latest market snapshot and identify any with a minimum edge of 10% and 65% confidence.
- Read your context and instructions
- Compiled the btc kalshi market
Processed 8 active Bitcoin threshold contracts. Applied conservative edge and confidence filters.
Kalshi Hourly Scan Results
| Contract | Strike | Market Mid | Model Fair Value | Edge | Recommendation |
|---|---|---|---|---|---|
| KXBTCD-24MAY24-B68000 | >$68,000 | 0.45 | 0.62 | +0.17 | BUY YES |
| KXBTCD-24MAY24-B70000 | >$70,000 | 0.12 | 0.15 | +0.03 | NO TRADE |
| KXBTCD-24MAY24-B65000 | >$65,000 | 0.88 | 0.82 | -0.06 | NO TRADE |
| KXBTCD-24MAY24-B72000 | >$72,000 | 0.05 | 0.04 | -0.01 | NO TRADE |
Decision Summary
- Top Pick: KXBTCD-24MAY24-B68000 shows significant edge (17%) above the 10% minimum threshold.
- Abstentions: 7 contracts resulted in NO TRADE. Most failed the
min_edgeguard or had spreads exceeding 0.08.
Warnings: Source health for derivatives data is degraded (Binance API timeout). Liquidity score for strike $72k is below 0.50.
Next steps
- Manually verify the order book depth for the $68k strike on the Kalshi interface.
- Review
hourly_outputs/scan_20240524_1400.jsonfor full driver breakdown. - Check
signal_engineoutput to confirm if macro sentiment aligns with the 60m horizon model.
Connects securely to your tools. The creator never sees your data.
About this skill
Manually assessing Bitcoin market indicators and Kalshi contract spreads is slow and prone to emotional bias. This skill pack automates the end-to-end research pipeline from raw API data collection to guarded decision fusion.
What it does
- Data collection builds multi-source Bitcoin snapshots including price, liquidity, derivatives, and sentiment into structured JSON.
- Rule-based scoring transforms market snapshots into explainable directional probabilities (up, down, range) for 12h and 24h horizons.
- Horizon-matched scanning filters Kalshi-style threshold contracts against ML models to identify fair value vs market mid.
- Decision fusion applies strict edge and confidence guards to recommend BUY YES, BUY NO, or NO TRADE.
- Calibration auditing tracks Brier scores and log loss across prediction logs to detect model drift.
How it works
- Run
btc_market_intel_collector.pyto generate a fresh intelligence snapshot from public APIs. - Pipe the snapshot into
signal_engine.pyto extract deterministic probabilities and key drivers. - Execute
hourly_event_scanner.pyto rank active contracts based on horizon-matched model forecasts. - Review the
decision-report.mdoutput which fuses model edge with market-implied probabilities.
Frameworks & tools
This skill requires Python 3.11+. It integrates with the bitcoin-data-collector repository and uses libraries for JSON schema validation and statistical evaluation of prediction logs.
Why this beats prompting it yourself
Generic prompts fail to maintain consistent probability schemas or calculate Brier scores accurately over time. This tool enforces deterministic logic and strict liquidity gates that prevent acting on thin order books or low-confidence noise.
Use cases
- Generating explainable BTC directional odds for research reports.
- Filtering hourly Kalshi threshold markets for contracts with specific edge.
- Auditing prediction accuracy to decide when model retraining is necessary.
- Validating source health across multiple market data providers.
Known limitations
Does not support automated order execution or live trading. Requires manual checkout of the data collector repository for full ML horizon matching.
No automated execution or order routing. Requires Python 3.11+. ML features require local model directories for specific horizons. Data limited to public API availability.
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 any payment.
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 6 days ago
Requires