Works with the AI tools you already use
KPI Definition & Metric Contract Architect
Turns ambiguous business metrics into auditable metric contracts with formulas, boundaries, ownership, and validation tests.
Secure checkout via Stripe
See it in action
You say
Apply kpi-definition-architect to our Q3 churn notes. Build the metric contract for 'Net Revenue Retention', map the formula, and highlight any evidence gaps regarding late-arriving data.
Your agent does
Metric Contract: Net Revenue Retention (NRR)
- ID: MTR-001
- Formula: (Ending ARR + Expansions - Contractions - Churn) / Starting ARR
- Evidence Gap: [CRITICAL] Source S2 mentions 'grace periods' but lacks a specific day-count for late data exclusion.
- Owner: Finance Ops
What you get
About this skill
The problem
Vague business metrics lead to data pipeline drift, conflicting reports, and lack of accountability. Generic brainstorming tools fail to address the technical nuances like cohort leakage, late-arriving data, or specific exclusion rules.
What it does
- Transforms ambiguous business requirements into auditable metric contracts with formal definitions.
- Builds an evidence ledger that maps every formula component to specific source IDs and locators.
- Identifies technical pitfalls including double counting, timezone grain mismatches, and population boundary errors.
- Generates comprehensive validation suites and conflict memos when source materials disagree.
- Distinguishes between verified facts, model inferences, and human-reserved decisions.
Why this beats prompting it yourself
Standard LLM prompts often "hallucinate" missing data or smooth over conflicting definitions to appear helpful. This skill enforces a strict traceability gate, ensuring that unknown variables are flagged as risks rather than hidden behind generic assumptions.
Use cases
- Converting messy stakeholder interview notes into technical SQL specifications.
- Auditing existing KPI definitions for logic gaps or cohort leakage.
- Creating a source-of-truth metric registry for a centralized data platform.
- Reconciling conflicting metric definitions between finance and operations departments.
Known limitations
Does not perform external data fetching or API calls. Requires provided source materials to establish the evidence ledger.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean today
- One-time purchase, yours forever