菜单
Retrieve human architect review comments from APIView for a date range. Use for: architect comments, human comments, reviewer comments, board comments, architect comments for March, what did architects say, human review comments.
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。
基于 SOC 职业分类
Create, get, update, abandon, and link SDK PRs to release plan work items for Azure SDK releases. **UTILITY SKILL**. USE FOR: "create release plan", "get release plan", "update release plan", "update API spec in release plan", "update SDK details in release plan", "abandon release plan", "link SDK PR to plan", "namespace approval", "check release plan status". DO NOT USE FOR: SDK code generation, pipeline troubleshooting, API review feedback. INVOKES: azure-sdk-mcp:azsdk_create_release_plan, azure-sdk-mcp:azsdk_get_release_plan, azure-sdk-mcp:azsdk_get_release_plan_for_spec_pr, azure-sdk-mcp:azsdk_update_release_plan, azure-sdk-mcp:azsdk_update_api_spec_pull_request_in_release_plan, azure-sdk-mcp:azsdk_update_sdk_details_in_release_plan, azure-sdk-mcp:azsdk_abandon_release_plan, azure-sdk-mcp:azsdk_link_sdk_pull_request_to_release_plan, azure-sdk-mcp:azsdk_link_namespace_approval_issue.
Authors and modifies Azure TypeSpec (.tsp) API specifications. USE FOR: any TypeSpec/tsp change — api versions (add, bump, preview, stable, promote), resources, operations, models, properties, decorators, visibility, constraints, breaking changes, LRO, suppressions, operationId, spread model. Covers ARM resource-manager and data-plane services. DO NOT USE FOR: SDK generation, releasing SDK packages, or single MCP tool calls. INVOKES: azure-sdk-mcp:azsdk_typespec_generate_authoring_plan, azure-sdk-mcp:azsdk_run_typespec_validation.
Create a new evaluation dataset or add cases to an existing one for the Azure SDK QA bot evaluation. WHEN: "add eval dataset item", "add a test case", "new evaluation dataset", "create dataset", "add question to dataset", "curate eval data", "promote staging cases", "upload dataset asset", "new scenario dataset". DO NOT USE FOR: running evaluations, pipeline troubleshooting, knowledge-graph indexing.
Run Azure SDK QA bot evaluations on curated datasets locally, including a single test case. WHEN: "run evaluation", "run eval", "evaluate the bot", "run perf evaluation", "run basic evaluation", "run a single test case", "evaluate one question", "run all scenarios", "score the bot", "run evals locally". DO NOT USE FOR: preparing or uploading datasets, pipeline troubleshooting, knowledge-graph indexing.
Analyze markdown files for token efficiency and reduce context-window bloat. **UTILITY SKILL**. DO NOT USE FOR: code optimization, general file editing, non-markdown files. TRIGGERS: optimize markdown, reduce tokens, token count, token bloat, too many tokens, make concise, shrink file, file too large, optimize for AI, token efficiency, verbose markdown, reduce file size. INVOKES: waza CLI.
**WORKFLOW SKILL** — Iteratively improve skill frontmatter compliance using the Ralph loop pattern. WHEN: "run sensei", "sensei help", "improve skill", "fix frontmatter", "skill compliance", "frontmatter audit", "score skill", "check skill tokens". INVOKES: token counting tools, test runners, git commands. FOR SINGLE OPERATIONS: use token CLI directly for counts/checks.
| name | report-architect-comments |
| description | Retrieve human architect review comments from APIView for a date range. Use for: architect comments, human comments, reviewer comments, board comments, architect comments for March, what did architects say, human review comments. |
| argument-hint | Month name (e.g. 'March') or language + month (e.g. 'Python for March') |
This command returns comments written by human language board approvers in APIView. It excludes:
The set of approvers is determined from the APIView Permissions container — members of groups whose roles include "Architect" or "Deputy Architect" for the specified language. When no language is specified, all architect and deputy-architect group members are included.
Use --all-commenters to skip approver filtering and return comments from all users.
Unless the user says otherwise, always apply these defaults:
production--language unless user specifies one)--format)The user will typically specify a calendar month by name (e.g. "March", "January 2025"). Resolve to the full month date range:
| User says | start_date | end_date |
|---|---|---|
| "March" (current year) | YYYY-03-01 | YYYY-03-31 |
| "January 2025" | 2025-01-01 | 2025-01-31 |
| "March 1 to March 15" | YYYY-03-01 | YYYY-03-15 |
When only a month name is given without a year, use the current year. Be careful with month lengths (28/29/30/31 days).
Show the resolved command and run it immediately in a foreground terminal with a 120-second timeout (timeout: 120000). Redirect to a file since output can be very large.
Full terminal command (cleanup + run):
New-Item -ItemType Directory -Path output -Force | Out-Null; if (Test-Path output/architect_comments_output.json) { Remove-Item output/architect_comments_output.json }; python cli.py report architect-comments -s <start_date> -e <end_date> | Out-File -Encoding UTF8 output/architect_comments_output.json
After the command completes, read the output file with read_file to get the JSON results. Summarize the findings for the user (total count, languages covered, common themes, etc.).
For follow-up questions about the same data (filtering, counting, searching), read the output file with read_file instead of re-running the command. The file is at output/architect_comments_output.json.
# All architect comments for March 2026
python cli.py report architect-comments -s 2026-03-01 -e 2026-03-31
# Python architect comments only
python cli.py report architect-comments -s 2026-03-01 -e 2026-03-31 -l python
# All commenters (not just approvers)
python cli.py report architect-comments -s 2026-03-01 -e 2026-03-31 -l python --all-commenters
# Include reply comments (by default only first comment per thread is returned)
python cli.py report architect-comments -s 2026-03-01 -e 2026-03-31 -l java --include-replies
# YAML output
python cli.py report architect-comments -s 2026-03-01 -e 2026-03-31 --format yaml
# Staging environment
python cli.py report architect-comments -s 2026-03-01 -e 2026-03-31 --environment staging
| Flag | Type | Default | Description |
|---|---|---|---|
--start-date / -s | string | required | Start date (YYYY-MM-DD) |
--end-date / -e | string | required | End date (YYYY-MM-DD) |
--language / -l | string | all | Language to filter by (e.g., python, Go, C#) |
--environment | string | production | production or staging |
--format / -f | string | json | Output format: json or yaml |
--all-commenters | flag | false | Include comments from all users, not just approvers |
--include-replies | flag | false | Include reply comments. By default only the first comment per thread is returned |
read_file rather than relying on terminal output.python cli.py not .\avc: The avc.bat script may resolve to system Python.2>&1: Merges stderr into stdout, corrupting JSON. Only redirect stdout.>: Produces UTF-16 in PowerShell 5.1. Use | Out-File -Encoding UTF8.