菜单
Collects comparison test run artifacts and answers the user's questions based on the trajectories of each run. WHEN TO USE: collect comparison test artifacts
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/microsoft/GitHub-Copilot-for-Azure --skill analyze-comparison-tests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。
Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end with azd. USE FOR: azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy, prompt agent create, create agent, update agent, add tool to agent, invoke agent, agent.yaml, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, prompt optimizer, optimize agent instructions, Agent Optimizer scaffold, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, troubleshoot agent, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, fine-tuned model, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).
Architect and provision enterprise Azure infrastructure from workload descriptions. For cloud architects and platform engineers planning networking, identity, security, compliance, and multi-resource topologies with WAF alignment. Generates Bicep or Terraform directly (no azd). WHEN: 'plan Azure infrastructure', 'architect Azure landing zone', 'design hub-spoke network', 'plan multi-region DR topology', 'set up VNets firewalls and private endpoints', 'subscription-scope Bicep deployment', 'Azure Backup for VM workloads'. PREFER azure-prepare FOR app-centric workflows.
Review skill PRs with structured severity-rated feedback covering token budgets, routing conflicts, required sections, and repo conventions. WHEN: "review skill", "review skill PR", "review skill changes", "check skill quality", "skill PR feedback".
正在显示 SKILL.md
| name | analyze-comparison-tests |
| description | Collects comparison test run artifacts and answers the user's questions based on the trajectories of each run. WHEN TO USE: collect comparison test artifacts |
| license | MIT |
| metadata | {"author":"Microsoft","version":"1.0.0"} |
Execute the collect-artifacts script to download the test run artifacts.
The user must provide an JSON file to correlate each comparison test run with the GitHub Actions run. The script expects one input argument as the path to this JSON file. The JSON input is supposed to be the JSON output when queuing the comparison test runs using the npm run compare:run command.
cd tests/
npm run compare:collect -- input.json
The collect-artifacts script will download the test run artifacts to a directory named comparison-artifacts in the current working directory. Before executing the script, check if there is already such an directory. If so, skip executing the script and proceed to step 2.
The downloaded artifacts will have the following folder structure:
comparison-artifacts/
├── <branch-name>/
│ ├── <stimulus-name-1>/
│ │ ├── <model>-with-skill/
│ │ │ ├── agent-metadata-<date-string-1>.md
│ │ │ ├── agent-metadata-<date-string-2>.md
│ │ │ └── ...
│ │ └── <model>-without-skill/
│ │ ├── agent-metadata-<date-string-1>.md
│ │ ├── agent-metadata-<date-string-2>.md
│ │ └── ...
│ └── <stimulus-name-2>/
│ ├── <model>-with-skill/
│ │ └── agent-metadata-*.md
│ └── <model>-without-skill/
│ └── agent-metadata-*.md
└── <branch-name-2>/
└── ...
Each <branch-name>/<stimulus-name>/<model>-with-skill or <branch-name>/<stimulus-name>/<model>-without-skill directory contains the test run trajectories for that stimulus and model on that branch, with or without skills. Each trajectory is a markdown file that records user prompts, tool call requests, tool execution results, assistant responses that happened during the run. It also contains statistics such as token usage and turns. Based on the trajectories, answer the user's questions for each test run. Generate a report following the report-template to show your answers.