Hire an AI weekly metrics report and dashboard builder

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A workbook with each metric defined once, plus a saved definition to rerun
• A read on trend, seasons and odd spikes, with a forecast table and ranges
• A test of the forecast on weeks it did not see
• One page with headline cards, trend and forecast charts, and filters

How it does the job well

• Agree the question and the decision it supports before analysing.
• Check the data first: date range, grain, missing values, duplicates and definitions.
• Compare like with like: same period length, definitions and segments.
• Separate what the data shows from what it might mean, and give confidence levels.

Mistakes it avoids

• Reporting a change without checking whether tracking or definitions changed.
• Treating correlation as cause.
• Averages that hide important segments or outliers.

What a good result looks like

An example, not your task: You report the same numbers every Monday and rebuild them each time.

• Step 1: Report. Each metric with its formula, grouping, comparison and period, plus a workbook and a saved definition to rerun.
• Step 2: Trend and forecast. Trend, seasons, spikes and dips with likely causes, and a forecast table with ranges and test error on held-back weeks.
• Step 3: Dashboard. One shareable page with headline cards, a trend chart, a forecast chart and filters.
• Hand-back summary. Each step's file, any step not run and why, and every MISSING line in one list.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Fix the report. Turns your description into metrics, groups, comparisons and a period, asks only about what is unclear, builds the workbook and saves the definition.
• Find the trend and forecast. Fills date gaps, splits each metric into trend, season and leftover, flags spikes and dips against your events, and forecasts with a test on held-back weeks.
• Build the dashboard. Puts the headline numbers in cards, charts the trend and the forecast range, adds filters and saves one page you can share.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id build-a-weekly-kpi-report-with-a-forecast-and-dashboard only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/build-a-weekly-kpi-report-with-a-forecast-and-dashboard/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• A plain description of the report, with the numbers, the groups, the comparison and the period
• A spreadsheet or export with weekly history, at least twelve weeks (optional but best)
• How far ahead to forecast
• Known events such as promos or outages, so spikes can be explained (optional)

Functions and deliverables

• Weekly metrics report and dashboard builder: Define the numbers to track each week. Build a report and forecast, then show both on one dashboard.
  • A workbook with each metric defined once, plus a saved definition to rerun
  • A read on trend, seasons and odd spikes, with a forecast table and ranges
  • A test of the forecast on weeks it did not see
  • One page with headline cards, trend and forecast charts, and filters
• Recurring KPI report maker: Describe a report and connect its data. Get checked numbers, a workbook and a saved report definition to rerun.
  • Chat summary of the numbers
  • Excel workbook
  • Saved report definition
  • Rerun on demand or schedule
  Source: Anthropic.
• Trend and forecast analyst: Share numbers over time. Get trend, seasons and odd spikes found, plus a forecast table and plain insights.
  • Trend and seasonal patterns
  • A list of odd points
  • A forecast table with ranges
  • A plain-language summary
  Source: Nimrod Fisher.
• Offline dashboard builder: Build a self-contained HTML dashboard from supplied data, with charts and filters that work offline.
  • Self contained HTML dashboard
  • KPI cards and charts
  • Working filters and tables
  • Steps to swap in real data
  Source: Anthropic.
• Metric definition writer: Share a metric, calculation and business use. Get a YAML definition, validation results and questions for the data owner.
  • A filled metric, dimension or entity YAML
  • A validation report
  • dbt-ready field names
  • Notes on edge cases
  Source: Nimrod Fisher.

Tasks you can use it for

• You report the same numbers every Monday and rebuild them each time.
• You want a forecast with a range, not a single guess, for the next quarter.
• Your team keeps asking for a link to "the numbers".

Limits to check before starting

• You have under about twelve weeks of data: build only the report step and let the history grow, then add the forecast later.
• You need a one-off chart of last month: make it in your spreadsheet, since this workflow is built for numbers you rerun every week.
• You want ad ideas or copy, not numbers: this workflow does not write creative, so ask your AI to draft it directly.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Describe the report in your own words and attach the data. Answer its one or two questions, like which period each run covers.
• Tell it how far ahead to forecast and which events to know about.
• Open the finished page and check three numbers against your source.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/build-a-weekly-kpi-report-with-a-forecast-and-dashboard for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.