Menu
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。
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
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.
引用与脚注规范 —— 所有事实必须可点击回溯到 sources 数组。
| name | market-research |
| description | 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。 |
| triggers | ["用户提到\"调研 / 分析 / 对比 / 市场 / 竞品 / 玩家 / 份额\"","用户给出产品名 / 品类名 / 公司名要做\"画像\"","复合问题需要外部数据支撑"] |
| scripts | [] |
把用户问题拆成 3-7 个互不重叠的子问题。常用模板：
| 维度 | 子问题示例 |
|---|---|
| 定义 | 这个品类包含什么 / 排除什么？ |
| 玩家 | 头部 3-5 家是谁？份额怎样？ |
| 产品 | 功能对比矩阵（按用户视角）？ |
| 商业 | 商业模式 / 定价 / 主要市场？ |
| 增长 | 近 2 年的增长信号 / 公开数字？ |
| 风险 | 政策 / 技术 / 替代品 / 法务 |
把子问题与计划用的工具一起返回给用户，再开始执行。
web_search + web_fetch）对每个子问题：
web_search 给 1-3 个不同关键词（中英文皆可）。web_fetch 拉正文。sources[]：{title, url, publishedAt, accessedAt}。禁止仅依赖单一来源（例如只用维基百科）做关键数字结论。
把抓到的事实做 dedup：
confidence=highcaveats 注明差异confidence=low，并在 caveats 写"仅 1 个来源"report_builder 生成最终输出report_builder 接受 sections + sources，返回符合 persona 输出契约的 JSON：
report_builder(
topic="...",
subQuestions=[...],
sections=[
{"title": "市场玩家", "body": "...(¹)(²)", "citations": [1, 2]},
...
],
sources=[...],
confidence="medium",
caveats=["IDC 与 Statista 在 2024 份额上有 5% 差异"]
)
工具会做最后的 schema 校验；不通过则抛错让你修补。
caveats，不要编造数字。personas/shared/guardrails.md 的"不做投资建议"规则。引文必须按出现顺序编号（(¹)、(²)、(³) …），与 sources[].id 严格对应。同一 source 可被多次引用同一个编号。