product-analytics

product-analytics is a skill for Claude Code, Codex from TrentM6/baseline-core. It costs 40 tokens per session (3,216 once invoked), scanned A, original, MIT.

A set of practices for choosing product metrics, analyzing usage data, and using the results to make decisions. It includes measures such as key performance indicators, funnels, dashboards, and experiments.

In plain words
What is it for?
Use it to define success measures, design dashboards, analyze funnels and A/B tests, segment users, and report product usage.
Why use it?
It helps teams avoid collecting numbers that do not answer a useful question. It also helps distinguish what happened in the data from why it happened.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is Follow the [Workflow Orchestration Pattern](../../frameworks/workflow-orchestration.md) for the universal workflow approach. Below are the analytics-specific de.

Good fit Use it to define success measures, design dashboards, analyze funnels and A/B tests, segment users, and report product usage.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/TrentM6/baseline-core
agentmods
npx agentmods add skills/trentm6/baseline-core/product-analytics

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for product-analytics

README.md
[![agentmods](https://agentmods.dev/badge/skills/trentm6/baseline-core/product-analytics/github.svg)](https://agentmods.dev/skills/trentm6/baseline-core/product-analytics)
Your own site
<a href="https://agentmods.dev/skills/trentm6/baseline-core/product-analytics"><img src="https://agentmods.dev/badge/skills/trentm6/baseline-core/product-analytics/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for product-analytics

Your own site · 80×15
<a href="https://agentmods.dev/skills/trentm6/baseline-core/product-analytics"><img src="https://agentmods.dev/badge/skills/trentm6/baseline-core/product-analytics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,216 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00040 $0.03216
Opus 5.5 $0.00016 $0.01286
Sonnet 5.5 $0.00008 $0.00643
Haiku 4.5 $0.00004 $0.00322

Measured yesterday against content hash 48bcee0c6262, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

product-analytics scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/product-analytics/product-analytics-skill.md · 402 lines

How it starts

The opening of the file, as written. The whole thing — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Analytics

Product analytics is the discipline of measuring what matters and turning data into decisions. Not just tracking everything — defining the right metrics, understanding what the numbers mean, and using data to improve the product. It's the quantitative complement to qualitative research.


Core Principles

  1. Metrics serve decisions. A metric that doesn't inform a decision is vanity. Every metric should answer a question or trigger an action.

  2. Measure outcomes, not outputs. "Features shipped" is output. "User problems solved" is outcome. Optimize for what actually matters.

  3. Leading indicators over lagging. Revenue is lagging — you find out too late. Leading indicators (activation, engagement) let you act sooner.

  4. Fewer metrics, better understood. A dashboard with 50 metrics means none of them matter. Ruthlessly prioritize.

  5. Correlation is not causation. Data shows what happened, not why. Pair quantitative analysis with qualitative research for the full picture.

  6. Segment everything. Averages hide insights. The average user doesn't exist. Break down by user type, cohort, behavior.

  7. Data quality is non-negotiable. Wrong data is worse than no data. Validate tracking, audit regularly, document definitions.

Industry Principles

  1. North Star metric matters. One metric that captures the core value your product delivers. Everything else ladders up.

  2. Funnels reveal friction. Where do users drop off? Conversion funnels expose the biggest opportunities.

  3. Retention is the ultimate test. Acquisition is vanity, retention is sanity. If users don't come back, nothing else matters.

  4. A/B tests require rigor. Statistical significance, sample size, runtime — don't call experiments early or make decisions on noise.

  5. Instrumentation is investment. Good analytics requires good event tracking. Invest in the foundation.


Workflow

Follow the Workflow Orchestration Pattern for the universal workflow approach. Below are the analytics-specific details for each step.

Read the full file on GitHub · 402 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 402 lines · 40 tokens per session scan A 48bcee0c6262

Subscribe to this mod's changes

product-analytics is a skill published in the GitHub repository TrentM6/baseline-core (23 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 3,216 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-17.

Related

product-analytics compared with skills from other repositories

product-analytics next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
product-analyticsTrentM6/baseline-coreSkill232d agoMITA40Claude Code, Codex
imagegenopenai/codexSkill136ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill80kyesterdayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill101ktodayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill395ktodayMITA36Claude Code
free-llm-apismnfst/awesome-free-llm-apisSkill14ktodayCC0-1.0A113Claude Code, Codex
next-cache-components-adoptionvercel/next.jsSkill144ktodayMITA95Claude Code