Define the events and properties needed to measure a product journey. — Claude Skill
Um Skill Claude para Claude Code por ElasticFlow✓ — executar /tracking-plan no Claude·Atualizado em 12 de jun. de 2026·vmanual@2026-06-12
Turns a product flow, launch, or metric question into a practical tracking plan with events, properties, owners, and QA checks.
- Turns a product journey into events and properties a business team can understand before analytics implementation.
- Connects every event to the question it answers, so tracking does not become a random list.
- Flags missing owners, naming problems, privacy concerns, and events that need QA before launch.
- Produces an implementation-ready table plus a plain-language summary for PM, data, and engineering.
A PM asks for 'tracking on the new flow', engineering adds a few events, and nobody knows whether the launch can be measured.
Run /tracking-plan to define the question, events, properties, owners, and QA checks before implementation.
Para quem é
Turn measurement questions into event plans and QA checks.
Ver skills para esta funçãoTrack conversion experiments and funnel steps with cleaner event definitions.
Ver skills para esta funçãoDefine how a launch or journey will be measured before it ships.
Ver skills para esta funçãoO que faz
Define what to track before a new feature ships.
Measure where users drop off across setup, invite, activation, and first value.
Check whether existing events answer the business question or need cleanup.
Como funciona
Describe the product flow, launch, or metric you need to understand.
List the key user actions, decision points, success metric, and segments that matter.
The skill proposes events, properties, definitions, owners, and QA checks.
A human confirms naming standards, privacy rules, and whether engineering can instrument the plan.
Opções de entrada
Screens, user steps, feature states, success moment, and known drop-off points.
Exemplo
New onboarding flow: 1. User creates workspace. 2. User chooses a template. 3. User creates first project. 4. User invites teammates. Goal: understand why teams fail to invite teammates. Segments: company size, admin role, template type, plan. Need: event names, properties, owner, and QA checks before launch next Friday.
Where do teams stop before inviting teammates? Does template choice change invite rate? Do larger companies need a different prompt?
workspace_created, onboarding_template_selected, project_created, teammate_invite_started, teammate_invite_sent, teammate_invite_accepted.
workspace_id, user_role, company_size_bucket, plan, template_type, invite_count, invited_role, source_step.
Verify event fires once, IDs are consistent, properties are populated, test accounts are excluded, and invite accepted joins back to the workspace.
Confirm privacy rules for invited email addresses and final event naming standard with the analytics owner.
Métricas que melhora
Funciona com
Turn the plan into events and properties for analytics routing.
Measure product journeys, funnels, cohorts, and activation behavior.
Connect journey events to acquisition and conversion reporting.
Publish definitions, owners, and QA rules for the team.
Em qualquer lugar
Paste the notes, exports, screenshots, or summaries you already have. The skill works without a connected system.
Connect the relevant support, analytics, CRM, or data tool when you want fresher source evidence.
Quer usar Tracking Plan?
Escolha como começar.
Instale e execute este skill localmente no seu computador.
Abra um terminal no seu computador e cole este comando:
Visite o repositório do GitHub e siga as instruções de instalação no README.
Inicie o Claude Code, depois escreva o comando:
Tracking Plan
Command: /tracking-plan
When to use it
Turns a product flow, launch, or metric question into a practical tracking plan with events, properties, owners, and QA checks.
What the skill produces
- Turns a product journey into events and properties a business team can understand before analytics implementation.
- Connects every event to the question it answers, so tracking does not become a random list.
- Flags missing owners, naming problems, privacy concerns, and events that need QA before launch.
- Produces an implementation-ready table plus a plain-language summary for PM, data, and engineering.
Inputs to provide
- Product journey: Screens, user steps, feature states, success moment, and known drop-off points.
- Measurement question: What decision the team needs to make from the data.
- Existing tracking: Current event names, analytics screenshots, Segment plan, or dashboard fields.
Recommended flow
- Describe the product flow, launch, or metric you need to understand.
- List the key user actions, decision points, success metric, and segments that matter.
- The skill proposes events, properties, definitions, owners, and QA checks.
- A human confirms naming standards, privacy rules, and whether engineering can instrument the plan.
Useful result example
Measurement questions
Where do teams stop before inviting teammates? Does template choice change invite rate? Do larger companies need a different prompt?
Core events
workspace_created, onboarding_template_selected, project_created, teammate_invite_started, teammate_invite_sent, teammate_invite_accepted.
Important properties
workspace_id, user_role, company_size_bucket, plan, template_type, invite_count, invited_role, source_step.
QA checks
Verify event fires once, IDs are consistent, properties are populated, test accounts are excluded, and invite accepted joins back to the workspace.
Human review
Confirm privacy rules for invited email addresses and final event naming standard with the analytics owner.
Guardrails
- Keep user-provided numbers, dates, tool names, commands, IDs, URLs, and rules intact.
- Do not invent a source, metric, owner, decision, or risk that is not present in the supplied material.
- Clearly mark what a human must confirm before publishing, changing a tool, or making a business decision.
Documentos de referência
Tracking Plan
ElasticFlow editorial instructions for presenting /tracking-plan in the catalogue.
Purpose
Turns a product flow, launch, or metric question into a practical tracking plan with events, properties, owners, and QA checks.
Non-technical presentation
Explain the business problem, what the user provides, what the AI returns, and what a human still needs to confirm. Avoid implementation detail unless the user supplied it.
Catalogue Presentation Method
Every skill should read clearly for a business owner: current painful workflow, better workflow, concrete example, and review checklist.
The page must answer four questions: when to use it, what to provide, what the AI returns, and which human decision remains.