[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M699EXYSQJ282VEZ83XCMA21":3,"skill-same:01M699EXYSQJ282VEZ83XCMA21":50},{"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":21,"linkOnly":22,"markdownContent":23,"markdownBody":24,"frontMatter":25,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M699EXYSQJ282VEZ83XCMA21","int-project-context",null,"Shared project context for all Copilot Studio sub-agents. Provides project structure, schema lookup usage, and skill invocation guidance.","microsoft\u002Fskills-for-copilot-studio","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M699DXBD563FYBGWKPJJRAVM",492,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills-for-copilot-studio\u002Fblob\u002Fmain\u002Fskills\u002Fint-project-context\u002FSKILL.md",[],[19,20],"int project context","project structure","2026-11-10 10:12:30",false,"---\nname: int-project-context\ndescription: >\n  Shared project context for all Copilot Studio sub-agents. Provides project\n  structure, schema lookup usage, and skill invocation guidance.\nuser-invocable: false\n---\n\n# Copilot Studio — Shared Project Context\n\nYou are working inside a Copilot Studio agent project. All YAML files have the `.mcs.yml` extension.\n\n## Project Structure\n\n```\n\u003Cagent-dir>\u002F           # Auto-discover via Glob: **\u002Fagent.mcs.yml\n├── agent.mcs.yml      # Agent metadata (display name, schema version)\n├── settings.mcs.yml   # Agent settings (schemaName, GenerativeActionsEnabled, instructions)\n├── topics\u002F            # Conversation topics (AdaptiveDialog YAML files)\n├── actions\u002F           # Connector-based actions (TaskDialog YAML files)\n├── knowledge\u002F         # Knowledge sources (KnowledgeSourceConfiguration YAML files)\n├── variables\u002F         # Global variables (GlobalVariableComponent YAML files)\n└── agents\u002F            # Child agents (AgentDialog YAML files, each in its own subfolder)\n```\n\n## Schema Lookup Script\n\nWhen you write new YAML files, be sure to use the schema lookup script to understand the schema, including mandatory fields, definitions, and references. The script is located at `${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fschema-lookup.bundle.js`, and you can use it in the terminal as follows:\n\n```bash\nnode ${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fschema-lookup.bundle.js search trigger             # Search by keyword\nnode ${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fschema-lookup.bundle.js lookup SendActivity        # Look up a definition\nnode ${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fschema-lookup.bundle.js resolve AdaptiveDialog     # Resolve with $refs\nnode ${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fschema-lookup.bundle.js kinds                      # List all valid kind values\nnode ${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fschema-lookup.bundle.js summary Question           # Compact overview\nnode ${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fschema-lookup.bundle.js validate \u003Cfile.yml>        # Validate a YAML file\n```\n\nIf you already know the specific definition you want to look up, use `lookup`. If you want to explore the schema around a certain topic, use `search` or `summary`.\nAlways check the schema before writing YAML to ensure you include all required fields and use valid values.\n\n**NEVER load the full schema file** (`reference\u002Fbot.schema.yaml-authoring.json`) — it's too long. Always use the script above.\n\n## Connector Lookup Script\n\nThe connector lookup script is at `${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fconnector-lookup.bundle.js`. Use it for any questions about connectors, actions, their inputs, and outputs:\n\n```bash\nnode ${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fconnector-lookup.bundle.js list                                 # List all connectors with operation counts\nnode ${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fconnector-lookup.bundle.js operations \u003Cconnector>               # List operations for a connector\nnode ${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fconnector-lookup.bundle.js operation \u003Cconnector> \u003CoperationId>  # Full details of one operation (inputs\u002Foutputs)\nnode ${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fconnector-lookup.bundle.js search \u003Ckeyword>                     # Search operations across all connectors\n```\n\n`\u003Cconnector>` matches by API name (`shared_office365`) or partial display name (`outlook`).\n\n**When to use this**: When you need to understand available connectors, what inputs\u002Foutputs an action has, or what operations are available. The action YAML files in the agent only show *configured* inputs — connector-lookup shows the *full* connector definition with all available inputs and outputs.\n\n## Skill-First Rule (VERY IMPORTANT)\n\nYou have access to specialized skills that handle YAML creation, editing, validation, and testing. **ALWAYS invoke the matching skill instead of doing it manually.**\nSkills contain correct templates, schema validation, and patterns. Doing it manually risks hallucinated `kind:` values, missing required fields, and broken YAML.\nExample skills include `\u002Fcopilot-studio:new-topic` for creating new topics, `\u002Fcopilot-studio:add-action` for adding connector actions and tools, and `\u002Fcopilot-studio:validate` for validating YAML files.\n\n**If no skill matches**, only then work manually — but always validate with `\u002Fcopilot-studio:validate` afterward.\n\n## Key Conventions\n\n- **Agent Discovery**: NEVER hardcode agent names. Always `Glob: **\u002Fagent.mcs.yml`.\n- **ID Generation**: Random alphanumeric, 6-8 chars after prefix (e.g., `sendMessage_g5Ls09`).\n- **Template `_REPLACE`**: Always replace `_REPLACE` placeholder IDs with unique random IDs.\n- **Power Fx**: Expressions start with `=`. String interpolation uses `{}`. Only use supported functions (check `int-reference` skill).\n- **Generative Orchestration**: When `GenerativeActionsEnabled: true`, use topic inputs\u002Foutputs instead of hardcoded questions\u002Fmessages.\n","# Copilot Studio — Shared Project Context\n\nYou are working inside a Copilot Studio agent project. All YAML files have the `.mcs.yml` extension.\n\n## Project Structure\n\n```\n\u003Cagent-dir>\u002F           # Auto-discover via Glob: **\u002Fagent.mcs.yml\n├── agent.mcs.yml      # Agent metadata (display name, schema version)\n├── settings.mcs.yml   # Agent settings (schemaName, GenerativeActionsEnabled, instructions)\n├── topics\u002F            # Conversation topics (AdaptiveDialog YAML files)\n├── actions\u002F           # Connector-based actions (TaskDialog YAML files)\n├── knowledge\u002F         # Knowledge sources (KnowledgeSourceConfiguration YAML files)\n├── variables\u002F         # Global variables (GlobalVariableComponent YAML files)\n└── agents\u002F            # Child agents (AgentDialog YAML files, each in its own subfolder)\n```\n\n## Schema Lookup Script\n\nWhen you write new YAML files, be sure to use the schema lookup script to understand the schema, including mandatory fields, definitions, and references. The script is located at `${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fschema-lookup.bundle.js`, and you can use it in the terminal as follows:\n\n```bash\nnode ${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fschema-lookup.bundle.js search trigger             # Search by keyword\nnode ${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fschema-lookup.bundle.js lookup SendActivity        # Look up a definition\nnode ${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fschema-lookup.bundle.js resolve AdaptiveDialog     # Resolve with $refs\nnode ${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fschema-lookup.bundle.js kinds                      # List all valid kind values\nnode ${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fschema-lookup.bundle.js summary Question           # Compact overview\nnode ${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fschema-lookup.bundle.js validate \u003Cfile.yml>        # Validate a YAML file\n```\n\nIf you already know the specific definition you want to look up, use `lookup`. If you want to explore the schema around a certain topic, use `search` or `summary`.\nAlways check the schema before writing YAML to ensure you include all required fields and use valid values.\n\n**NEVER load the full schema file** (`reference\u002Fbot.schema.yaml-authoring.json`) — it's too long. Always use the script above.\n\n## Connector Lookup Script\n\nThe connector lookup script is at `${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fconnector-lookup.bundle.js`. Use it for any questions about connectors, actions, their inputs, and outputs:\n\n```bash\nnode ${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fconnector-lookup.bundle.js list                                 # List all connectors with operation counts\nnode ${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fconnector-lookup.bundle.js operations \u003Cconnector>               # List operations for a connector\nnode ${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fconnector-lookup.bundle.js operation \u003Cconnector> \u003CoperationId>  # Full details of one operation (inputs\u002Foutputs)\nnode ${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fconnector-lookup.bundle.js search \u003Ckeyword>                     # Search operations across all connectors\n```\n\n`\u003Cconnector>` matches by API name (`shared_office365`) or partial display name (`outlook`).\n\n**When to use this**: When you need to understand available connectors, what inputs\u002Foutputs an action has, or what operations are available. The action YAML files in the agent only show *configured* inputs — connector-lookup shows the *full* connector definition with all available inputs and outputs.\n\n## Skill-First Rule (VERY IMPORTANT)\n\nYou have access to specialized skills that handle YAML creation, editing, validation, and testing. **ALWAYS invoke the matching skill instead of doing it manually.**\nSkills contain correct templates, schema validation, and patterns. Doing it manually risks hallucinated `kind:` values, missing required fields, and broken YAML.\nExample skills include `\u002Fcopilot-studio:new-topic` for creating new topics, `\u002Fcopilot-studio:add-action` for adding connector actions and tools, and `\u002Fcopilot-studio:validate` for validating YAML files.\n\n**If no skill matches**, only then work manually — but always validate with `\u002Fcopilot-studio:validate` afterward.\n\n## Key Conventions\n\n- **Agent Discovery**: NEVER hardcode agent names. Always `Glob: **\u002Fagent.mcs.yml`.\n- **ID Generation**: Random alphanumeric, 6-8 chars after prefix (e.g., `sendMessage_g5Ls09`).\n- **Template `_REPLACE`**: Always replace `_REPLACE` placeholder IDs with unique random IDs.\n- **Power Fx**: Expressions start with `=`. String interpolation uses `{}`. Only use supported functions (check `int-reference` skill).\n- **Generative Orchestration**: When `GenerativeActionsEnabled: true`, use topic inputs\u002Foutputs instead of hardcoded questions\u002Fmessages.\n",{"name":5,"description":26,"user-invocable":22},"Shared project context for all Copilot Studio sub-agents. Provides project structure, schema lookup usage, and skill invocation guidance.\n","main","9c42d3a612c6e06389b6e5b4eed579aaed1a8b63","skills\u002Fint-project-context",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":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add microsoft\u002Fskills-for-copilot-studio --skill int-project-context",{"tool":42,"command":43},"bunx","bunx skills add microsoft\u002Fskills-for-copilot-studio --skill int-project-context",{"tool":45,"command":46},"pnpm","pnpm dlx skills add microsoft\u002Fskills-for-copilot-studio --skill int-project-context","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills-for-copilot-studio\u002Fblob\u002Fmain\u002Fskills\u002Fint-project-context\u002FSKILL.md",true,[],[51,63,81,90,101,110],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":62,"publishedAt":21},"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",[57],{"categoryNo":58,"categoryName":59,"taxonomyType":60,"taxonomyTypeDesc":61},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[53],{"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":75,"publishedAt":21},"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",[69,72],{"categoryNo":70,"categoryName":71,"taxonomyType":60,"taxonomyTypeDesc":61},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":73,"categoryName":74,"taxonomyType":60,"taxonomyTypeDesc":61},"01JBSEEDCAT000000000000010","后端与接口",[76,77,78,79,80],"test","auth","test auth","sdk","workflow",{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":88,"publishedAt":21},"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",[87],{"categoryNo":70,"categoryName":71,"taxonomyType":60,"taxonomyTypeDesc":61},[89,76],"run tests kit",{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":99,"publishedAt":21},"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",[96,97,98],{"categoryNo":70,"categoryName":71,"taxonomyType":60,"taxonomyTypeDesc":61},{"categoryNo":73,"categoryName":74,"taxonomyType":60,"taxonomyTypeDesc":61},{"categoryNo":58,"categoryName":59,"taxonomyType":60,"taxonomyTypeDesc":61},[100,76],"run eval",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":108,"publishedAt":21},"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",[107],{"categoryNo":58,"categoryName":59,"taxonomyType":60,"taxonomyTypeDesc":61},[109],"new topic",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":117,"publishedAt":21},"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",[116],{"categoryNo":58,"categoryName":59,"taxonomyType":60,"taxonomyTypeDesc":61},[118,77,119],"manage agent","sync"]