data-engineering · datawithbaraa — плагин для Claude Code: задачи и установка
Плагин data-engineering для Claude Code помогает дата-инженерам разбирать сбои, проверять изменения и описывать данные. В наборе 16 скиллов для разных этапов работы с платформой данных.
MIT ★ 106 обновлён 2026-11-06
/plugin marketplace add DataWithBaraa/claude-code-data-engineering-skills
/plugin install data-engineering@data-with-baraaЧто делает data-engineering
Плагин собирает 16 скиллов для задач дата-инженера: от изучения нового источника и описания таблиц до разбора инцидентов, ревью изменений и планирования миграции. Отдельные скиллы сверяют показатели, оценивают качество таблиц и анализируют расходы на вычисления и хранение.
Скиллы создают отчёты и документацию, часто в виде HTML-страниц, которые можно открыть в браузере. Каждый описан в собственном файле SKILL.md; примеры результатов лежат в references/. Для работы нужен Claude Code с планом Claude Pro, Max, Team или Enterprise либо аккаунтом Claude Console. Обновления плагина не устанавливаются автоматически.
Какие задачи решает
- разобрать причину сбоя конвейера данных
- оценить влияние изменения таблицы или функции
- сверить показатели, которые должны совпадать
- подготовить документацию по таблицам и проекту
Примеры запросов агенту
- Изучи новый источник данных по пути
data/landing/purchasingчерез/data-engineering:profile. - Разбери сбой за
2026-08-19командой/data-engineering:incident. - Проведи ревью этого pull request по стандартам проекта через
/data-engineering:pr-review.
Как установить data-engineering
Через маркетплейс плагинов
/plugin marketplace add DataWithBaraa/claude-code-data-engineering-skills/plugin install data-engineering@data-with-baraaПо шагам, с командами для каждой платформы: Плагины Claude Code: маркетплейсы, установка и как собрать свой
Вопросы о data-engineering
Как установить data-engineering в Claude Code?
В Claude Code выполни /plugin marketplace add DataWithBaraa/claude-code-data-engineering-skills, затем /plugin install data-engineering@data-with-baraa.
Что делает data-engineering?
Добавляет 16 скиллов для дата-инженерных задач: профилирования источников, проверки качества данных, расследования сбоев, ревью и документации.
Что нужно для работы data-engineering?
Нужен Claude Code с планом Claude Pro, Max, Team или Enterprise либо аккаунтом Claude Console.
Исходный текст
SKILL.md · MIT
# Claude Code skills for data engineers  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 <table> <tr> <td width="50%"><img src="docs/profile.png" alt="The profile of a new source"><br><sub><b>profile:</b> one new source on one page</sub></td> <td width="50%"><img src="docs/incident-root-cause.png" alt="The root cause of a failed run"><br><sub><b>incident:</b> the root cause, and the same failure in the incident log</sub></td> </tr> <tr> <td width="50%"><img src="docs/impact-graph.png" alt="What a change to the orders table reaches"><br><sub><b>impact:</b> what a change to one table reaches</sub></td> <td width="50%"><img src="docs/quality-verdict.png" alt="The verdict per table"><br><sub><b>quality:</b> a verdict for every table</sub></td> </tr> <tr> <td width="50%"><img src="docs/toolkit-architecture.png" alt="The architecture page of the toolkit"><br><sub><b>toolkit:</b> the architecture, drawn from what runs</sub></td> <td width="50%"><img src="docs/data-product.png" alt="The page of one data product"><br><sub><b>data-product:</b> one data product for its consumers</sub></td> </tr> </table> 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).
© Data With Baraa · MIT · DataWithBaraa/claude-code-data-engineering-skills
Похожие плагины
Все плагины по теме «Данные и базы» →Сначала — data-engineering от других авторов.