data-product — Claude Code skill: what it does and how to install
A Claude Code skill that builds a data product page for people using a table. It runs when a table is released, changed, or served to consumers.
MIT ★ 106 updated 2026-11-06
/plugin marketplace add DataWithBaraa/claude-code-data-engineering-skills
/plugin install data-engineering@data-with-baraaWhat data-product does
The skill assembles a data product page from a table, its SQL, query logs, consumer-reported corrections, and knowledge about the table. It presents a plan first, then documents the table’s purpose and grain, its readers, service levels, data model, metrics, starter queries, and quality rules.
The page also includes release notes with version differences and a draft data contract in the Open Data Contract Standard. Output is an HTML file with tabs for each product. Before creating it, the skill reads references/data-products.html for the layout. It never changes a table or SQL; findings remain open for a data engineer. Release notes are drafted, not sent.
What it helps with
- document a table’s purpose and grain for its consumers
- map the tables and joins behind a data product
- derive starter queries from query logs
- compile quality rules and their results
- draft a data contract and release notes
Example prompts for the agent
- Create a data product page for the
orderstable - Prepare consumer documentation for
customer_events - Refresh the data product page after the
revenue_dailytable changes
How to install data-product
1Plugin marketplace
/plugin marketplace add DataWithBaraa/claude-code-data-engineering-skills/plugin install data-engineering@data-with-baraaThis installs the whole data-engineering plugin with all its skills
2Skills CLI (Vercel)
npx skills add DataWithBaraa/claude-code-data-engineering-skills --skill data-product -a claude-code3Manually: put the files in place
~/.claude/skills/data-product/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/data-product/
1Skills CLI (Vercel)
npx skills add DataWithBaraa/claude-code-data-engineering-skills --skill data-product -a codex2Manually: put the files in place
.agents/skills/data-product/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add DataWithBaraa/claude-code-data-engineering-skills --skill data-product -a cursor2Manually: put the files in place
.cursor/skills/data-product/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install DataWithBaraa/claude-code-data-engineering-skills skills/data-product2Manually: put the files in place
.github/skills/data-product/SKILL.md1Skills CLI (Vercel)
npx skills add DataWithBaraa/claude-code-data-engineering-skills --skill data-product -a gemini-cli2Platform CLI
gemini skills install https://github.com/DataWithBaraa/claude-code-data-engineering-skills --path skills/data-productManually: put the files in place
.devin/skills/data-product/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about data-product
How do I install data-product in Claude Code?
Add the marketplace with /plugin marketplace add DataWithBaraa/claude-code-data-engineering-skills, then install the skill with /plugin install data-engineering@data-with-baraa.
What does data-product do?
It builds an HTML page with a table overview, data model, metrics, starter queries, quality rules, release notes, and a data contract. It does not alter tables or SQL.
Does data-product change tables or send release notes?
No. It records findings as open points for a data engineer and drafts release notes without sending them.
Source text
SKILL.md · MIT
--- name: data-product description: Use when a table is served to consumers, released or changed, to build everything a consumer needs as a data product, the guide, the data model, the metrics, the starter queries, the quality, the releases and the data contract. argument-hint: "[table]" --- # Data product The job: the consumer side of one table, planned first. It changes no table and no SQL. Input: the table to serve. ## Steps 1. Plan first: read the table, its code and the queries of its consumers, and show the plan before writing anything. 2. Overview: what the table is for, its grain, who reads it, and the service levels. 3. Guide: what to trust, the known issues, and where to start. 4. Data model: the tables behind it and how they join. 5. Metrics: every measure with its rule, and what is safe to sum. 6. Queries: the starter queries, taken from the query logs. 7. Quality: the quality rules and their results. 8. Releases: the release notes, the number diff between the versions, and the corrections the consumers reported. 9. Contract: the data contract with the consumers, in the Open Data Contract Standard. 10. Add the product to the data products page, where the consumers browse. ## Output One HTML file, like [references/data-products.html](references/data-products.html): the data products page with every product, and each product with its tabs, from the overview to the contract. Read it for the layout before you write the page. ## Reads - the table, its SQL, the query logs, the corrections the consumers reported, the knowledge ## Writes - the documentation of the product, and the data products page ## Never - Never changes the table or any SQL: a finding is listed as an open point for the data engineer. - Never sends a release note: it drafts.
© Data With Baraa · MIT · DataWithBaraa/claude-code-data-engineering-skills