# big-review Adopt this skill: https://proskills.md/skills/other/datawithbaraa-claude-code-data-engineering-skills-skills-big-review Page: https://proskills.md/skills/other/datawithbaraa-claude-code-data-engineering-skills-skills-big-review This document is the public skill bundle for that page. It contains SKILL.md and every helper file the catalog carries. No login is required. ## File: skills/big-review/SKILL.md size: 1610 sha: 258f4916405c1829463ae5a92e9ac9f45db98d45 upstream: https://github.com/datawithbaraa/claude-code-data-engineering-skills/blob/main/skills/big-review/SKILL.md ```text --- 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 Code health: duplicated logic, outdated documents and the longest functions. 5.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. ``` ## File: skills/big-review/references/big-review.html size: 39730 sha: 3539b6f05f6b6e578376808b7ff23d0404b07621 upstream: https://github.com/datawithbaraa/claude-code-data-engineering-skills/blob/main/skills/big-review/references/big-review.html Content is not inlined in the catalog. Read the upstream file: https://github.com/datawithbaraa/claude-code-data-engineering-skills/blob/main/skills/big-review/references/big-review.html ## File: skills/big-review/references/fonts/BricolageGrotesque-700.woff2 size: 76868 sha: b908aff816383eee73ef620808f6f2f8a05d2542 upstream: https://github.com/datawithbaraa/claude-code-data-engineering-skills/blob/main/skills/big-review/references/fonts/BricolageGrotesque-700.woff2 Content is not inlined in the catalog. Read the upstream file: https://github.com/datawithbaraa/claude-code-data-engineering-skills/blob/main/skills/big-review/references/fonts/BricolageGrotesque-700.woff2 ## File: skills/big-review/references/fonts/JetBrainsMono-500.woff2 size: 31340 sha: 2ca6ac605954ee884442db8ea1d61093000bcc29 upstream: https://github.com/datawithbaraa/claude-code-data-engineering-skills/blob/main/skills/big-review/references/fonts/JetBrainsMono-500.woff2 Content is not inlined in the catalog. Read the upstream file: https://github.com/datawithbaraa/claude-code-data-engineering-skills/blob/main/skills/big-review/references/fonts/JetBrainsMono-500.woff2 ## File: README.md upstream: https://github.com/datawithbaraa/claude-code-data-engineering-skills/blob/main/README.md ````text # Claude Code skills for data engineers ![The incident report of a failed run, one of the pages these skills write](docs/hero.png) 16 Claude Code skills for the work of a data engineer beyond writing code: profiling a new source, investigating a failed pipeline, building the metadata, reviewing changes, documenting, and keeping the platform clean. Most of them end in a web page you can read and share. ⭐ If these skills help you, star the repository so other data engineers can find them too. Seven of them are from the video [How I Use Claude Code as a Data Engineer](https://youtu.be/F5lZj1bQyUw) on the [Data With Baraa](https://www.youtube.com/@DataWithBaraa) YouTube channel. The example pages describe a fictional company with fictional data. > [!NOTE] > This is the first draft. We will expand and enhance the skills over time. Questions, ideas, or a skill of your own to share? Join the [🤖・claude-code channel on Discord](https://discord.gg/AFZet4FXF). ## Install You need Claude Code with a Claude Pro, Max, Team or Enterprise plan, or a Claude Console account. ```bash git clone https://github.com/DataWithBaraa/claude-code-data-engineering-skills.git mkdir -p your-project/.claude/skills cp -r claude-code-data-engineering-skills/skills/* your-project/.claude/skills/ ``` Or install them as a plugin, inside Claude Code: ```text /plugin marketplace add DataWithBaraa/claude-code-data-engineering-skills /plugin install data-engineering@data-with-baraa ``` Then type a skill and what it needs, for example `/profile data/landing/purchasing` or `/incident 2026-08-19`. As a plugin, it is `/data-engineering:profile`. Read a skill before you use it: each one says what it reads, what it writes and what it never does. To get new versions, pull the repo and copy the skills again, or update the plugin under `/plugin`. Plugin updates are not automatic. ## The skills **When new data arrives** - [profile](skills/profile/SKILL.md): understand a new source before you build anything on it. - [contract](skills/contract/SKILL.md): the data contract with the source system, in the Open Data Contract Standard. - [metadata](skills/metadata/SKILL.md): every table and column described, the types from the data, the descriptions from the documents. **When something breaks** - [incident](skills/incident/SKILL.md): a failed run, from the error to the root cause, the fix options, the email drafts and the log entry. - [quality](skills/quality/SKILL.md): which checks failed or warned, and whether each table is safe to use today. - [reconcile](skills/reconcile/SKILL.md): two numbers that should agree, where they diverge and why. **Before a change goes in** - [impact](skills/impact/SKILL.md): what a change to a table, a column or a function breaks, and the safe order of the change. - [test-data](skills/test-data/SKILL.md): test data with the edge cases, and the expected result written first. - [pr-review](skills/pr-review/SKILL.md): a pull request reviewed pass by pass against your standards, with pushback. **When you need the big picture** - [toolkit](skills/toolkit/SKILL.md): the documentation site of the project, built from the repo. - [big-review](skills/big-review/SKILL.md): the whole platform from the query logs and the repo, with proposals. - [cost-review](skills/cost-review/SKILL.md): where the compute and the storage money goes, and what to cut. **When others use your data** - [data-product](skills/data-product/SKILL.md): everything a consumer needs for one table, from the guide to the contract. - [docs](skills/docs/SKILL.md): the runbook and the how-to guides, matching the code. **When the project grows** - [knowledge-refresh](skills/knowledge-refresh/SKILL.md): the knowledge Claude Code reads, checked against the code and the data. - [migration](skills/migration/SKILL.md): an old estate of jobs and tables, inventoried, rated and planned into waves. The seven from the video are profile, metadata, incident, toolkit, data-product, pr-review and big-review. In the video the incident skill is called `/incidents`. ## What they make
The profile of a new source
profile: one new source on one page		 The root cause of a failed run
incident: the root cause, and the same failure in the incident log
What a change to the orders table reaches
impact: what a change to one table reaches		 The verdict per table
quality: a verdict for every table
The architecture page of the toolkit
toolkit: the architecture, drawn from what runs		 The page of one data product
data-product: one data product for its consumers
Each skill is one `SKILL.md` with the job, the input, the steps, the output, what it reads, what it writes and what it never does. Most have an example result in `references/`. Open the HTML files in your browser, because GitHub only shows their code. ## Make them yours The skills are generic on purpose. Add your own paths, standards and rules to the steps. [CLAUDE.md](CLAUDE.md) is the instructions file from the video: copy it into the root of your project and adapt it. Other Claude apps may reject the `argument-hint` line, so remove it before you upload a skill there. ## License MIT, see [LICENSE](LICENSE). The fonts of the example pages are under the SIL Open Font License, see [OFL.txt](OFL.txt). ````