メニュー
Generate an API markdown file and token file using ApiView. Use this when the user wants to generate an API markdown file and review API changes.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | generate-api-markdown |
| description | Generate an API markdown file and token file using ApiView. Use this when the user wants to generate an API markdown file and review API changes. |
cd <repo_root>
pip install -e ./eng/tools/azure-sdk-tools
azpysdk apistub .
api.md and api.metadata.yml in the package directory, which are the files needed to pass the API consistency check. Provide these files to the user for review.azpysdk apistub . --token-file instead.Automate updating the emitter package dependencies in eng/emitter-package.json for the Azure SDK for Python repository, then open a PR. Use this skill when the user wants to update @azure-tools/typespec-python (or any other dependency in emitter-package.json) to the latest version, create a PR for an emitter-package version bump, or manage emitter-package.json updates.
Emit the azure-ai-projects Python SDK from TypeSpec, apply post-emitter fixes, and create a Pull Request. WHEN: "emit SDK from TypeSpec", "generate azure-ai-projects SDK", "update azure-ai-projects from TypeSpec", "emit from TypeSpec", "regenerate azure-ai-projects". DO NOT USE FOR: other Azure SDK packages, manual code edits without TypeSpec. INVOKES: PostEmitter.ps1 script, git commands, gh CLI for PR creation.
Update CHANGELOG.md by comparing public APIs between the current branch and the latest released version on PyPI. WHEN: "update changelog", "generate changelog", "add changelog entry", "what changed in this version". DO NOT USE FOR: other Azure SDK packages. INVOKES: PyPI API, GitHub API (for tags), file operations.
Drafts concise team status updates with progress, plans, and blockers.
Create and test a classify-and-route Azure AI Content Understanding pipeline for packets that contain multiple document types (e.g. invoice + bank statement + loan application in one PDF). Walks per-type schema authoring → outer classifier wiring → batch test → category-aware stdout summary using the typed ContentUnderstandingClient. Use when the user has mixed-document packets.
Iteratively author and test a custom Azure AI Content Understanding analyzer for a folder of **document** files (PDFs, page images) of a single type. Walks layout extraction → schema authoring → validation → batch test → agent review → refine cycle using the typed ContentUnderstandingClient. Document modality only — audio, video, and image analyzers are planned for a later update. Use when the user wants to author a custom analyzer for invoices, contracts, forms, or any other single-type document set.