Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    linear programming model builder

    1

    Business logic alone cannot solve resource allocation.

    $2.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    linear programming model builder

    linear programming model builder

    Example session with this skill installed

    Build a model to maximize profit from two products, A and B, with profits of $50 and $40. Product A takes 2 hours of labor, B takes 1 hour. Total labor is 100 hours. Solve and show shadow prices.

    • Read your context and instructions
    • Compiled the linear programming model

    The linear program was successfully solved using the exact rational simplex method. The solution is certified optimal.

    Linear Programming Model Builder — Production Dept, 2024-05-20

    Model

    • Objective: Maximize Total Profit
    • Variables: Product_A, Product_B
    • Constraints: 1 hard (Labor_Limit)

    Solution

    • Objective Value: 2500.00
    • Allocations:
      • Product_A: 50.0
      • Product_B: 0.0
    • Optimality: Certified Optimal

    Constraint diagnostics

    ConstraintActivitySlack/SurplusBindingShadow PriceAllowable DecreaseAllowable Increase
    Labor_Limit100.00.0Yes25.0100.0null

    Sensitivity

    VariableCoefficientAllowable DecreaseAllowable Increase
    Product_A50.010.0null
    Product_B40.0null10.0

    Feasibility and solver status

    The model is feasible and reached an optimal basis. The Labor_Limit constraint is fully utilized.

    Proposed actions

    • Draft Action: Allocate resources to produce 50 units of Product_A.
    • Draft Action: Evaluate increasing labor hours as each additional hour contributes $25.00 to profit.
    • Note: These actions require human approval.

    Appendix. Calculation trace

    • ID: OBJ_VAL, Formula: (50 * 50) + (40 * 0), Result: 2500.0, Unit: Currency
    • ID: LAB_ACT, Formula: (2 * 50) + (1 * 0), Result: 100.0, Unit: Hours

    Next steps

    1. Review the shadow price for Labor_Limit to justify overtime costs.
    2. Confirm if the demand for Product_A supports a 50-unit run.
    3. Approve the draft allocation in the production management system.

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

    About this skill

    Business logic alone cannot solve resource allocation. Guessing at product mixes or capacity limits leads to waste or missed targets. This skill builds and solves formal linear programming models to find the certified exact optimum for your constraints.

    What it does

    • Model building converts objectives and named constraints into a formal linear program structure.
    • Exact solving uses a two-phase rational simplex to find the optimal allocation for variables.
    • Sensitivity analysis reports shadow prices, allowable RHS ranges, and objective coefficient bounds.
    • Feasibility diagnostics identifies binding constraints and checks if any valid solution exists.
    • Heuristic processing handles larger models (over 12 variables) via a density-greedy approach when consented.

    How it works

    1. Data ingestion maps user objectives, variables, and constraints into a structured JSON request.
    2. Model validation checks for missing coefficients, contradictory fields, or size limit breaches.
    3. Execution runs the solver script to generate an optimality certificate or a heuristic bound.
    4. Analysis interprets the status to identify slack, surplus, and the marginal value of resources.

    Frameworks & tools

    The skill relies on a Python execution environment using scripts/run.py. It requires structured JSON inputs following specific schemas for objectives and constraints.

    Why this beats prompting it yourself

    Generic LLM prompts often hallucinate optimal values or fail at the mathematical rigour of the simplex method. This skill uses a certified solver that provides a traceable calculation appendix and never claims optimality for heuristic results.

    Use cases

    • Maximize product mix contribution given limited machine hours and labor.
    • Determine the minimum cost for material blending while meeting quality specs.
    • Evaluate the shadow price of additional warehouse capacity for budget planning.
    • Perform make-versus-buy analysis across multiple components and suppliers.

    Known limitations

    Exact solving is limited to 12 variables and 16 constraints. It does not support integer, multi-objective, or stochastic programming.

    Exact solving capped at 12 variables and 16 constraints. No support for integer, multi-objective, or non-linear programs. Decision support only, requiring human approval for actions.

    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 2 days ago

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Environment Variables
    Listed2 days ago

    What's inside

    Frequently Asked Questions

    This skill is designed for complex resource allocation problems where guessing leads to waste, such as optimizing product mixes, minimizing blending costs, or determining the most efficient use of labor and machine hours.

    Unlike standard AI prompts that may hallucinate calculations, this skill uses a formal rational simplex solver to provide mathematically certified optimal results and detailed sensitivity analysis.

    The skill includes a pre-configured Python execution environment and a structured JSON schema, allowing it to integrate with any AI agent capable of running scripts and handling data objects.

    The exact rational solver is optimized for models with up to 12 variables and 16 constraints; however, larger models can be processed using a density-greedy heuristic approach if you provide consent.

    Beyond the optimal solution, you receive shadow prices, allowable ranges for RHS values, and objective coefficient bounds to help you understand the marginal value of your resources.