More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    mmm budget optimizer

    2

    Optimize marketing budgets using a deterministic C++ engine for attribution and marginal ROI forecasting.

    Free

    8 uses4.0 (1 review)
    mmm budget optimizer

    mmm budget optimizer

    Example session with this skill installed

    I have two years of weekly spend for Meta, Google, and TV, plus revenue data. Run the MMM engine, fit the model, and tell me where to move 10% of my budget for the best lift.

    • Read your context and instructions
    • Compiled the mmm budget optimizer

    I have processed your data and fitted the MMM model. The model achieved a Holdout R² of 0.82 and a Holdout MAPE of 4.2%, which exceeds the confidence threshold for budget reallocation.

    MMM Analysis and Optimization Report

    The model attributes 34% of total revenue to paid marketing channels. Meta shows the highest marginal ROI, suggesting that the next unit of spend will return more than in other channels. Google Search is currently near saturation.

    ChannelCurrent Weekly SpendOptimized SpendChangeMarginal ROITotal ROI
    Meta Ads£5,000£6,800+36%4.2x3.1x
    Google Search£4,500£3,650-19%1.8x2.5x
    TV£10,000£10,0000%1.2x1.4x
    Total£19,500£20,450+5%--

    Summary Findings:

    • Recommended Move: Reallocate £850 from Google Search to Meta Ads and increase total budget by 5%.
    • Expected Lift: This plan is estimated to increase weekly revenue by £3,200 (+4.5% lift).
    • Confidence Level: High. The model explains 82% of variance in the held-out data.

    Next steps

    1. Review the mmm-report.md for detailed saturation curves and adstock decay rates.
    2. Conduct a 4-week geo-lift test on Meta Ads to verify the predicted 4.2x marginal ROI.
    3. If shifting budget to Meta, monitor for creative fatigue as spend nears the saturation ceiling.

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

    About this skill

    Marketing Mix Modeling (MMM) projects often fail because they rely on expensive, black-box software or noisy Bayesian estimates that are hard to verify. This skill provides a deterministic C++ engine to attribute sales to specific marketing channels and reallocate budgets based on marginal ROI. It handles the full pipeline from data preparation to optimization with cold, mathematical precision.

    What it does

    • Data sanitization processes raw sales and spend files into cleaned weekly CSVs while checking for data gaps or singular matrices.
    • Model fitting uses a C++23 engine to fit adstock and saturation curves, measuring accuracy against a 13-week holdout set.
    • Attribution reporting calculates both total and marginal ROI, identifying which channels have no measurable effect on sales.
    • Budget optimization reallocates weekly spend across channels to maximize sales within specific safety bounds.
    • Performance forecasting predicts future sales lift based on the optimized spend plan.

    How it works

    1. Prepare by merging raw CSVs into a standardized weekly format using the internal Python scripts.
    2. Fit the model using the mmm CLI to generate a model.json and verify Holdout MAPE and R² scores.
    3. Optimize by running the engine to find the highest-ROI allocation for a given budget and bound.
    4. Report by generating a Markdown summary that lead with marginal ROI and attributes sales to specific channels.

    Frameworks & tools

    Requires a C++23 compiler (GCC 13+ or Clang 17+), CMake 3.27+, and Python 3.9+. It utilizes a dedicated C++ engine for deterministic fitting without relying on external API keys or cloud services.

    Why this beats prompting it yourself

    Generic LLM prompting cannot perform the complex non-linear regressions required for adstock and saturation modeling. This skill enforces strict validation gates, ensuring you never make budget decisions based on models with poor holdout accuracy or insufficient training data.

    Use cases

    • Budget reallocation to move money from low-marginal-ROI channels to high-performers.
    • Channel auditing to see which marketing activities are actually driving sales versus baseline demand.
    • Media planning to forecast the weekly sales lift of a 50% increase in total marketing budget.
    • Incrementality verification to prepare for geo-lift or holdout tests based on model attributions.

    Known limitations

    Requires at least 104 weeks of data for reliable results. High-confidence optimization is limited to +/- 50% of current spend to avoid unreliable extrapolation.

    Requires C++23 support. Minimum data volume of 2x(7+channels) weeks needed. Optimization is less reliable when extrapolating far beyond current spend bounds.

    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

    4.0
    1 review
    5
    0
    4
    1
    3
    0
    2
    0
    1
    0

    This skill has been used 8 times.

    Trust & safety

    Security scan

    Security scan passed 23 days ago

    • Free with an Agensi account

    Requires

    Python
    Git

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listed23 days ago

    What's inside

    Frequently Asked Questions

    This skill replaces black-box Bayesian estimates with a deterministic C++23 engine, providing verifiable attribution and marginal ROI calculations that avoid the 'hallucinations' or noise common in purely LLM-based analysis.

    You will receive the proprietary C++ optimization engine, Python data preparation scripts, the CLI tool for model fitting, and a comprehensive guide on how to structure your CSV data for the best results.

    The skill requires at least 104 weeks (2 years) of historical data to accurately model seasonality and adstock effects, and it limits spend reallocations to +/- 50% to ensure the forecasts remain statistically valid.

    This skill is designed for technical environments; you will need a C++23 compatible compiler (like GCC 13+ or Clang 17+), CMake 3.27+, and Python 3.9+ to run the engine locally.

    The engine calculates both total and marginal ROI, identifying 'diminishing returns' thresholds to show you exactly where an extra dollar of spend will generate the most sales versus where it will be wasted.