菜单
Meta-skill loaded at session start. Directs Claude to check for applicable OpenMetadata skills before starting any task. Ensures structured workflows are followed.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/open-metadata/OpenMetadata --skill openmetadata-workflow命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Set up, verify, or repair a local OpenMetadata development environment on macOS or Linux. Installs the toolchain (Java 21, Maven, Node 22, Yarn 1.x, Python 3.10+, ANTLR 4.9.2, Docker), creates the Python venv, generates models, installs UI dependencies and pre-commit hooks. Use for a fresh clone, a new worktree, onboarding, or when a build fails with a missing/wrong tool.
Run `mvn spotless:apply` to fix Java checkstyle / formatting failures and verify the result. Invoke after authoring or modifying any `.java` files, or when CI reports a "Java checkstyle failed" or "Fix Java checkstyle" issue on a PR.
Generate robust, zero-flakiness Playwright E2E tests following OpenMetadata patterns. Creates comprehensive test files with proper waits, API validation, multi-role permissions, and complete entity lifecycle management.
正在显示 SKILL.md
基于 SOC 职业分类
| name | openmetadata-workflow |
| description | Meta-skill loaded at session start. Directs Claude to check for applicable OpenMetadata skills before starting any task. Ensures structured workflows are followed. |
This skill is loaded automatically at session start. It ensures you follow the right workflow for every task.
Check which skills apply to your task and use them. This is not optional — if a skill applies, you must follow it.
| Task type | Required skill(s) |
|---|---|
| New feature (multi-file) | /planning then /tdd then /test-enforcement then /verification |
| Bug fix | /systematic-debugging then /tdd (write regression test) then /verification |
| New API endpoint | /planning then /tdd then /test-enforcement (must include integration test) |
| New connector | /connector-standards then /connector-building then /test-enforcement |
| UI component | /ui-core-components + /react-best-practices + /composition-patterns before writing, then /tdd, then /web-design-guidelines after, then /test-enforcement (must include Jest + Playwright if user-facing) |
| UI a11y / UX / design audit | /web-design-guidelines |
| React perf work (re-renders, waterfalls, bundle) | /react-best-practices |
| Code review / PR review | /code-review then /test-enforcement |
| Opening / finalizing a PR | /test-enforcement then /verification then /pr-checklist |
| Connector review | /connector-review |
| E2E test creation | /playwright |
| Finishing implementation | /test-enforcement then /verification |
Note: Connector skills (
/connector-standards,/connector-building,/connector-review) and/playwrightare part of the OpenMetadata Skills plugin and ship together with this workflow skill. They are defined in theskills/directory alongside this file.
Why the UI row names skills explicitly: a skill only loads when it is invoked, and the model decides that from the skill's own
description./composition-patternsdescribes itself as being for refactoring prop proliferation and building component libraries, and/web-design-guidelinesdescribes itself as being for "review my UI" / "check accessibility" — so neither reliably fires on "build me a component". Naming them here is what makes them part of the workflow instead of a coin flip. Invoke/web-design-guidelinesafter the component exists: it is an audit, and running it first works against its own trigger.
/react-best-practices,/composition-patternsand/web-design-guidelinesare vendored from vercel-labs/agent-skills (MIT) underskills/vendor/. They are authoring aids, not gates — enforcement isui-checkstyle, seedocs/ui-code-quality-gate.md.
Plan before coding. For any non-trivial task, use /planning to design the approach before writing code.
Test-first when possible. Use /tdd to write failing tests before implementation. This applies to Java, Python, and TypeScript equally.
Always enforce test coverage. Before any PR, use /test-enforcement to verify:
Verify with evidence. Use /verification before claiming completion. Show actual test output, not claims.
Review before merging. Use /code-review for two-stage review (spec compliance + code quality).
Fill the PR template completely. Use /pr-checklist before gh pr create to gather every required section: linked issue, high-level design (large PRs), tests + coverage, UI screen recording, and manual test steps.
When your task touches multiple layers, ensure all are synchronized:
openmetadata-spec/ → run make generateyarn parse-schemabootstrap/sql/migrations/locale/languages/en-us.json then run yarn i18nmvn spotless:applymake py_format && make py_format_checkyarn organize-imports:cli && yarn lint:fix && yarn pretty:base --writeyarn license-header-fix)yarn generate:app-docsIf CLAUDE.md instructions conflict with any skill, CLAUDE.md wins. Skills are supplementary workflows, not overrides.