Hire an AI metric definition and weekly update writer

Everything it can hand back

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

• A definition for each metric: what it counts, excludes, its source and timing
• An assumptions log for the analysis
• A weekly update: what changed, why, what we do
• The key figures as plain pictures a reader can hold

How it does the job well

• Turn every request into owned actions: who, what and by when.
• Work from the real calendar, notes and lists. Never invent meetings, people or dates.
• Put the most important decision or deadline first, then the details.
• Prepare drafts and proposals. Sending, booking and changing records waits for approval.

Mistakes it avoids

• Losing commitments buried in long notes.
• Mixing confirmed facts with guesses about other people's plans.
• Adding process when a short checklist would do.

What a good result looks like

An example, not your task: Two reports show different numbers for the same thing.

• Step 1: Metric definitions. For each metric, what it counts, what it excludes, its source, how often it updates and who owns it.
• Step 2: Assumptions log. Every assumption behind this week's analysis, such as time windows, exclusions and estimates, and which metric each affects.
• Step 3: Weekly update. What changed, why, what we do and what we are watching, with each number tied to its definition.
• Step 4: Plain pictures. The two or three key figures turned into pictures a reader can hold, placed at the top of the update.
• 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.

A second opinion

Before it hands back, your AI reviews the draft the way Chip Heath would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Define each metric. Writes what each metric counts, excludes, where it comes from and who owns it.
• Log the assumptions. Logs every assumption behind the analysis: windows, exclusions, estimates.
• Write the weekly update. Writes the update: what changed, why, what we do and what we watch, each number tied to its definition.
• Turn figures into pictures. Turns the key figures into pictures a reader can hold, inspired by Chip and Dan Heath, and puts them at the top.

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 define-your-metrics-once-and-write-a-weekly-update-anyone-gets 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/define-your-metrics-once-and-write-a-weekly-update-anyone-gets/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

• The metrics you track and where each comes from
• This week's numbers and last week's
• Who reads the update and what they decide with it
• Your current update, if you have one (optional)

Helpful context (optional)

• Questions readers asked about past updates
• The exports the numbers come from
• A metric that changed definition in the past, and when

Tools and access

• Any good chat AI: Every step is a plan or a piece of writing.
• A spreadsheet: Holds the numbers and the definitions side by side.
• Any good chat AI: A one-message prompt works in any strong chat AI, with nothing to install.
• Any good chat AI: Finding comparisons and checking the sums is work any strong chat AI does well with this skill.
• A calculator or spreadsheet: To check each comparison against the real figure.

Functions and deliverables

• Metric definition and weekly update writer: Define each measure and log assumptions. Write a weekly update with plain explanations of the numbers that matter most.
  • A definition for each metric: what it counts, excludes, its source and timing
  • An assumptions log for the analysis
  • A weekly update: what changed, why, what we do
  • The key figures as plain pictures a reader can hold
• 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.
• Analysis assumptions logger: Share an analysis and its key choices. Get a log of assumptions, confidence, risks and checks for reviewers.
  • A logged list of data, business and statistical assumptions
  • Confidence and impact for each
  • Validation plans for the risky ones
  • A sign-off sheet for reviewers
  Source: Nimrod Fisher.
• Weekly status update writer: Write a weekly status update from your notes. Get a one-page report with an overall call, risks and the decisions you need, in under 250 words.
  • An overall status with a reason
  • Done, in progress, risks and decisions needed
  • Next period's top three
• Visual numbers explainer: Turn your key figures into pictures an audience can feel. Give it your numbers and your listeners. You get each one as a comparison or a count of people.
  • A short list of the figures worth keeping
  • Each one as a comparison, a count of people or a human picture
  • The original figure next to each version
  • A note on what to ask a non-expert to test it
• me.md builder: Answer a few questions, or let your AI use what it remembers. Get one private file that tells any AI who you are.
  • One me.md file with up to ten dated sections
  • A list of facts taken from memory, for you to check
  • A short note of what it removed for privacy
  • The two next steps, to save it and set it up
• Chip Heath: Clarify a message, change plan or difficult choice using Chip Heath’s public methods. Find the core, make it concrete and widen the options.
  • Your problem worked on the way Chip Heath would: their questions, their method, their push-back
  • The answer or the work, in Chip Heath's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• Two reports show different numbers for the same thing.
• Your weekly update is sent and not read.
• A leader asked "so what does that mean" after your last report.

Limits to check before starting

• You need one figure explained once, with no weekly update: ask your AI for a short summary instead.
• You want the numbers charted with a forecast: use the Weekly metrics report and dashboard builder workflow.
• You have no numbers yet and only a rough idea of what to track: write a short list of goals with your team first.

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 plus one skill file for each step.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Paste the metrics and where they come from. It writes the definitions and the assumptions log.
• Paste this week's and last week's numbers. It writes the update and the plain pictures.
• Read the update once as the reader. Send it, and reuse the definitions every week.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/define-your-metrics-once-and-write-a-weekly-update-anyone-gets 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.