Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    manufacturing bottleneck and throughput analyzer

    1

    Industrial production lines often hide their constraints, leading to missed targets and unoptimized staffing.

    $1.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    manufacturing bottleneck and throughput analyzer

    manufacturing bottleneck and throughput analyzer

    Example session with this skill installed

    Analyze this line: Stamping (3.5 min/unit, batch 50), Welding (5.2 min/unit, batch 1), Assembly (4.0 min/unit, batch 10). Available time is 480 mins. Demand is 100 units.

    • Read your context and instructions
    • Compiled the manufacturing bottleneck

    The throughput analysis is complete. The bottleneck has been identified at the Welding station, which is currently the primary constraint preventing the line from meeting the target demand.

    Manufacturing Throughput Audit

    MetricValue
    Bottleneck Station(s)Welding
    Bottleneck Cycle Time5.20 min/unit
    Theoretical Throughput92.31 units/period
    Total Flow Time219.00 min/batch
    Capacity Shortfall7.69 units
    Demand Utilization0.9231

    Station Breakdown

    StationProcessing TimeBatch SizeUtilizationBottleneck?
    Stamping3.50 min500.3646No
    Welding5.20 min10.0108*Yes
    Assembly4.00 min100.0833No

    Note: While Welding has the highest cycle time per unit (constraining the line flow), the utilization calculation factors in batch processing time against available period time. Analysis confirms Welding defines the maximum throughput.

    Next steps

    1. Evaluate cycle time reduction at the Welding station to increase total line throughput.
    2. Review the 7.69 unit shortfall to determine if overtime is required to meet the 100-unit demand.
    3. Validate if the Stamping batch size can be optimized to reduce total flow time.

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

    About this skill

    Industrial production lines often hide their constraints, leading to missed targets and unoptimized staffing. This skill identifies the exact bottleneck in multi-stage manufacturing systems to reveal why your throughput isn't meeting demand.

    What it does

    • Bottleneck identification finds the station or stations with the highest utilization rates.
    • Utilization analysis calculates per-station load as a fraction of available production time.
    • Throughput computation estimates the theoretical units per period based on the constraint cycle time.
    • Capacity shortfall analysis compares line capacity against planned demand to flag potential misses.
    • Flow time estimation sums batch processing times to determine the total time a unit spends in the system.

    How it works

    1. Provide a list of production stations including their processing times and batch sizes.
    2. Define the available production time per period and optional planned demand.
    3. The skill runs a deterministic calculation engine to process cycle times and utilization.
    4. Review the generated report containing the bottleneck station, throughput metrics, and shortfall data.

    Frameworks & tools

    This skill uses a Python-based calculation engine with Decimal arithmetic for exact precision. It enforces data integrity via JSON Schema validation for both inputs and outputs.

    Why this beats prompting it yourself

    Generic prompts often struggle with batch-size math and exact utilization rounding across multiple stages. This skill uses a dedicated execution script to ensure deterministic results, preventing the hallucinated calculations common in standard LLM math.

    Use cases

    • Identify which station in a multi-stage assembly line is limiting total output.
    • Determine if a production shift has enough available time to meet a specific order volume.
    • Calculate the total flow time for a batch to move from the first station to the last.
    • Perform a "what-if" analysis on throughput by adjusting specific station cycle times.

    Known limitations

    Designed for deterministic manufacturing lines only. It does not handle stochastic wait times, queueing theory distributions (M/M/1), or complex capital investment optimization.

    Works only for deterministic lines. No support for stochastic arrival patterns, queueing theory (M/M/1), or financial capital investment modeling.

    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 analyzes multi-stage assembly lines by calculating the utilization of each station to pinpoint the 'weakest link' or bottleneck, while simultaneously measuring throughput against your production targets.

    Unlike standard LLMs that often make errors in multi-step arithmetic, this skill uses a dedicated Python-based calculation engine to ensure 100% deterministic results for batch sizes and cycle times.

    This skill is designed for any AI agent or platform that supports JSON-based tools and Python execution environments, making it compatible with most enterprise-grade agentic frameworks.

    No, this version is designed for deterministic lines with fixed cycle times; it does not currently support stochastic variables like random machine breakdowns or complex queueing theory.

    You will receive the validated JSON input/output schemas, the core calculation logic, and integration documentation to deploy the skill within your chosen agent environment.

    Setup is straightforward: you simply need to define your production stages, cycle times, and batch sizes in a structured format, which the agent then processes through the analyzer.