Works with the AI Agents you already use
executive metric definition architect
- **Analyze lineage** to detect circular dependencies and map the depth of derived metrics.
$1.99
executive metric definition architect
Example session with this skill installed
Validate these three metrics for our sales dashboard: sales_rev (sum of gross), net_margin (formula: sales_rev - costs), and customer_count. Check against our 'Revenue Growth' goal.
- Read your context and instructions
- Compiled the executive metric definition
I have processed the three metric definitions against the Revenue Growth goal. The validation script has scored the metrics based on formula completeness and metadata alignment.
KPI Dictionary Analysis — Sales Department, 2024-05-20
1. Summary and sources
- Sources: E1 (User provided sales definitions)
- Metrics Analysed: 3
- Average Score: 72.5
- Tier Distribution: 1 Gold, 1 Silver, 1 Bronze
2. KPI Dictionary (scored)
| ID | Name | Type | Score | Tier | Issues |
|---|---|---|---|---|---|
| sales_rev | Sales Revenue | Base | 85.0 | Gold | 0 |
| net_margin | Net Margin | Derived | 78.0 | Silver | 1 |
| customer_count | Customer Count | Base | 54.5 | Bronze | 3 |
3. Business goal coverage
| Goal | Mapped Metrics | Status |
|---|---|---|
| Revenue Growth | sales_rev, net_margin | Covered |
| Retention Target | Information gap — organizational validation required |
4. Lineage analysis
- Max Depth: 1 (net_margin -> sales_rev)
- Circular Dependencies: None detected.
- Base Metrics: 2
- Derived Metrics: 1
5. Naming and source validation
- Convention: snake_case
- Compliance Rate: 100%
- Source Mismatches:
customer_countlacks asource_systemidentifier.
6. Recommendations
Define Source System: Add source_system to customer_count to reach Silver tier.
Management decision required.
2.
Detail Formula: Explicitly define 'costs' in net_margin to ensure lineage traceability.
Management decision required.
7. Warnings and items for human review
- Metric
customer_countis missing aggregation metadata. Verify if distinct count is required.
Next steps
- Provide the missing
source_systemfor the customer metric. - Define the 'costs' metric to complete the lineage for Net Margin.
- Map a metric to the 'Retention Target' goal to close the information gap.
Connects securely to your tools. The creator never sees your data.
About this skill
Building a semantic layer or an executive dashboard often starts with a mess of poorly defined KPIs and inconsistent naming. This skill validates your metric definitions against governance standards to ensure every formula, dimension, and lineage path is architecturally sound.
What it does
- Validate formulas by checking for completeness and reference consistency across the metric catalogue.
- Score quality using a deterministic algorithm that assigns metrics into quality tiers based on metadata density.
- Analyze lineage to detect circular dependencies and map the depth of derived metrics.
- Map goal coverage to identify business objectives that lack supporting metrics or highlight orphaned KPIs.
- Enforce conventions by auditing naming styles (snake_case, camelCase, etc.) and source system identifiers.
How it works
- Input gathering: Provide your metric definitions, business goals, and dimension registries.
- JSON generation: The skill structures your data into a schema-compliant request for processing.
- Automated audit: A specialized validation script processes the definitions to compute scores and identify architectural flaws.
- Report delivery: You receive a structured KPI dictionary with scored metrics, coverage gaps, and prioritized fixes.
Frameworks & tools
The skill utilizes a self-contained Python validation engine and adheres to specific JSON schemas for metric metadata and output envelopes.
Why this beats prompting it yourself
Generic prompts often hallucinate metric scores or miss subtle circular dependencies in complex lineage graphs. This skill uses a deterministic script to ensure scoring is mathematically precise and consistent across large catalogues.
Use cases
- Auditing a metric catalogue before implementing it in a semantic layer like Looker or dbt.
- Establishing naming and governance standards during a BI platform migration.
- Identifying gaps in executive reporting by mapping KPIs to strategic business goals.
- Detecting technical debt in complex derived metrics before they break production dashboards.
Known limitations
Does not calculate actual data values or generate SQL code. Requires a provided list of metrics as it cannot invent definitions from scratch.
Does not calculate metric values or generate SQL. Cannot invent definitions; requires user-provided metric lists. Analysis is limited to metadata and definitions provided in the input.
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 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 day ago