session behavior profiler

    1

    Builds empirical behavioral profiles for market sessions using range, volume, and volatility metrics.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    session behavior profiler

    Example session with this skill installed

    Analyze the last 30 days of BTC/USD 15m data. Focus on the London/New York overlap behavior regarding range expansion and gap continuation.

    • Read your context and instructions
    • Compiled the session behavior profiler

    london_ny_overlap:
    range_profile:
    avg_range_atr: 1.25
    range_classification: expansion
    continuation_profile:
    prior_close_continuation_probability: 0.68
    behavioral_signature: "High volatility expansion zone, strong trend persistence from London open."

    Connects securely to your tools. The creator never sees your data.

    About this skill

    The problem

    Traders often struggle to quantify how market behavior shifts between sessions, leading to strategies that fail during low-volume lunch hours or high-volatility opens. Relying on gut feeling about session characteristics lacks the empirical backing needed for systematic backtesting.

    What it does

    • Segments OHLCV time series data into Asia, London, New York, lunch, and close windows.
    • Calculates normalized range profiles including ATR percentiles and expansion/contraction classifications.
    • Analyzes volume intensity relative to daily averages and session-specific benchmarks.
    • Quantifies directional bias using body-to-wick ratios and R-multiple net moves.
    • Measures continuation probabilities to identify persistence or reversal tendencies between sessions.

    Frameworks & tools

    Works with standard OHLCV data structures, CSV exports, or JSON time series. Applicable for Python (Pandas/NumPy) or TypeScript financial analysis environments.

    Why this beats prompting it yourself

    Manually prompting for session analysis often results in vague qualitative descriptions. This skill enforces a strict quantitative framework, calculating specific metrics like body ratios and annualized realized volatility that generic LLMs miss without deep financial engineering instructions.

    Use cases

    • Identify which sessions have the highest probability of filling overnight gaps.
    • Adjust risk parameters based on the volatility state of the upcoming session.
    • Filter trade signals that occur during low-intensity volume phases like the lunch window.
    • Optimize entry timing by aligning with session-specific directional consistency.

    Known limitations

    Profiles are empirical observations of historical data, not predictive signals. Requires structured OHLCV data with clear timezone context for accurate session segmentation.

    Requires time series data with timezone context. Profiles reflect historical behavior and are not predictive signals.

    How to use

    1. 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. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 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 3 months ago

    Permissions

    No special permissions declared or detected

    Listed3 months ago

    What's inside

    Frequently Asked Questions

    The profiler segments time series data into specific trading windows (Asia, London, New York, etc.) and applies a quantitative framework to calculate range, volume intensity, and directional bias for each. This eliminates guesswork by providing empirical data to help you decide when to scale risk or sit out during low-probability sessions.

    The skill is designed to process standard OHLCV (Open, High, Low, Close, Volume) data formats, including CSV exports and JSON time series. It is compatible with AI agents configured for Python (Pandas/NumPy) or TypeScript financial analysis environments.

    You will receive the structured logic and configuration parameters required to deploy the profiling framework within your AI agent or trading platform. This includes the calculation schemas for metrics like ATR percentiles and body-to-wick ratios.

    No, the profiler is an empirical analysis tool that quantifies historical and current market states. While it identifies high-probability continuation and reversal patterns based on past data, it is intended to be used as a filter or input for your own predictive strategies.

    Accurate session segmentation requires structured data with clear timezone metadata. Users should ensure their data source aligns with UTC or a specific local exchange time to prevent session overlaps and incorrect volume attribution.

    New in Trading & Investing