From ai-analyst
Browses, searches, and displays metric definitions including formulas, source tables, dimensions, guardrails, and validations from active dataset's metric dictionary via /metrics commands.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ai-analyst:view-metricsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Browse, search, and display metric definitions from the active dataset's
Browse, search, and display metric definitions from the active dataset's metric dictionary. Provides quick access to how metrics are defined, computed, and validated.
/metrics or "show me the metrics" or "what metrics do we track?"/metrics — list all metrics for the active dataset
/metrics {id} — show full spec for a specific metric
/metrics category={cat} — filter by category (e.g., monetization)
/metrics search={term} — search metric names and descriptions
<workspace>/.knowledge/active.yaml to identify the active dataset.<workspace>/.knowledge/datasets/{active}/metrics/index.yaml for the metric list.List all (/metrics):
Example output:
Metrics (10 total)
MONETIZATION:
revenue Revenue ↑ Target ✓ Valid
mrr Monthly Recurring ↑ Target ✓ Valid
aov Avg Order Value ↑ Target ⚠ Stale
ENGAGEMENT:
dau Daily Active Users ↑ Target ✓ Valid
retention_d7 7-Day Retention ↑ Target ? Undefined
...
Use `/metrics {id}` to see full definition.
Show specific (/metrics {id}):
<workspace>/.knowledge/datasets/{active}/metrics/{id}.yamlExample output:
Metric: revenue
Category: Monetization
Owner: Finance Team
Direction: ↑ Higher is better
Unit: USD
Granularity: Daily, Monthly
Formula:
SELECT DATE(order_date), SUM(amount)
FROM orders
WHERE status = 'completed'
GROUP BY 1
Source tables: orders
Dimensions: product_category, region, customer_segment
Guardrails:
- Daily min: $100K (warn if below)
- Daily max: $5M (alert if above)
- Typical range: $300K - $2M
Validation:
Last validated: 2026-03-10
Status: ✓ Valid
Notes: Matches finance reporting
Related metrics: mrr, aov, gross_margin
Filter by category (/metrics category=monetization):
Search (/metrics search=revenue):
Example:
/metrics search=revenue
Matches (3):
1. revenue Monetization ✓ Valid
2. gross_revenue Monetization ✓ Valid
3. net_revenue Monetization ✓ Valid
After displaying metrics, suggest relevant actions:
Each metric in <workspace>/.knowledge/datasets/{active}/metrics/{id}.yaml should contain:
id: revenue
name: Revenue
category: Monetization
owner: Finance Team
direction: up # "up" or "down"
unit: USD
granularity:
- daily
- monthly
formula: |
SELECT DATE(order_date), SUM(amount)
FROM orders
WHERE status = 'completed'
GROUP BY 1
source_tables:
- orders
dimensions:
- product_category
- region
- customer_segment
guardrails:
min_daily: 100000
max_daily: 5000000
typical_range: [300000, 2000000]
validation:
last_validated: "2026-03-10T00:00:00Z"
status: valid # "valid", "stale", "undefined"
notes: "Matches finance reporting"
related_metrics:
- mrr
- aov
- gross_margin
npx claudepluginhub ai-analyst-lab/ai-analyst-plugin --plugin ai-analystDefines metrics using a standardized template covering plain English definition, formula, components, segmentation, data sources, thresholds, limitations, and drivers. Ensures clarity in analysis.
Produces complete metrics specs for product areas: names, formulas, data sources, segmentation, SQL/event tracking, thresholds. Use for KPI definition or feature instrumentation.
Produce a complete metrics definition doc — metric name, formula, data source, segmentation, SQL or event tracking spec, and what good/bad looks like. Given a product area, outputs the full metrics spec. Use when asked to "define KPIs", "metrics framework", "what should we measure", "north star metric", or "instrument this feature".