Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Bottleneck Hunter

    1

    Find the real workflow constraint, measure its impact, and test improvements safely.

    $9.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Bottleneck Hunter

    Bottleneck Hunter

    Example session with this skill installed

    Our hypothetical customer onboarding takes 12 calendar days end-to-end. Median stage waits: sales handoff 2 days, security review 6 days, setup 1 day, customer scheduling 3 days. Only 20 cases measured. Analyze likely constraints, what can and can't be concluded, additional data needed, safe experiments, and how to detect constraint migration. These are example figures, not real data.

    • Read your context and instructions
    • Compiled the bottleneck hunter

    Workflow Constraint Review — Customer Onboarding

    Evidence status: The figures are hypothetical and based on 20 cases. Treat the result as an initial hypothesis, not a statistically reliable diagnosis. Confirm how calendar days and stage boundaries were measured.

    Observed pattern

    Reported end-to-end median is 12 calendar days. Median waits are sales handoff 2 days, security review 6 days, setup 1 day, and customer scheduling 3 days. The listed stage waits total 12 days, but confirm whether they are sequential, overlap, or omit other touch time and queues.

    Leading constraint hypotheses

    Security review queue: largest reported stage wait; investigate capacity, batch cadence, required information, policy gates, and rework. A long wait alone does not prove that this stage limits sustainable throughput.
    2.

    Customer scheduling: 3-day wait may create demand-driven delays; check response time, time zones, availability, and outreach cadence.
    3.

    Sales handoff: missing or inconsistent information could cause downstream rework even though the wait is shorter.

    What 20 cases cannot establish

    The sample may not represent different customer segments, complexity, seasonality, or exceptions. Medians conceal variation and dependencies. Throughput, touch time, queue size, rework, and resource capacity are not supplied. Do not use Little's Law without compatible system boundaries and stable averages.

    Data to collect next

    For each case, record start/end timestamps per stage, active touch time, queue-entry time, customer segment, complexity, completeness at handoff, approval/rework loops, security reviewer capacity, weekly arrivals/completions, and exception reason. Preserve privacy and required controls.

    Safe improvement tests

    • Pilot a required-information checklist at sales handoff; measure missing fields and rework.
    • Pre-triage security submissions for completeness without waiving review; measure queue age and rejection loops.
    • Offer structured scheduling windows and reminders; compare response delay.
    • Run one change at a time, keep a baseline, and watch quality, risk, compliance, and downstream queues.

    Decision rule: Scale only if lead time or throughput improves without increased defects, risk, or work shifted to another stage. Re-measure after each test; the constraint may move.

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

    About this skill

    Bottleneck Hunter

    Diagnose where work accumulates and why by examining demand, throughput, work in progress, cycle and wait time, capacity, variability, handoffs, rework, dependencies, and policies. Separate observed evidence, calculated results, user claims, and hypotheses. Recommend practical interventions that improve total system flow without blindly optimizing local steps.

    What it delivers

    • Process-boundary and metric definitions
    • Queue, capacity, delay, handoff, and rework diagnosis
    • Evidence-backed constraint hypotheses and impact estimates when data permits
    • Low-risk tests, owners, measures, and review points
    • Checks for bottleneck migration and downstream congestion

    A busy resource or long-duration step is not automatically the true constraint. Local speedups can worsen total flow. Preserve safety, compliance, security, quality, financial, and approval controls. In regulated or safety-critical environments, escalate professional judgments. Never fabricate measures or claim certainty unsupported by data.

    Diagnosis quality depends on clear process boundaries and representative, accurately timed data. A long queue or busy person is not sufficient proof of the system constraint. Small samples, shifting demand, overlapping stages, and missing touch-time or throughput data limit conclusions. Tests require human ownership and must preserve essential controls.

    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 1 month ago

    Permissions

    No special permissions declared or detected

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    No. A long wait is a useful lead, but the true system constraint depends on demand, throughput, capacity, variability, dependencies, rework, and process boundaries. Validate the hypothesis with end-to-end evidence.

    Only when the user supplies suitable, traceable data and the calculation assumptions are explicit. Otherwise it can identify what measures are needed; it must not invent costs, throughput, or savings.

    No. Preserve required safety, compliance, security, quality, financial, and approval controls. Improve information flow, queue management, or capacity only through appropriately reviewed tests.

    New in Business & Operations