Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    BI Dashboard Architect

    1

    Turn business questions and trusted metrics into clear, actionable, and governed dashboard designs.

    $9.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    BI Dashboard Architect

    BI Dashboard Architect

    Example session with this skill installed

    Design a dashboard for a subscription software leadership team. The main decision is whether to intervene when new customer activation is falling. We have signups, activation events, trial-to-paid conversion, cancellations, support tickets, and a monthly target, but definitions and data freshness are not documented. Provide intake questions, a metric dictionary template, page hierarchy, recommended visuals, filters/drill paths, accessibility/performance requirements, and a validation plan. Do not invent values.

    • Read your context and instructions
    • Compiled the bi dashboard architect

    Activation Health Dashboard Blueprint

    Decision and audience

    Decision: when and where should leadership investigate a decline in new-customer activation?
    Primary users: leadership for weekly monitoring; operations and product analysts for diagnosis.
    Constraint: metric definitions, freshness, targets, and data lineage are not yet verified. Treat all figures as unavailable until confirmed.

    Intake before build

    1. What event counts as activation, and is it tied to a product milestone?
    2. What is the denominator: signups, eligible trials, or another cohort?
    3. Which timezone, cohort start, and maturity window apply?
    4. How is the monthly target allocated across weeks and segments?
    5. What lag and completeness are expected for each source?
    6. Who owns each metric and approves changes?

    Metric dictionary (template)

    MetricDefinition to confirmGrain / cohortOwnerSourceFreshness
    New signupsCount of eligible new accountsSignup date × segmentAssign ownerSignup sourceVerify
    Activation rateActivated accounts ÷ eligible signup cohortCohort week × segmentProduct analyticsEvent sourceVerify
    Trial-to-paidPaid conversions ÷ eligible trial cohortTrial-start cohortRevenue opsBilling sourceVerify
    Cancellation rateCancellations ÷ defined customer baseMonth × planFinance / CSBilling sourceVerify
    Support ticketsCount using agreed ticket inclusion rulesWeek × issue typeSupport opsTicket sourceVerify

    Do not compare rates until numerator, denominator, exclusions, and time windows are aligned.

    Page hierarchy

    1. Leadership overview: activation rate versus approved target and prior comparable cohort; cohort size; freshness timestamp; status note if data is incomplete.
    2. Diagnose: activation trend by signup cohort, plan, acquisition channel, and product version only where definitions are reliable. Pair rate with eligible counts to avoid small-sample overreaction.
    3. Operational detail: supporting trial-to-paid, cancellation, and ticket trends, with links or drill paths to owned analyses. Keep ticket counts descriptive; they do not explain causality by themselves.

    Visual specification

    • Use a line chart for weekly cohort activation trend, with clearly labeled time window and a target reference only after target logic is confirmed.
    • Use a ranked horizontal bar chart for segment comparison with denominator counts and consistent scale.
    • Use a compact table for exact cohort values and freshness; allow export only under the team’s data policy.
    • Avoid pie charts, decorative gauges, dual axes, and unexplained red/green status. Use labels or symbols as well as color.

    Filters and drill paths

    Provide date/cohort, plan, acquisition channel, and product version only if dimensions are complete and stable. Show active filter chips and preserve metric semantics across drill-down. Default to the latest fully matured cohort rather than a partial current week.

    Accessibility and performance

    Provide keyboard-operable filters, visible focus, readable labels, sufficient contrast, descriptive chart text, and a table alternative. Keep the initial view focused; defer high-cardinality detail. Specify expected refresh latency, query budget, and fallback messaging for stale or incomplete data.

    Validation plan

    1. Data owner signs off metric definitions and lineage.
    2. Reconcile a sample of dashboard values to source queries.
    3. Test freshness and partial-cohort behavior.
    4. Ask leaders to complete real tasks: spot an exception, identify its segment, and state the next action.
    5. Revise any visual that users interpret inconsistently; monitor load time and adoption.

    Next step: appoint metric owners and document activation and target logic before implementation. No dashboard values or causal explanations have been assumed.

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

    About this skill

    BI Dashboard Architect

    Design business intelligence dashboards around the decisions people need to make. Translate a specific audience, question, action, metric definition, and data context into a clear information hierarchy, suitable visual encodings, filters, drill paths, and validation plan.

    What it delivers

    • Audience, decision, cadence, and KPI discovery brief
    • Metric dictionary with owner, grain, unit, source, time basis, and filters
    • Dashboard layout and chart-selection specification
    • Filter, drill-down, accessibility, mobile, and performance guidance
    • Data freshness, quality, lineage, and adoption checklist

    Tool-neutral process

    Clarify intended users and decisions first. Confirm authoritative metric definitions and data availability before designing visuals. Separate executive monitoring from operational action and detailed analysis when needs conflict. Select encodings for the analytical task, make comparisons and exceptions legible, and test comprehension using real user tasks.

    Guardrails

    Do not invent KPIs, values, integrations, data quality, benchmarks, or business outcomes. Show targets and comparisons only when supplied or justified. Use zero baselines for bars when appropriate, avoid misleading axes and aggregation, do not rely on color alone, and treat freshness, accessibility, and performance as part of trust. Mobile layouts require deliberate adaptation.

    Dashboard quality depends on accurate, timely source data and agreed metric definitions. A design brief cannot verify a live BI implementation, guarantee performance or adoption, or prove that a metric explains a business outcome. Platform capabilities and accessibility behavior must be tested in the chosen tool with real users and data.

    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. It can produce tool-neutral dashboard and metric specifications. If you name Power BI, Tableau, Looker, or another platform, the design can be adapted to that environment; implementation details should be verified there.

    Only if a suitable, authorized data source or connector is available. Otherwise it provides definitions and validation steps; ask metric owners to confirm actual values, lineage, and freshness.

    Test it with real users and realistic tasks, such as spotting an exception and finding its segment. Check whether people interpret measures consistently, can operate filters accessibly, and understand freshness and context.

    New in Business & Operations