agentleFS
adhyayanrathi01adhyayanrathi01/product-manager-os/skills/analytics/create-tracking-plan/SKILL.md

create-tracking-plan

Skill2 starsChanged 2 months agoMITView on GitHub

Define or revise a provider-neutral product analytics tracking plan. Use when a PM needs events, properties, identities, success metrics, test-account handling, instrumentation requirements, or measurement acceptance criteria for a feature or flow.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify existing event and naming sources when available.

    line 12
  2. Distinctive:

    Read the approved product goal, user flow, and measurement question.

    line 18
  3. Distinctive:

    Check for ambiguous names, duplicate events, sensitive properties, and excessive collection.

    line 32
  4. Distinctive:

    Create or modify events through an available tool only when the user explicitly requests execution.

    line 34
  5. Distinctive:

    Add post-implementation validation criteria.

    line 35
  6. Very specific:

    Every field above must appear as a labeled section in the produced output.

    line 44

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Create Tracking Plan

<!-- CORE:BEGIN -->

Contract

  • Require an approved or explicitly exploratory product goal, user flow, actor or entity model, measurement questions, and privacy constraints.
  • Verify existing event and naming sources when available. Mark the plan partial when identity, exclusions, ownership, or validation environment is unresolved.
  • Output a reviewable plan and acceptance checks. Do not create events or mutate instrumentation without explicit authorization.
<!-- CORE:END -->

Process

  1. Read the approved product goal, user flow, and measurement question.
  2. Inspect the existing event dictionary and naming conventions when available.
  3. Reuse existing events when they accurately represent the behavior.
  4. Define each required event with:
    • name;
    • business question;
    • exact trigger;
    • actor or identity;
    • required properties;
    • optional properties;
    • source surface;
    • validation method.
  5. Define user-identity and anonymous-to-known behavior.
  6. Define how test, employee, bot, demo, and internal activity is marked or excluded.
  7. Check for ambiguous names, duplicate events, sensitive properties, and excessive collection.
  8. Present the tracking plan for PM and engineering review.
  9. Create or modify events through an available tool only when the user explicitly requests execution.
  10. Add post-implementation validation criteria.
<!-- CORE:BEGIN -->

Output

Provide a tracking table plus open questions, risks, ownership, and acceptance checks. Keep the plan independent of a specific analytics provider unless the user asks for provider-specific instructions.

Required fields: Tracking table|Open questions|Risks|Ownership|Acceptance checks

Every field above must appear as a labeled section in the produced output. Verify with evals/check-output.sh create-tracking-plan <artifact>.

<!-- CORE:END -->

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.