菜单
引用与脚注规范 —— 所有事实必须可点击回溯到 sources 数组。
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
Build Azure AI Foundry agents using the Microsoft Agent Framework Python SDK (agent-framework-azure-ai). Use when creating persistent agents with AzureAIAgentsProvider, using hosted tools (code interpreter, file search, web search), integrating MCP servers, managing conversation threads, or implementing streaming responses. Covers function tools, structured outputs, and multi-tool agents.
Build AI applications using the Azure AI Projects Python SDK (azure-ai-projects). Use when working with Foundry project clients, creating versioned agents with PromptAgentDefinition, running evaluations, managing connections/deployments/datasets/indexes, or using OpenAI-compatible clients. This is the high-level Foundry SDK - for low-level agent operations, use azure-ai-agents-python skill.
Deploy, evaluate, and manage Foundry agents end-to-end: Docker build, ACR push, hosted/prompt agent create, container start, batch eval, continuous eval, prompt optimizer workflows, agent.yaml, dataset curation from traces. USE FOR: deploy agent to Foundry, hosted agent, create agent, invoke agent, evaluate agent, run batch eval, continuous eval, continuous monitoring, continuous eval status, optimize prompt, improve prompt, prompt optimizer, optimize agent instructions, improve agent instructions, optimize system prompt, deploy model, Foundry project, RBAC, role assignment, permissions, quota, capacity, region, troubleshoot agent, deployment failure, create dataset from traces, dataset versioning, eval trending, create AI Services, Cognitive Services, create Foundry resource, provision resource, knowledge index, agent monitoring, customize deployment, onboard, availability. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).
Guide for creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services. Use when creating new skills or updating existing skills.
市场/竞品研究的标准 4 步流程：拆解问题 → 多源检索 → 摘要抽取 → 结构化报告。
| name | citation-format |
| description | 引用与脚注规范 —— 所有事实必须可点击回溯到 sources 数组。 |
| triggers | ["任何业务输出包含外部数据点 / 数字 / 结论 / 公司动向"] |
| scripts | [] |
数字、市占率、增长率、定价等事实型陈述后立即加 (¹)、(²) 编号，与 sources 数组的 id 一一对应。
中国新茶饮市场 2024 年规模约 ¥3,547 亿元(¹)，同比增长 23%(²)。
{
"id": 1,
"title": "美团 2024 茶饮赛道白皮书",
"url": "https://example.com/report",
"publishedAt": "2024-12-01",
"accessedAt": "2025-01-15",
"domain": "example.com",
"kind": "report|news|official|wiki|forum"
}
publishedAt 不可推断时填 null。accessedAt 必填，工具会自动填当前日期。(¹)，只在第一次出现时标。据估算，X 占了 30% 的市场。 ← ❌ 无引用
Y 公司 CEO 表示 ... ← ❌ 无引用
该品类增速放缓 ← 解读句，无须引用，但前文必须有引用支撑这个判断
sources 里点到？sources[].url 是否真实有效 ?（生成阶段不可主动验证，但不要捏造域名）