big-review — Claude Code skill: data review and install
The big-review Claude Code skill reviews a data platform using query logs and repository code. It produces an HTML report with findings and proposed changes ranked by effort and risk.
MIT ★ 106 updated 2026-11-06
/plugin marketplace add DataWithBaraa/claude-code-data-engineering-skills
/plugin install data-engineering@data-with-baraaWhat big-review does
big-review examines table and query usage, unused data, dead code, code health, and data-quality checks. The default review period is the last month. Finding unused tables and columns requires at least 90 days of query logs.
The output is a single HTML page with metrics, charts or tables, and prioritized proposals. The skill reads query logs, the catalog, pipeline code, and documentation; it writes only the report. It does not alter the platform. A table can be dropped only after its owner agrees.
What it helps with
- spot slow queries and heavily read tables
- identify unused tables and columns while accounting for scheduled jobs
- find dead code and duplicated logic
- rank proposed changes by effort and risk
Example prompts for the agent
- Review the data platform for the last month.
- Find tables and columns that were unused during this period.
- Create an HTML review from the query logs and pipeline code.
How to install big-review
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 big-review -a claude-code3Manually: put the files in place
~/.claude/skills/big-review/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/big-review/
1Skills CLI (Vercel)
npx skills add DataWithBaraa/claude-code-data-engineering-skills --skill big-review -a codex2Manually: put the files in place
.agents/skills/big-review/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add DataWithBaraa/claude-code-data-engineering-skills --skill big-review -a cursor2Manually: put the files in place
.cursor/skills/big-review/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install DataWithBaraa/claude-code-data-engineering-skills skills/big-review2Manually: put the files in place
.github/skills/big-review/SKILL.md1Skills CLI (Vercel)
npx skills add DataWithBaraa/claude-code-data-engineering-skills --skill big-review -a gemini-cli2Platform CLI
gemini skills install https://github.com/DataWithBaraa/claude-code-data-engineering-skills --path skills/big-reviewManually: put the files in place
.devin/skills/big-review/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 big-review
How do I install big-review in Claude Code?
Run /plugin marketplace add DataWithBaraa/claude-code-data-engineering-skills first, then run /plugin install data-engineering@data-with-baraa.
What does big-review do?
It inspects query logs, the catalog, pipeline code, and documentation, then creates an HTML report with findings and ranked proposals. It does not modify the platform.
How much query history does big-review need to find unused data?
At least 90 days of query logs are needed to identify unused tables and columns. The default overall review period is the last month.
Source text
SKILL.md · MIT
--- name: big-review description: Use once a month, or when the platform feels slow, heavy or cluttered, to review the whole platform from the query logs and the repo, and propose improvements with effort and risk. argument-hint: "[period]" --- # Big review The job: one review of the whole platform, from what the consumers use to what nobody uses, every proposal with its effort and risk. It changes nothing. Input: the period, the last month by default, with at least 90 days of query logs for the unused data. ## Steps 1. Usage: the most read tables, the slowest queries, and the rows scanned against the rows needed. 2. Unused data: the tables and columns nobody read in the last 90 days, checked against the month-end, quarter-end and year-end jobs, the stale tables, and the storage they take. 3. Dead code: the functions, parameters and SQL that nothing uses. 4. Code health: duplicated logic, outdated documents and the longest functions. 5. Data quality: the checks per layer, and the layers without any. 6. Proposals: each one with the effort and the risk, in order of priority. A table is deprecated first and dropped only after its owner agrees. 7. Give the result as one web page. ## Output One HTML file, like [references/big-review.html](references/big-review.html): the numbers on top, one section per step with a chart or a table, the proposals last. Read it for the layout before you write the page. ## Reads - the query logs, the catalog, the pipeline code, the documents ## Writes - the web page only ## Never - Never changes anything: it proposes, the data engineer decides.
© Data With Baraa · MIT · DataWithBaraa/claude-code-data-engineering-skills