pr-review

bởi microsoft

Xác minh độ chính xác kỹ thuật của một pull request vscode-docs so với mã nguồn VS Code trong microsoft/vscode và microsoft/vscode-copilot-chat. Sử dụng khi…

npx skills add https://github.com/microsoft/vscode-docs --skill pr-review

PR Technical Accuracy Review

Review a vscode-docs pull request and verify every factual claim about VS Code behavior against the source code in microsoft/vscode and microsoft/vscode-copilot-chat. Produce an actionable list of findings the author can address before merging.

This skill checks technical accuracy only. It does not enforce writing style, frontmatter, or release-notes structure — use the release-note-writer or frontmatter-description skills for those.

When to Use

  • Reviewing a vscode-docs PR that documents a new or updated VS Code or Copilot feature.
  • Auditing existing docs for drift after a feature has changed.
  • Asked to "fact-check", "verify", or "validate" a docs change against the product.
  • Before merging a PR that touches docs/, api/, remote/, or release-notes content tied to a specific behavior.

Do not use this skill for pure copy-edits, redirects, image swaps, or other changes that make no factual claims.

Repos to Check

Area being documentedPrimary source repo(s)
Core editor, workbench, debug, terminal, tasks, settings, commands, keybindingsmicrosoft/vscode
Copilot Chat, inline chat, agent mode, chat tools, chat participants, MCP integration in chatmicrosoft/vscode-copilot-chat
Extension API, contribution points, package.json schemamicrosoft/vscode (under src/vs/workbench/api/, src/vscode-dts/, and extensions/)
Enterprise policiesmicrosoft/vscode (policy definitions) — note that enterprise/policies.md is generated; verify against source, not the generated file

Use the gh CLI for all GitHub interactions (see user memory gh-cli-powershell.md for PowerShell-specific patterns).

Procedure

1. Identify the PR and its diff

  • If a PR number was given, run gh pr view <number> --json number,title,headRefName,baseRefName,files,body to get metadata and the file list.
  • If no argument was given, run gh pr view --json ... to use the PR for the current branch. If there is no associated PR, fall back to git diff origin/main...HEAD.
  • Get the actual changed lines with gh pr diff <number> (or git diff for a branch).
  • Skip files whose changes are purely cosmetic (typo fixes, image renames, redirect entries, frontmatter-only edits).

2. Extract verifiable claims

Walk the diff and build a list of every claim that can be checked against source code. Include line numbers from the new file content. Categories to look for:

CategoryExamples
Settingeditor.fontSize, chat.agent.enabled, default values, allowed enum values, deprecation status
CommandCommand IDs (workbench.action.*), command palette titles, the action they perform
KeybindingDefault key bindings, when clauses, platform-specific overrides
Menu / UI labelMenu item text, button labels, view titles, walkthrough step titles
APINames, signatures, and shapes in vscode.d.ts / vscode.proposed.*.d.ts
Contribution pointpackage.json schema entries (contributes.*), required fields
Chat tool / participantTool names, participant IDs, tool input/output schemas, agent mode availability
MCPServer config schema, supported transports, capability flags
Version availability"Available since 1.X" / "New in 1.X" claims
Default behaviorWhat happens out-of-the-box, what is on/off by default
PolicyPolicy names, supported values, scope

Treat anchor-style references (e.g., setting(chat.agent.enabled), command:workbench.action.X) as claims to verify.

3. Verify each claim

For every claim, locate the source of truth and compare. Prefer one targeted lookup per claim — do not download full files when a search will do.

Search the source repos (parallelize independent lookups):

  • gh search code --repo microsoft/vscode '"<exact-string>"' for setting IDs, command IDs, contribution keys.
  • gh search code --repo microsoft/vscode-copilot-chat '"<exact-string>"' for chat tool names, participant IDs, agent-mode flags.
  • gh api "search/code?q=<query>+repo:microsoft/vscode" when the gh search CLI quotes the query in a way that breaks qualifiers (see user memory gh-cli-powershell.md).
  • gh api repos/microsoft/vscode/contents/<path>?ref=main to read a specific file.

Where things live (common starting points):

  • Settings — search for '<setting.id>' near registerConfiguration calls; default values are in the default: field of the schema.
  • Commands — search for CommandsRegistry.registerCommand or registerAction2 with the matching id.
  • Keybindings — search for KeybindingsRegistry.registerKeybindingRule or look in src/vs/workbench/browser/parts/editor/... and feature folders.
  • Extension API — src/vscode-dts/vscode.d.ts (stable) and src/vscode-dts/vscode.proposed.*.d.ts (proposed).
  • Chat tools — search microsoft/vscode-copilot-chat for displayName, toolReferenceName, or the tool ID string.
  • Contribution points — extensions/<ext>/package.json and the schema in src/vs/workbench/api/common/extHost*.ts.

Version availability — when a doc claims "since 1.X":

  • gh api repos/microsoft/vscode/contents/<file>?ref=release/1.X to see if the symbol existed in that branch, or
  • gh search commits --repo microsoft/vscode '<symbol>' to find when it was introduced.

If a claim cannot be verified after a reasonable search, mark it Unverified rather than failing it — the author may have access to context the source does not expose.

4. Categorize each finding

SeverityUse when
ErrorThe doc contradicts the source code (wrong setting name, wrong default, wrong command ID, removed API, wrong key binding).
WarningThe claim is partially correct but misleading (default changed in a recent release, behavior is platform-specific and the doc does not say so, feature is behind a setting the doc does not mention).
SuggestionOptional clarification — link to the source, add a "since 1.X" note, mention a related setting.
UnverifiedCould not locate the source of truth; ask the author to confirm.

5. Produce the findings list

Output a Markdown report with this structure:

## PR Accuracy Review: #<number> — <title>

**Files reviewed:** <count>
**Claims checked:** <count>
**Result:** <Pass | Pass with warnings | Needs changes>

### Errors

* **`<file>`:L<line>** (`<category>`) — <one-line description>
  * Doc says: `<quoted text>`
  * Source: `<repo>/<path>#L<line>` — <what the source actually says>
  * Fix: <specific suggested correction>

### Warnings

* ...

### Suggestions

* ...

### Unverified

* **`<file>`:L<line>** — <claim>. Searched <queries tried>. Please confirm.

Rules for the report:

  • Use workspace-relative paths and 1-based line numbers for vscode-docs files, formatted as Markdown links per the fileLinkification rules.
  • For source-code citations, include the repo, file path, and (when known) line or commit. A gh-friendly URL is fine: https://github.com/microsoft/vscode/blob/main/<path>#L<line>.
  • Quote the doc text exactly so the author can search for it.
  • Keep each finding to one issue — split combined problems into separate items.
  • If everything checks out, say so explicitly and skip the empty sections.

6. Summary

End with:

  • Counts by severity.
  • An overall verdict: Pass, Pass with warnings, or Needs changes (any Errors → Needs changes).
  • A reminder that this review covers technical accuracy only, and to run style/frontmatter skills separately if needed.

Notes

  • Do not push commits or post review comments on the PR unless the user explicitly asks. This skill produces a report for the user to act on.
  • Do not edit enterprise/policies.md — it is generated; flag policy issues against enterprise/policies-template.md and the source policy definitions instead.
  • When the doc references screenshots or videos, do not attempt to verify their contents — only verify any captions, labels, or alt text that make factual claims.
  • Prefer main as the source-of-truth ref unless the PR explicitly documents behavior on a release branch or Insiders-only feature, in which case check release/1.X or recent commits accordingly.

Thêm skills từ microsoft

oss-growth
microsoft
Cá tính tăng trưởng OSS
agent-framework-azure-ai-py
microsoft
Xây dựng các tác nhân Azure AI Foundry bằng SDK Python của Microsoft Agent Framework (agent-framework-azure-ai). Sử dụng khi tạo các tác nhân bền vững với AzureAIAgentsProvider, sử dụng các công cụ được lưu trữ (trình thông dịch mã, tìm kiếm tệp, tìm kiếm web), tích hợp máy chủ MCP, quản lý chuỗi hội thoại hoặc triển khai phản hồi phát trực tuyến. Bao gồm các công cụ hàm, đầu ra có cấu trúc và các tác nhân đa công cụ.
development
airunway-aks-setup
microsoft
Thiết lập AI Runway trên AKS — từ cụm trống đến mô hình đang chạy. Bao gồm xác minh cụm, cài đặt controller, đánh giá GPU, thiết lập nhà cung cấp và triển khai đầu tiên. KHI NÀO: "thiết lập AI Runway", "onboard cụm AKS", "cài đặt AI Runway", "thiết lập airunway", "triển khai mô hình lên AKS", "suy luận GPU trên AKS", "thiết lập KAITO trên AKS", "chạy LLM trên AKS", "vLLM trên AKS", "thiết lập phục vụ mô hình trên AKS", "AI Runway controller".
devops
appinsights-instrumentation
microsoft
Hướng dẫn để instrument các ứng dụng web với Azure Application Insights. Cung cấp các mẫu telemetry, thiết lập SDK, và tài liệu tham khảo cấu hình. KHI NÀO: cách instrument ứng dụng, App Insights SDK, các mẫu telemetry, App Insights là gì, hướng dẫn Application Insights, ví dụ instrumentation, các phương pháp tốt nhất APM.
devops
applicationinsights-web-ts
microsoft
Instrument các ứng dụng trình duyệt/web bằng SDK JavaScript Application Insights (@microsoft/applicationinsights-web). Dùng cho Real User Monitoring (RUM) — lượt xem trang, nhấp chuột, phụ thuộc AJAX/fetch, ngoại lệ, sự kiện tùy chỉnh và dấu vết tác nhân GenAI phía trình duyệt tương quan với dấu vết OpenTelemetry phía backend. Bao gồm thiết lập SDK Loader Script và npm, tiện ích mở rộng framework (React, React Native, Angular), Click Analytics, trình khởi tạo telemetry và quy ước ngữ nghĩa OTel GenAI cho các span tác nhân/công cụ/mô hình phát ra từ trình duyệt.
devops
azure-ai-anomalydetector-java
microsoft
Xây dựng ứng dụng phát hiện bất thường với Azure AI Anomaly Detector SDK cho Java. Sử dụng khi triển khai phát hiện bất thường đơn biến/đa biến, phân tích chuỗi thời gian hoặc giám sát hỗ trợ AI.
development
azure-ai-language-conversations-py
microsoft
Triển khai Conversational Language Understanding (CLU) bằng SDK Python azure-ai-language-conversations. Sử dụng khi làm việc với ConversationAnalysisClient để phân tích ý định và thực thể trong hội thoại, xây dựng tính năng NLP, hoặc tích hợp hiểu ngôn ngữ vào ứng dụng.
development
azure-ai-ml-py
microsoft
Azure Machine Learning SDK v2 cho Python. Dùng cho không gian làm việc ML, công việc, mô hình, tập dữ liệu, tính toán và quy trình. Kích hoạt: "azure-ai-ml", "MLClient", "không gian làm việc", "đăng ký mô hình", "công việc đào tạo", "tập dữ liệu".
development