agentsclimarketplace

Product tracking model

Skill yigityildiz0/universal-ai-skill-library/skills/common/product-tracking-model

Model a product before telemetry work by defining users, value moments, entities, lifecycle states, and decision questions. Use when asked to map a product for analytics, define what a product does, prepare a tracking model, or establish a telemetry foundation.From its SKILL.md

Install
npx -y skills add yigityildiz0/universal-ai-skill-library --skill product-tracking-model

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

  • 26 days oldThe repository was created 26 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.8 KB, 297 tokens by cl100k_base, as published. Nobody here has run it

Product Tracking: Model

Create a compact product model that makes later telemetry decisions traceable. Do not select an analytics vendor, add SDKs, or send data.

Workflow

  1. Read only the product materials and repository areas the user put in scope.
  2. Separate confirmed facts from assumptions. Ask only for facts that materially change the model.
  3. Define:
    • primary user roles and accountable organizations;
    • the smallest meaningful value moment;
    • core entities and their stable relationships;
    • lifecycle states, permissions, and meaningful transitions;
    • product questions that evidence should answer.
  4. Identify sensitive fields. Prefer pseudonymous identifiers and data minimization; do not include secrets, free-form user content, regulated data, or unnecessary identifiers in telemetry.
  5. Produce a reviewable model before designing events.

Deliverable

Use this structure in conversation or, when the user requests project artifacts, propose .telemetry/product-model.md:

Product outcome
Users and organizations
Core value moment
Entities and relationships
Lifecycle states and transitions
Decision questions
Known unknowns and privacy boundaries

Quality bar

  • Every proposed event later must map to a decision question or value moment.
  • Do not turn every click into a product event.
  • Mark inference clearly; never pretend a codebase proves product intent.
  • Hand off to product-tracking-audit for current reality or product-tracking-plan for the target design.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,512. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.