product-analytics.dataflow — Claude Code prompt for a data-flow diagram
This prompt guides Archify through a product analytics data-flow diagram, from web and mobile events to dashboards and a model, with a distinct path for consent-gated identity data.
Apache-2.0 ★ 98,599 updated 2026-10-25
.claude/commands/product-analytics.dataflow.mdWhat product-analytics.dataflow does
The prompt asks Archify to produce a typed JSON diagram specification for product analytics. Web and mobile clients send events to an edge ingestion API. Consent is checked before identity data moves into a protected PII vault; accepted events enter a stream, become normalized warehouse facts, and feed dashboards. Aggregated warehouse data also goes to a feature store and a model.
The diagram targets the showcase quality profile, while internal IDs and layout are left to the agent. It must visually separate the privacy boundary and restricted identity path from ordinary analytics. When shell access is available, the prompt calls for using the bundled Archify CLI to validate and repair the candidate. Save the final candidate only as benchmark-candidate.json at the repository root. CLI validation does not mean the external validation passed.
What it helps with
- trace client events through the ingestion API
- separate identity data from the ordinary analytics path
- connect warehouse facts to dashboards and a feature store
- create a typed JSON diagram specification for Archify
Example prompts for the agent
- Create a product analytics data-flow diagram using
product-analytics.dataflow. - Show the consent check and distinguish the protected identity path from analytics events.
- Save the final candidate as
benchmark-candidate.jsonand leave other files unchanged.
How to install product-analytics.dataflow
Manually: put the files in place
.claude/commands/product-analytics.dataflow.mdHow to use
Paste the text at the start of a chat or into project instructions
Questions about product-analytics.dataflow
How do I install product-analytics.dataflow in Claude Code?
Place the command file at .claude/commands/product-analytics.dataflow.md.
What does product-analytics.dataflow do?
It instructs Archify to create a typed JSON diagram of product analytics, including a visually distinct route for identity data.
Where should product-analytics.dataflow save its output?
Write the final candidate to benchmark-candidate.json at the repository root without editing other files.
Source text
product-analytics.dataflow.md · Apache-2.0
# Product analytics data flow Use the Archify skill in this repository to create a data-flow diagram for product analytics. Web and mobile clients send events to an edge ingestion API. Consent is checked before identity data enters a protected PII vault. Accepted events enter a stream, become normalized warehouse facts, and feed dashboards. Aggregated warehouse data also feeds a feature store and model. Author a fresh typed JSON diagram specification targeting the `showcase` quality profile. Choose your own stable internal IDs and layout. Make the privacy boundary and restricted identity path visually distinct from the ordinary analytics path. Use the bundled Archify CLI to validate and repair the candidate when shell access is available. The external harness will independently validate the frozen candidate. Write the final candidate to exactly `benchmark-candidate.json` in the repository root. Do not edit any other file. The candidate file, not the prose response, is the attempt 1 artifact. Do not copy a checked-in example. Do not claim that validation passed.
© tt-a1i · Apache-2.0 · tt-a1i/archify