Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    renewable generation variance

    1

    Compare actual renewable generation to expected output. Compute capacity factors, performance ratios, and identify underperforming periods for solar, wind, or hydro facilities.

    $1.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    renewable generation variance

    renewable generation variance

    Example session with this skill installed

    Analyze the solar_pv generation records for the last 24 hours. Compare actual_kwh against expected_kwh to find variance and the overall performance ratio for the 500kw array.

    • Read your context and instructions
    • Compiled the renewable generation variance

    I have completed the variance analysis for the solar_pv facility. The overall performance ratio is 0.82, with a total variance of -420 kWh for the period.

    Renewable Generation Variance Report

    PeriodActual (kWh)Expected (kWh)Variance (%)Capacity Factor
    08:00 - 09:00110115-4.3%0.22
    09:00 - 10:00250265-5.7%0.50
    10:00 - 11:00380410-7.3%0.76
    11:00 - 12:00120450-73.3%0.24
    12:00 - 13:00440460-4.3%0.88
    13:00 - 14:00410430-4.7%0.82

    Findings

    Significant Deviation: A 73.3% drop was detected at 11:00. This exceeds the expected variance marker and likely indicates localized cloud cover, inverter clipping, or a transient fault.

    Performance Ratio: The calculated PR of 0.82 is within the acceptable range for this technology type, despite the mid-day dip.

    • Capacity Factor: The average capacity factor for this 24-hour window is 0.57.

    Next steps

    1. Inspect the inverter logs for the 11:00 - 12:00 window to rule out hardware tripping.
    2. Cross-reference the 11:00 variance with local meteorological sky-cam data.
    3. Schedule a thermographic drone sweep if this midday variance repeats over the next three days.

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

    About this skill

    Asset performance management relies on accurate data, but manual variance analysis often masks subtle equipment degradation or clipping issues. This skill automates the comparison of actual renewable generation against resource-based expectations to surface hidden underperformance.

    What it does

    • Metric Computation calculates capacity factors and performance ratios across solar, wind, and hydro assets.
    • Variance Identification isolates periods where actual kWh deviates significantly from expected kWh models.
    • Asset Benchmarking compares performance across different technology types including PV and onshore/offshore wind.
    • Root Cause Support flags specific intervals for O&M review based on significant production gaps.

    How it works

    1. Prepare Data by formatting generation records with actual output, expected output, and installed capacity.
    2. Execute Analysis using the provided Python runtime script to process the JSON request.
    3. Review Metrics to evaluate the total variance and overall facility health.
    4. Inspect Findings via the generated period-by-period table to pinpoint exact timestamps of underperformance.

    Frameworks & tools

    The core engine runs via python3 and handles JSON-structured generation data. It is designed for integration into energy management systems or data science notebooks.

    Why this beats prompting it yourself

    Generic prompts often struggle with the domain-specific math required for capacity factors or fail to maintain consistency with resource model uncertainty. This skill uses validated methods to ensure performance ratios are calculated accurately across varying time scales.

    Use cases

    • Auditing monthly solar farm production against irradiance-based forecasts.
    • Identifying failing turbines in a wind fleet by detecting persistent negative variance.
    • Calculating the performance ratio of a hydro facility for quarterly investor reporting.

    Known limitations

    This tool is for decision support only. It does not perform real-time plant control, curtailment, or carbon intensity tracking.

    Requires pre-calculated expected generation data based on resource models. Operational actions derived from results require manual operator approval. Not for carbon intensity or demand forecasting.

    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 today

    Permissions

    Terminal / Shell
    Read Files
    Environment Variables
    Listedtoday

    What's inside

    Frequently Asked Questions

    The skill automates the comparison between your actual energy output and resource-based expectations, helping you identify subtle equipment degradation or clipping that manual analysis often misses.

    You will receive the core Python analysis script, documentation for the JSON data schema, and a guide for integrating the tool into your existing energy management systems or data science notebooks.

    Yes, the skill is designed for cross-technology benchmarking, allowing you to compare performance ratios and capacity factors across solar (PV), wind (onshore/offshore), and hydro assets within a single framework.

    The skill requires a Python 3 environment and accepts generation records in a structured JSON format including actual output, expected output, and installed capacity.

    While it provides the math and identifies periods of underperformance for O&M review, it is a decision-support tool and does not perform real-time plant control or curtailment actions.