# Metric Narrative

> Write reviewed KPI and metric narratives from supplied data, definitions, and assumptions. Use when Codex is asked to explain a metric movement, summarize dashboard results, write an executive metric update, describe activation/retention/revenue trends, or turn analysis into a decision-ready narrative.

- Skill: `gabrielmoreira/metric-narrative` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add gabrielmoreira/metric-narrative`
- Raw SKILL.md: https://api.skillmd.com/api/skills/gabrielmoreira/metric-narrative/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- License: MIT
- Author: gabrielmoreira (https://skillmd.com/u/gabrielmoreira)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/gabrielmoreira/metric-narrative

---


# Metric Narrative

## Core Workflow

1. Identify the metric, definition, time period, comparison baseline, segment,
   and intended audience.
2. Verify supplied numbers against metric definitions and source notes before
   writing conclusions.
3. Separate observed facts, plausible drivers, assumptions, data quality issues,
   and recommended follow-up checks.
4. Explain direction, magnitude, affected segments, confidence, and business
   implication.
5. Include what would change the interpretation: missing data, delayed events,
   tracking changes, seasonality, or cohort mix.
6. End with decision options or next checks when the evidence is incomplete.

## Safety Rules

- Do not invent figures, sources, baselines, definitions, or causal drivers.
- Do not publish external or executive-facing numbers without reviewer
  confirmation.
- Do not treat correlation as causation without experimental or operational
  evidence.
- Escalate when metrics affect finance, investor reporting, compliance,
  compensation, customer commitments, or public claims.

## Deliverable Shape

For metric narratives, provide:

- Metric and period
- Source and definition used
- Observed movement
- Segment or cohort notes
- Likely drivers and confidence
- Data quality caveats
- Business implication
- Follow-up checks or decision options

## References

- Read `references/metric-narrative-checklist.md` when writing or reviewing KPI,
  dashboard, activation, retention, revenue, or executive metric narratives.