[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M699E2JDT290B9SHDNMCME13":3,"skill-same:01M699E2JDT290B9SHDNMCME13":62},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":35,"ownerDescription":36,"updatedAt":37,"install":38,"resources":51},"01M699E2JDT290B9SHDNMCME13","add-generative-answers",null,"Add generative answer nodes (SearchAndSummarizeContent or AnswerQuestionWithAI) to a Copilot Studio topic. Use this instead of \u002Fadd-node when the user asks to add grounded answers, knowledge search, generative answers, or AI-powered responses — these nodes require specific patterns (ConditionGroup follow-up, knowledge source references, autoSend, responseCaptureType) that \u002Fadd-node does not cover.","microsoft\u002Fskills-for-copilot-studio","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M699DXBD563FYBGWKPJJRAVM",493,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills-for-copilot-studio\u002Fblob\u002Fmain\u002Fskills\u002Fadd-generative-answers\u002FSKILL.md",[],[19],"add generative answers","2026-11-10 10:12:30",false,"---\nuser-invocable: false\ndescription: Add generative answer nodes (SearchAndSummarizeContent or AnswerQuestionWithAI) to a Copilot Studio topic. Use this instead of \u002Fadd-node when the user asks to add grounded answers, knowledge search, generative answers, or AI-powered responses — these nodes require specific patterns (ConditionGroup follow-up, knowledge source references, autoSend, responseCaptureType) that \u002Fadd-node does not cover.\nargument-hint: \u003Ctopic-name or \"new\">\nallowed-tools: Bash(node *schema-lookup.bundle.js *), Read, Write, Edit, Glob\ncontext: fork\nagent: copilot-studio-author\n---\n\n# Add Generative Answers\n\nAdd `SearchAndSummarizeContent` nodes to generate responses grounded in the agent's knowledge sources.\n\n## Important: Do You Even Need a Topic?\n\nWhen knowledge sources are added to the agent (via `\u002Fadd-knowledge`), the AI can **directly search them without any topic** if it recognizes a QnA-style query. A dedicated topic with `SearchAndSummarizeContent` is useful when:\n- You want to **restrict the search to a subset of knowledge sources** (not all of them)\n- You want to **control the flow** around the answer (e.g., follow-up questions, formatting, adaptive cards)\n- You want to **process the response** before showing it (e.g., extract content, combine with other data)\n- You want to **use a specific input** other than the user's last message\n\nIf the user just wants the agent to answer questions from its knowledge, adding the knowledge source may be enough.\n\n## Instructions\n\n1. **Auto-discover the agent directory**:\n   ```\n   Glob: **\u002Fagent.mcs.yml\n   ```\n   NEVER hardcode an agent name.\n\n2. **Determine the approach** based on what the user needs:\n   - **Add to existing topic**: Read the target topic and insert a SearchAndSummarizeContent node\n   - **Create new search topic**: Generate a complete topic with the search pattern\n\n3. **Look up the schema** for both nodes:\n   ```bash\n   node ${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fschema-lookup.bundle.js resolve CreateSearchQuery\n   node ${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fschema-lookup.bundle.js resolve SearchAndSummarizeContent\n   ```\n\n4. **Read `settings.mcs.yml`** to check if `GenerativeActionsEnabled: true`. This determines the best pattern:\n   - **`GenerativeActionsEnabled: true`** → prefer **Pattern 2 (Orchestrator)**: use topic inputs\u002Foutputs and let the orchestrator handle the response. This is the best approach for generative-orchestrated agents.\n   - **`GenerativeActionsEnabled: false`** (or not set) → use **Pattern 1 (Direct Response)**: `autoSend: false` + manual SendActivity, or **Pattern 3 (Fallback Search)** for a simple all-knowledge fallback.\n   - **Verbatim\u002Fexact content needed** → use **Pattern 4 (Precision Search)**: `SearchKnowledgeSources` + `CreateSearchQuery` for raw results without AI summarization (insurance policies, HR docs, legal text).\n\n5. **Ask the user** to clarify the behavior (if not already clear from their request):\n   - Should it search **all knowledge sources** or only **specific ones**?\n   - Should **general model knowledge** also be used, or only the configured knowledge sources?\n   - Should the response be **sent automatically** to chat, or **processed first** (e.g., custom formatting, adaptive card, combined with other data)?\n\n6. **Always precede `SearchAndSummarizeContent` with `CreateSearchQuery`** to preserve conversational context. Never pass `=System.Activity.Text` directly to `SearchAndSummarizeContent` — the raw last message may lack context (e.g., \"tell me more about that\"). `CreateSearchQuery` rewrites the input into an optimized search query. Access the result via `Topic.\u003CResultVar>.SearchQuery`.\n\n7. **Generate unique IDs** for all nodes (format: `\u003CnodeType>_\u003C6-8 random alphanumeric>`).\n\n8. **Build the YAML** using the appropriate pattern. For full YAML examples, see [patterns.md](patterns.md). For the complete property reference table, see [property-reference.md](property-reference.md).\n\n## SearchAndSummarizeContent vs AnswerQuestionWithAI\n\n| Node | Use When | Data Source | Output |\n|------|----------|-------------|--------|\n| `SearchAndSummarizeContent` | You want answers grounded in the agent's knowledge sources (websites, SharePoint, Dataverse) | Agent's configured knowledge | AI-summarized response |\n| `SearchKnowledgeSources` | You need verbatim\u002Fexact content — insurance policies, legal text, HR docs — where AI summarization could lose details | Agent's configured knowledge | Raw search results (no AI summary) |\n| `AnswerQuestionWithAI` | You want a response based only on conversation history and general model knowledge | No external data | AI-generated response |\n\n**Use `SearchAndSummarizeContent`** for the vast majority of cases (what people call \"generative answers\"). Use `SearchKnowledgeSources` when you need raw, unsummarized results for precision scenarios (pair with `CreateSearchQuery` for better search accuracy). Use `AnswerQuestionWithAI` only when you explicitly want the model to respond without consulting knowledge sources.\n\n## Knowledge Source References\n\nWhen using `knowledgeSources` to restrict the search to specific sources:\n\n1. The knowledge source **must already exist** in the agent (add it first with `\u002Fadd-knowledge`)\n2. Find the knowledge source filename in the agent's `knowledge\u002F` directory\n3. Reference it **without the `.mcs.yml` extension**\n\nExample: if the file is `cre3c_agent.topic.MyDocs_abc123.mcs.yml`, the reference is:\n```yaml\nknowledgeSources:\n  kind: SearchSpecificKnowledgeSources\n  knowledgeSources:\n    - cre3c_agent.topic.MyDocs_abc123\n```\n","# Add Generative Answers\n\nAdd `SearchAndSummarizeContent` nodes to generate responses grounded in the agent's knowledge sources.\n\n## Important: Do You Even Need a Topic?\n\nWhen knowledge sources are added to the agent (via `\u002Fadd-knowledge`), the AI can **directly search them without any topic** if it recognizes a QnA-style query. A dedicated topic with `SearchAndSummarizeContent` is useful when:\n- You want to **restrict the search to a subset of knowledge sources** (not all of them)\n- You want to **control the flow** around the answer (e.g., follow-up questions, formatting, adaptive cards)\n- You want to **process the response** before showing it (e.g., extract content, combine with other data)\n- You want to **use a specific input** other than the user's last message\n\nIf the user just wants the agent to answer questions from its knowledge, adding the knowledge source may be enough.\n\n## Instructions\n\n1. **Auto-discover the agent directory**:\n   ```\n   Glob: **\u002Fagent.mcs.yml\n   ```\n   NEVER hardcode an agent name.\n\n2. **Determine the approach** based on what the user needs:\n   - **Add to existing topic**: Read the target topic and insert a SearchAndSummarizeContent node\n   - **Create new search topic**: Generate a complete topic with the search pattern\n\n3. **Look up the schema** for both nodes:\n   ```bash\n   node ${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fschema-lookup.bundle.js resolve CreateSearchQuery\n   node ${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fschema-lookup.bundle.js resolve SearchAndSummarizeContent\n   ```\n\n4. **Read `settings.mcs.yml`** to check if `GenerativeActionsEnabled: true`. This determines the best pattern:\n   - **`GenerativeActionsEnabled: true`** → prefer **Pattern 2 (Orchestrator)**: use topic inputs\u002Foutputs and let the orchestrator handle the response. This is the best approach for generative-orchestrated agents.\n   - **`GenerativeActionsEnabled: false`** (or not set) → use **Pattern 1 (Direct Response)**: `autoSend: false` + manual SendActivity, or **Pattern 3 (Fallback Search)** for a simple all-knowledge fallback.\n   - **Verbatim\u002Fexact content needed** → use **Pattern 4 (Precision Search)**: `SearchKnowledgeSources` + `CreateSearchQuery` for raw results without AI summarization (insurance policies, HR docs, legal text).\n\n5. **Ask the user** to clarify the behavior (if not already clear from their request):\n   - Should it search **all knowledge sources** or only **specific ones**?\n   - Should **general model knowledge** also be used, or only the configured knowledge sources?\n   - Should the response be **sent automatically** to chat, or **processed first** (e.g., custom formatting, adaptive card, combined with other data)?\n\n6. **Always precede `SearchAndSummarizeContent` with `CreateSearchQuery`** to preserve conversational context. Never pass `=System.Activity.Text` directly to `SearchAndSummarizeContent` — the raw last message may lack context (e.g., \"tell me more about that\"). `CreateSearchQuery` rewrites the input into an optimized search query. Access the result via `Topic.\u003CResultVar>.SearchQuery`.\n\n7. **Generate unique IDs** for all nodes (format: `\u003CnodeType>_\u003C6-8 random alphanumeric>`).\n\n8. **Build the YAML** using the appropriate pattern. For full YAML examples, see [patterns.md](patterns.md). For the complete property reference table, see [property-reference.md](property-reference.md).\n\n## SearchAndSummarizeContent vs AnswerQuestionWithAI\n\n| Node | Use When | Data Source | Output |\n|------|----------|-------------|--------|\n| `SearchAndSummarizeContent` | You want answers grounded in the agent's knowledge sources (websites, SharePoint, Dataverse) | Agent's configured knowledge | AI-summarized response |\n| `SearchKnowledgeSources` | You need verbatim\u002Fexact content — insurance policies, legal text, HR docs — where AI summarization could lose details | Agent's configured knowledge | Raw search results (no AI summary) |\n| `AnswerQuestionWithAI` | You want a response based only on conversation history and general model knowledge | No external data | AI-generated response |\n\n**Use `SearchAndSummarizeContent`** for the vast majority of cases (what people call \"generative answers\"). Use `SearchKnowledgeSources` when you need raw, unsummarized results for precision scenarios (pair with `CreateSearchQuery` for better search accuracy). Use `AnswerQuestionWithAI` only when you explicitly want the model to respond without consulting knowledge sources.\n\n## Knowledge Source References\n\nWhen using `knowledgeSources` to restrict the search to specific sources:\n\n1. The knowledge source **must already exist** in the agent (add it first with `\u002Fadd-knowledge`)\n2. Find the knowledge source filename in the agent's `knowledge\u002F` directory\n3. Reference it **without the `.mcs.yml` extension**\n\nExample: if the file is `cre3c_agent.topic.MyDocs_abc123.mcs.yml`, the reference is:\n```yaml\nknowledgeSources:\n  kind: SearchSpecificKnowledgeSources\n  knowledgeSources:\n    - cre3c_agent.topic.MyDocs_abc123\n```\n",{"agent":25,"context":26,"description":7,"allowed-tools":27,"argument-hint":28,"user-invocable":21},"copilot-studio-author","fork","Bash(node *schema-lookup.bundle.js *), Read, Write, Edit, Glob","\u003Ctopic-name or \"new\">","main","9c42d3a612c6e06389b6e5b4eed579aaed1a8b63","skills\u002Fadd-generative-answers",103,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills-for-copilot-studio","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-12 17:03:17",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add microsoft\u002Fskills-for-copilot-studio --skill add-generative-answers",{"tool":44,"command":45},"bunx","bunx skills add microsoft\u002Fskills-for-copilot-studio --skill add-generative-answers",{"tool":47,"command":48},"pnpm","pnpm dlx skills add microsoft\u002Fskills-for-copilot-studio --skill add-generative-answers","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills-for-copilot-studio\u002Fblob\u002Fmain\u002Fskills\u002Fadd-generative-answers\u002FSKILL.md",true,[52,58],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"patterns.md","REFERENCE","参考文档",8318,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills-for-copilot-studio\u002Fblob\u002Fmain\u002Fskills\u002Fadd-generative-answers\u002Fpatterns.md",{"path":59,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":60,"sourceHtmlUrl":61},"property-reference.md",4657,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills-for-copilot-studio\u002Fblob\u002Fmain\u002Fskills\u002Fadd-generative-answers\u002Fproperty-reference.md",[63,75,93,102,113,122],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":74,"publishedAt":20},"01M699FD973RBVBTQYE48GBFPG","validate","Validate Copilot Studio agent YAML files using the LSP binary's full diagnostics (YAML structure, Power Fx, schema, cross-file references). Use when the user asks to check, validate, or verify YAML files.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills-for-copilot-studio\u002Fblob\u002Fmain\u002Fskills\u002Fvalidate\u002FSKILL.md",[69],{"categoryNo":70,"categoryName":71,"taxonomyType":72,"taxonomyTypeDesc":73},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[65],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":87,"publishedAt":20},"01M699FBJC22B4HCFH9MA844C3","test-auth","Authenticate for Copilot Studio evaluation API and SDK chat. Caches a token that is shared across run-eval and chat-sdk skills. Run this before any eval or SDK chat workflow. Requires an App Registration with MakerOperations and Copilots.Invoke permissions.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills-for-copilot-studio\u002Fblob\u002Fmain\u002Fskills\u002Ftest-auth\u002FSKILL.md",[81,84],{"categoryNo":82,"categoryName":83,"taxonomyType":72,"taxonomyTypeDesc":73},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":85,"categoryName":86,"taxonomyType":72,"taxonomyTypeDesc":73},"01JBSEEDCAT000000000000010","后端与接口",[88,89,90,91,92],"test","auth","test auth","sdk","workflow",{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":100,"publishedAt":20},"01M699FA38G1TAVA0JWD9DG783","run-tests-kit","Run a batch test suite via the Copilot Studio Kit (Dataverse API). Uses the Power CAT Copilot Studio Kit to execute test cases against a published agent and produces pass\u002Ffail results with latencies. Requires the Kit installed in the environment, an App Registration with Dataverse permissions, and a published agent.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills-for-copilot-studio\u002Fblob\u002Fmain\u002Fskills\u002Frun-tests-kit\u002FSKILL.md",[99],{"categoryNo":82,"categoryName":83,"taxonomyType":72,"taxonomyTypeDesc":73},[101,88],"run tests kit",{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":111,"publishedAt":20},"01M699F8EP4BZT1EA3R4Y40X98","run-eval","Run evaluations against a Copilot Studio agent via the Power Platform Evaluation API. Works on DRAFT agents — no publish step required. Lists test sets, starts a run, polls until complete, fetches results, and proposes YAML fixes for failures. Use when the user wants to test agent changes without publishing.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills-for-copilot-studio\u002Fblob\u002Fmain\u002Fskills\u002Frun-eval\u002FSKILL.md",[108,109,110],{"categoryNo":82,"categoryName":83,"taxonomyType":72,"taxonomyTypeDesc":73},{"categoryNo":85,"categoryName":86,"taxonomyType":72,"taxonomyTypeDesc":73},{"categoryNo":70,"categoryName":71,"taxonomyType":72,"taxonomyTypeDesc":73},[112,88],"run eval",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":120,"publishedAt":20},"01M699F6NR5Z4RTN5MWH5WYV9H","new-topic","Create a new Copilot Studio topic YAML file. Use when the user asks to create a new topic, conversation flow, or dialog for their agent.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills-for-copilot-studio\u002Fblob\u002Fmain\u002Fskills\u002Fnew-topic\u002FSKILL.md",[119],{"categoryNo":70,"categoryName":71,"taxonomyType":72,"taxonomyTypeDesc":73},[121],"new topic",{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":129,"publishedAt":20},"01M699F4QN5BMQA3X9F7WC1NS0","manage-agent","Push\u002Fpull Copilot Studio agent content via the VS Code extension's LanguageServerHost LSP binary. Handles authentication (interactive browser login for push\u002Fpull, device code flow for chat token), sync push, sync pull, clone, and diff operations.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills-for-copilot-studio\u002Fblob\u002Fmain\u002Fskills\u002Fmanage-agent\u002FSKILL.md",[128],{"categoryNo":70,"categoryName":71,"taxonomyType":72,"taxonomyTypeDesc":73},[130,89,131],"manage agent","sync"]