metrics-briefing

Interpret startup metrics into a CEO briefing distinguishing actionable signals from vanity numbers.

3|Updated Mar 22, 2026
One-click install
npx skills add https://github.com/CodeAlive-AI/ceo-ai-os --skill metrics-briefing
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: metrics-briefing
Source: https://github.com/CodeAlive-AI/ceo-ai-os/tree/main/skills/metrics-briefing
Command: npx skills add https://github.com/CodeAlive-AI/ceo-ai-os --skill metrics-briefing

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps founders and operators interpret startup metrics without getting fooled by vanity numbers, turning scattered product, pipeline, retention, and PMF signals into a clear CEO briefing.

Core Features & Use Cases

  • CEO-level metric framing: Organizes performance into nine decision-focused categories, including market learning, product value, usage, pipeline, retention, execution, economics, and PMF.
  • Signal over noise: Separates meaningful progress from misleading totals by emphasizing behavior, account-level cohorts, and stage transitions.
  • Mixed-data analysis: Combines manual inputs from conversations, CRM notes, and founder observations with PostHog-based product analytics.
  • Use Case: A founder can use it to review weekly traction, identify whether the right customers are recurring, and decide what to change next.

Quick Start

Ask the metrics-briefing skill to summarize your current CEO metrics into a concise weekly briefing using your conversation notes, CRM data, and PostHog funnel signals.

Frequently Asked Questions about metrics-briefing

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I turn raw PostHog analytics into a CEO-ready metrics briefing?

To turn raw PostHog analytics into a CEO-ready metrics briefing, supply your conversation notes, CRM inputs, and funnel events. The system interprets these mixed-data sources to separate actionable signals from vanity numbers, producing threshold-based decisions and next actions.

How do I separate actionable startup metrics from vanity numbers during weekly reviews?

Separating actionable startup metrics from vanity numbers requires analyzing behavior, account-level cohorts, and stage transitions. This approach categorizes performance into nine decision-focused areas, emphasizing meaningful progress over misleading totals for your weekly founder reviews.

How do I assess product-market fit using pipeline and retention data?

Assessing product-market fit using pipeline and retention data involves organizing performance into specific categories like market learning, retention, and PMF. It analyzes account-level events and CRM notes to determine if the right customers are recurring and what to change next.

Can I combine manual conversation notes with CRM data to monitor startup retention?

Yes, you can combine manual conversation notes with CRM data to monitor startup retention. This mixed-data analysis merges founder observations with PostHog account-level events to produce threshold-based decisions and identify whether the right customers are recurring.

What is the best way to interpret startup metrics for go-to-market checks?

The best way to interpret startup metrics for go-to-market checks is to frame them across nine decision-focused categories, including pipeline, execution, and economics. This distinguishes meaningful progress from misleading totals to guide founder decisions.

Do I need PostHog funnel events to generate a weekly founder traction report?

Yes, PostHog funnel and account-level events are required alongside manual conversation data and CRM inputs. These data sources are necessary to produce the threshold-based decisions and next actions that form the weekly founder traction report.