菜单
Address review comments on design spec files. Use when a developer submits inline review comments and wants them addressed. Triggers include "address review comments", "handle my review", or review comment submission.
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。
基于 SOC 职业分类
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/AzureAD/android-complete --skill design-reviewer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。
正在显示 SKILL.md
| name | design-reviewer |
| description | Address review comments on design spec files. Use when a developer submits inline review comments and wants them addressed. Triggers include "address review comments", "handle my review", or review comment submission. |
Address review comments on design spec files.
Comments are stored in:
.github/design-reviews/reviews.json
Format:
{
"reviews": {
"path/to/spec.md": [
{ "line": 30, "text": "Why is this needed?", "lineContent": "the line text" }
]
}
}
.github/design-reviews/reviews.json"No review comments found. Add comments using the gutter icons in the editor."
For each comment, read ±5 lines around the comment's line number for full context.
| Comment Type | How to Identify | Action |
|---|---|---|
| Genuine issue | Points out bug, inaccuracy, missing info | Update the spec |
| Improvement | Suggests better approach | Update if it improves clarity |
| Question | "why?", "what?", "how?" | Answer clearly; update spec if answer should be documented |
| Challenge | "Are you sure?" | Verify against codebase; update if wrong, explain if correct |
| Acknowledgment | "nice", "👍" | Acknowledge briefly, no change |
For each comment requiring a spec update:
replace_string_in_fileAfter addressing all comments for a spec, remove that spec's entry from reviews.json.
If no reviews remain, delete the file.
## Review Comments Addressed
---
### Comment 1: Line N — "[short quote]"
**Type**: Question / Issue / Improvement / Acknowledgment
**Action**: [What was done or why no change was needed]
---
### Comment 2: Line N — "..."
...
Rules:
### heading for EVERY comment — never a table--- separators between commentsGenerate the weekly Android on-call (OCE) WoW + 60-day trend telemetry reports as polished self-contained HTML. Produces TWO reports by default — the Android Broker report (from `android_spans` materialized views) and the Authenticator app report (from the Authenticator scenario materialized views) — plus a combined index page. Use this skill for the weekly OCE rotation when asked to "produce the OCE report", "weekly on-call report", "WoW telemetry report", "weekly broker health report", "authenticator weekly report", "authapp telemetry report", or "generate this week's on-call summary". Supports modes `both` (default), `broker`, and `authapp`. Writes to `$env:USERPROFILE\android-oce-reports\` (outside the workspace so reports are never committed).
Understand, navigate, and troubleshoot the Android Auth Client CI/CD pipeline system. Use this skill when asked about pipelines, release processes, build pipelines, hotfix workflows, daily validation, cron schedules, pipeline templates, release branches, RC testing, publishing to Maven Central, or any ADO/GitHub Actions pipeline question. Triggers include "how does the release pipeline work", "what pipeline does X", "where is the cron job for releases", "how do hotfixes work", "trace the monthly release flow", "pipeline template for Y", "how are broker apps built".
Analyze GitHub Copilot code review effectiveness across Android Auth repositories. Collects all Copilot inline review comments via GitHub API, classifies them as helpful/declined/incorrect/unresolved through reply analysis, diff verification, and AI-assisted classification, then generates a report with Copilot precision plus per-repo and per-engineer statistics. Use this skill when asked to "analyze Copilot reviews", "measure Copilot review effectiveness", "generate Copilot review report", "how helpful are Copilot reviews", "run review analysis", or any request to measure/report on GitHub Copilot code review quality and adoption.