[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69B2W1NZHQ9HP1EHZJSG1QC":3,"skill-same:01M69B2W1NZHQ9HP1EHZJSG1QC":145},{"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":23,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":56,"ownerHtmlUrl":57,"ownerBlogUrl":58,"ownerDescription":59,"updatedAt":60,"install":61,"resources":74},"01M69B2W1NZHQ9HP1EHZJSG1QC","m365-agent-evaluator",null,"Use this skill when a user wants to create, run, or analyze evaluation suites for Microsoft 365 Copilot declarative agents with the public @microsoft\u002Fm365-copilot-eval CLI. Trigger on intents such as \"evaluate my agent\", \"test my agent\", \"run my evals\", \"create eval prompts\", \"add multi-turn tests\", \"tune evaluator thresholds\", \"why is my agent failing\", or \"set up eval environment variables\".","microsoft\u002Fskills","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M69AJYYW4E1RMSYCQDJ4FJSH",3204,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fmicrosoft-365-agents-toolkit\u002Fskills\u002Fm365-agent-evaluator\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,9,45],"agent evaluator","m365 agent evaluator","evaluator","m365","SET","failing","when","my","Variables","up","eval","analyze","why","cli","Evaluation","declarative agents","run","create","microsoft 365 copilot","copilot","create eval","test","2026-11-10 10:12:30",false,"---\nname: m365-agent-evaluator\ndescription: >\n  Use this skill when a user wants to create, run, or analyze evaluation suites for Microsoft 365 Copilot declarative agents with the public @microsoft\u002Fm365-copilot-eval CLI. Trigger on intents such as \"evaluate my agent\", \"test my agent\", \"run my evals\", \"create eval prompts\", \"add multi-turn tests\", \"tune evaluator thresholds\", \"why is my agent failing\", or \"set up eval environment variables\".\n---\n\n# M365 Agent Evaluator\n\nUse this skill to help users evaluate Microsoft 365 Copilot declarative agents with `@microsoft\u002Fm365-copilot-eval`. The skill designs schema-compatible eval datasets, runs the public preview CLI, analyzes results, and recommends targeted fixes.\n\nDefault to Microsoft 365 Agents Toolkit (ATK) projects when detected, but do not hard-stop solely because the current directory is not ATK. The CLI can also evaluate deployed agents with an explicit `M365_AGENT_ID` or `--m365-agent-id`.\n\n## Always use this CLI invocation\n\n```powershell\nnpx -y --package @microsoft\u002Fm365-copilot-eval@latest runevals\n```\n\nDo not recommend the old private `aka.ms` installer, global installs, bare `runevals`, bare `npx runevals`, `--input`, or `--html`.\n\n## Activation workflow\n\n1. Identify the user goal: setup, dataset authoring, running evals, analyzing results, or updating an existing eval suite.\n2. Load only the reference needed for the current goal:\n   - `references\u002Fworkflow.md` for the end-to-end operator workflow and CLI commands.\n   - `references\u002Fazure-setup.md` for prerequisites, env files, and secret handling.\n   - `references\u002Feval-templates.md` when creating or editing eval datasets.\n   - `references\u002Fpra-framework.md` when deciding what scenarios to generate.\n   - `references\u002Fresult-analysis.md` after JSON\u002FCSV\u002FHTML results exist.\n   - `references\u002Fguardrails.md` before writing files, handling secrets, clearing cache, signing out, or troubleshooting.\n3. Detect project shape:\n   - ATK: `.env.local`, `.env.local.user`, `env\\.env.local.user`, `m365agents.yml`, or `appPackage\\declarativeAgent.json`.\n   - Non-ATK: an eval dataset plus `M365_AGENT_ID`, `--m365-agent-id`, or a named environment file such as `env\\.env.dev`.\n4. Verify prerequisites without exposing values:\n   - Node.js 24.12.0 or newer.\n   - Microsoft 365 Copilot license and a deployed M365 Copilot agent.\n   - Tenant admin consent for the WorkIQ Client App.\n   - `TENANT_ID`, Azure OpenAI in Foundry Models endpoint\u002Fkey, and recommended\u002Fdefault `gpt-4o-mini` deployment.\n5. Choose the workflow:\n   - No dataset: create `evals\\evals.json`.\n   - Existing dataset: run, analyze prior results, or propose changes.\n   - Quick check: use inline prompts.\n   - Exploration: use interactive mode.\n\n## Current dataset contract\n\nGenerate schema version `1.2.0` documents with a root `items` array. Do not generate the old `PromptsObject` or root `prompts` format.\n\nMinimum shape:\n\n```json\n{\n  \"schemaVersion\": \"1.2.0\",\n  \"metadata\": {\n    \"name\": \"Agent evaluation suite\",\n    \"tags\": [\"starter\"]\n  },\n  \"default_evaluators\": {\n    \"Relevance\": {},\n    \"Coherence\": {}\n  },\n  \"items\": [\n    {\n      \"prompt\": \"What can this agent help me with?\",\n      \"expected_response\": \"The agent explains its supported scope without inventing unsupported capabilities.\"\n    }\n  ]\n}\n```\n\nUse `references\\prompts-schema.json` as the local schema source and `references\\eval-templates.md` for copyable single-turn, multi-turn, evaluator, and threshold examples.\n\n## Public evaluator names\n\nEvaluator names are case-sensitive. Use only the public configurable evaluator names unless a newer authoritative source proves otherwise.\n\n| Evaluator | Semantics |\n|---|---|\n| `Relevance` | LLM score from 1-5; default threshold 3. |\n| `Coherence` | LLM score from 1-5; default threshold 3. |\n| `Groundedness` | LLM score from 1-5 against `context`\u002Fexpected evidence; default threshold 3. |\n| `Similarity` | LLM score from 1-5 against `expected_response`; default threshold 3. |\n| `Citations` | Count-based citation check; default threshold 1. |\n| `ExactMatch` | Boolean exact string match. |\n| `PartialMatch` | String similarity from 0.0-1.0; default threshold 0.5. |\n\nTreat `ToolCallAccuracy` as legacy\u002Fprivate for authoring. Do not add it to generated datasets unless current public CLI\u002Fschema documentation explicitly reintroduces it.\n\n## Common commands\n\n```powershell\n# Version\u002Fhelp checks\nnpx -y --package @microsoft\u002Fm365-copilot-eval@latest runevals --version\nnpx -y --package @microsoft\u002Fm365-copilot-eval@latest runevals --help\n\n# First-time setup \u002F EULA\nnpx -y --package @microsoft\u002Fm365-copilot-eval@latest runevals accept-eula\nnpx -y --package @microsoft\u002Fm365-copilot-eval@latest runevals --init-only\n\n# Batch run with explicit JSON output\nnpx -y --package @microsoft\u002Fm365-copilot-eval@latest runevals --prompts-file evals\\evals.json --output .evals\\results.json\n\n# Human-review HTML or spreadsheet-friendly CSV\nnpx -y --package @microsoft\u002Fm365-copilot-eval@latest runevals --prompts-file evals\\evals.json --output .evals\\results.html\nnpx -y --package @microsoft\u002Fm365-copilot-eval@latest runevals --prompts-file evals\\evals.json --output .evals\\results.csv\n\n# Quick checks\nnpx -y --package @microsoft\u002Fm365-copilot-eval@latest runevals --prompts \"What can you help me with?\" --expected \"The agent describes its supported scope.\"\n\n# Non-ATK or named environment\nnpx -y --package @microsoft\u002Fm365-copilot-eval@latest runevals --prompts-file evals\\evals.json --m365-agent-id \u003Cagent-id> --env dev\n```\n\nUse `--concurrency` only with values 1-5. Start with `1` for debugging and increase only after setup is stable.\n\n## Version and PATH safety\n\nBefore diagnosing agent behavior, confirm which executable is running:\n\n```powershell\nGet-Command runevals -All\nnpm list -g @microsoft\u002Fm365-copilot-eval --depth=0\nnpm view @microsoft\u002Fm365-copilot-eval version\nnpx -y --package @microsoft\u002Fm365-copilot-eval@latest runevals --version\nnpx -y --package @microsoft\u002Fm365-copilot-eval@latest where runevals\n```\n\nIf bare `runevals` prints `This version of the M365 Evals CLI has stopped working and must be updated`, treat it as a stale PATH\u002Fglobal install. Re-run with the `npx --package ...@latest` command above, then ask before removing global shims with `npm uninstall -g @microsoft\u002Fm365-copilot-eval`.\n\n## File conventions\n\n| Path | Purpose |\n|---|---|\n| `.env.local` | Non-secret ATK config such as `M365_TITLE_ID`. |\n| `.env.local.user` or `env\\.env.local.user` | Local secrets such as tenant ID and Azure OpenAI key. |\n| `env\\.env.\u003Cenvironment>` | Named environment config for non-ATK or explicit `--env` workflows. |\n| `evals\\evals.json` | Source-controlled eval dataset if the user wants it committed. |\n| `.evals\\` | Local run outputs; usually gitignored. |\n\nNever print or commit secrets, prompts containing sensitive data, retrieved content, debug logs, or raw result files unless the user explicitly asks and confirms the data is safe to share.\n\n## Generation guidance\n\nUse PRA as a scenario-design framework:\n\n- Perceive: retrieval, grounding, and source coverage.\n- Reason: instruction adherence, synthesis, ambiguity handling, and refusal behavior.\n- Act: declared capability\u002Faction behavior. Score with public evaluators such as `Relevance`, `Coherence`, `Similarity`, `ExactMatch`, or `PartialMatch`; do not use legacy `ToolCallAccuracy`.\n\nAsk before overwriting an existing dataset. When writing generated evals, write to a temporary file first and rename on success.\n\n## Result analysis guidance\n\nAnalyze only evaluator keys that are present. Missing score keys usually mean the evaluator was not configured for that item, not that it failed.\n\nUse current score keys when present: `relevance`, `coherence`, `groundedness`, `similarity`, `citations`, `exactMatch`, and `partialMatch`. Group failures into likely root causes: instruction issue, grounding issue, citation issue, expected-answer mismatch, capability gap, auth\u002Fenvironment issue, or eval-quality issue.\n\nDo not run real tenant-dependent evals unless the user has provided or approved the necessary tenant, agent, and Azure OpenAI configuration.\n","# M365 Agent Evaluator\n\nUse this skill to help users evaluate Microsoft 365 Copilot declarative agents with `@microsoft\u002Fm365-copilot-eval`. The skill designs schema-compatible eval datasets, runs the public preview CLI, analyzes results, and recommends targeted fixes.\n\nDefault to Microsoft 365 Agents Toolkit (ATK) projects when detected, but do not hard-stop solely because the current directory is not ATK. The CLI can also evaluate deployed agents with an explicit `M365_AGENT_ID` or `--m365-agent-id`.\n\n## Always use this CLI invocation\n\n```powershell\nnpx -y --package @microsoft\u002Fm365-copilot-eval@latest runevals\n```\n\nDo not recommend the old private `aka.ms` installer, global installs, bare `runevals`, bare `npx runevals`, `--input`, or `--html`.\n\n## Activation workflow\n\n1. Identify the user goal: setup, dataset authoring, running evals, analyzing results, or updating an existing eval suite.\n2. Load only the reference needed for the current goal:\n   - `references\u002Fworkflow.md` for the end-to-end operator workflow and CLI commands.\n   - `references\u002Fazure-setup.md` for prerequisites, env files, and secret handling.\n   - `references\u002Feval-templates.md` when creating or editing eval datasets.\n   - `references\u002Fpra-framework.md` when deciding what scenarios to generate.\n   - `references\u002Fresult-analysis.md` after JSON\u002FCSV\u002FHTML results exist.\n   - `references\u002Fguardrails.md` before writing files, handling secrets, clearing cache, signing out, or troubleshooting.\n3. Detect project shape:\n   - ATK: `.env.local`, `.env.local.user`, `env\\.env.local.user`, `m365agents.yml`, or `appPackage\\declarativeAgent.json`.\n   - Non-ATK: an eval dataset plus `M365_AGENT_ID`, `--m365-agent-id`, or a named environment file such as `env\\.env.dev`.\n4. Verify prerequisites without exposing values:\n   - Node.js 24.12.0 or newer.\n   - Microsoft 365 Copilot license and a deployed M365 Copilot agent.\n   - Tenant admin consent for the WorkIQ Client App.\n   - `TENANT_ID`, Azure OpenAI in Foundry Models endpoint\u002Fkey, and recommended\u002Fdefault `gpt-4o-mini` deployment.\n5. Choose the workflow:\n   - No dataset: create `evals\\evals.json`.\n   - Existing dataset: run, analyze prior results, or propose changes.\n   - Quick check: use inline prompts.\n   - Exploration: use interactive mode.\n\n## Current dataset contract\n\nGenerate schema version `1.2.0` documents with a root `items` array. Do not generate the old `PromptsObject` or root `prompts` format.\n\nMinimum shape:\n\n```json\n{\n  \"schemaVersion\": \"1.2.0\",\n  \"metadata\": {\n    \"name\": \"Agent evaluation suite\",\n    \"tags\": [\"starter\"]\n  },\n  \"default_evaluators\": {\n    \"Relevance\": {},\n    \"Coherence\": {}\n  },\n  \"items\": [\n    {\n      \"prompt\": \"What can this agent help me with?\",\n      \"expected_response\": \"The agent explains its supported scope without inventing unsupported capabilities.\"\n    }\n  ]\n}\n```\n\nUse `references\\prompts-schema.json` as the local schema source and `references\\eval-templates.md` for copyable single-turn, multi-turn, evaluator, and threshold examples.\n\n## Public evaluator names\n\nEvaluator names are case-sensitive. Use only the public configurable evaluator names unless a newer authoritative source proves otherwise.\n\n| Evaluator | Semantics |\n|---|---|\n| `Relevance` | LLM score from 1-5; default threshold 3. |\n| `Coherence` | LLM score from 1-5; default threshold 3. |\n| `Groundedness` | LLM score from 1-5 against `context`\u002Fexpected evidence; default threshold 3. |\n| `Similarity` | LLM score from 1-5 against `expected_response`; default threshold 3. |\n| `Citations` | Count-based citation check; default threshold 1. |\n| `ExactMatch` | Boolean exact string match. |\n| `PartialMatch` | String similarity from 0.0-1.0; default threshold 0.5. |\n\nTreat `ToolCallAccuracy` as legacy\u002Fprivate for authoring. Do not add it to generated datasets unless current public CLI\u002Fschema documentation explicitly reintroduces it.\n\n## Common commands\n\n```powershell\n# Version\u002Fhelp checks\nnpx -y --package @microsoft\u002Fm365-copilot-eval@latest runevals --version\nnpx -y --package @microsoft\u002Fm365-copilot-eval@latest runevals --help\n\n# First-time setup \u002F EULA\nnpx -y --package @microsoft\u002Fm365-copilot-eval@latest runevals accept-eula\nnpx -y --package @microsoft\u002Fm365-copilot-eval@latest runevals --init-only\n\n# Batch run with explicit JSON output\nnpx -y --package @microsoft\u002Fm365-copilot-eval@latest runevals --prompts-file evals\\evals.json --output .evals\\results.json\n\n# Human-review HTML or spreadsheet-friendly CSV\nnpx -y --package @microsoft\u002Fm365-copilot-eval@latest runevals --prompts-file evals\\evals.json --output .evals\\results.html\nnpx -y --package @microsoft\u002Fm365-copilot-eval@latest runevals --prompts-file evals\\evals.json --output .evals\\results.csv\n\n# Quick checks\nnpx -y --package @microsoft\u002Fm365-copilot-eval@latest runevals --prompts \"What can you help me with?\" --expected \"The agent describes its supported scope.\"\n\n# Non-ATK or named environment\nnpx -y --package @microsoft\u002Fm365-copilot-eval@latest runevals --prompts-file evals\\evals.json --m365-agent-id \u003Cagent-id> --env dev\n```\n\nUse `--concurrency` only with values 1-5. Start with `1` for debugging and increase only after setup is stable.\n\n## Version and PATH safety\n\nBefore diagnosing agent behavior, confirm which executable is running:\n\n```powershell\nGet-Command runevals -All\nnpm list -g @microsoft\u002Fm365-copilot-eval --depth=0\nnpm view @microsoft\u002Fm365-copilot-eval version\nnpx -y --package @microsoft\u002Fm365-copilot-eval@latest runevals --version\nnpx -y --package @microsoft\u002Fm365-copilot-eval@latest where runevals\n```\n\nIf bare `runevals` prints `This version of the M365 Evals CLI has stopped working and must be updated`, treat it as a stale PATH\u002Fglobal install. Re-run with the `npx --package ...@latest` command above, then ask before removing global shims with `npm uninstall -g @microsoft\u002Fm365-copilot-eval`.\n\n## File conventions\n\n| Path | Purpose |\n|---|---|\n| `.env.local` | Non-secret ATK config such as `M365_TITLE_ID`. |\n| `.env.local.user` or `env\\.env.local.user` | Local secrets such as tenant ID and Azure OpenAI key. |\n| `env\\.env.\u003Cenvironment>` | Named environment config for non-ATK or explicit `--env` workflows. |\n| `evals\\evals.json` | Source-controlled eval dataset if the user wants it committed. |\n| `.evals\\` | Local run outputs; usually gitignored. |\n\nNever print or commit secrets, prompts containing sensitive data, retrieved content, debug logs, or raw result files unless the user explicitly asks and confirms the data is safe to share.\n\n## Generation guidance\n\nUse PRA as a scenario-design framework:\n\n- Perceive: retrieval, grounding, and source coverage.\n- Reason: instruction adherence, synthesis, ambiguity handling, and refusal behavior.\n- Act: declared capability\u002Faction behavior. Score with public evaluators such as `Relevance`, `Coherence`, `Similarity`, `ExactMatch`, or `PartialMatch`; do not use legacy `ToolCallAccuracy`.\n\nAsk before overwriting an existing dataset. When writing generated evals, write to a temporary file first and rename on success.\n\n## Result analysis guidance\n\nAnalyze only evaluator keys that are present. Missing score keys usually mean the evaluator was not configured for that item, not that it failed.\n\nUse current score keys when present: `relevance`, `coherence`, `groundedness`, `similarity`, `citations`, `exactMatch`, and `partialMatch`. Group failures into likely root causes: instruction issue, grounding issue, citation issue, expected-answer mismatch, capability gap, auth\u002Fenvironment issue, or eval-quality issue.\n\nDo not run real tenant-dependent evals unless the user has provided or approved the necessary tenant, agent, and Azure OpenAI configuration.\n",{"name":5,"description":7},"main","3f5b461b2314e01c400564051e92469114c5b68f",".github\u002Fplugins\u002Fmicrosoft-365-agents-toolkit\u002Fskills\u002Fm365-agent-evaluator",368,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills","https:\u002F\u002Fmicrosoft.github.io\u002Fskills\u002F","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-14 06:48:25",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add microsoft\u002Fskills --skill m365-agent-evaluator",{"tool":67,"command":68},"bunx","bunx skills add microsoft\u002Fskills --skill m365-agent-evaluator",{"tool":70,"command":71},"pnpm","pnpm dlx skills add microsoft\u002Fskills --skill m365-agent-evaluator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fmicrosoft-365-agents-toolkit\u002Fskills\u002Fm365-agent-evaluator\u002FSKILL.md",true,[75,81,85,89,93,97,101,105,109,113,117,121,125,129,133,137,141],{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"examples\u002Fanalyze-failures.md","REFERENCE","参考文档",1507,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fmicrosoft-365-agents-toolkit\u002Fskills\u002Fm365-agent-evaluator\u002Fexamples\u002Fanalyze-failures.md",{"path":82,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":83,"sourceHtmlUrl":84},"examples\u002Fbasic-generation.md",1822,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fmicrosoft-365-agents-toolkit\u002Fskills\u002Fm365-agent-evaluator\u002Fexamples\u002Fbasic-generation.md",{"path":86,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":87,"sourceHtmlUrl":88},"examples\u002Fiterate-on-changes.md",1302,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fmicrosoft-365-agents-toolkit\u002Fskills\u002Fm365-agent-evaluator\u002Fexamples\u002Fiterate-on-changes.md",{"path":90,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":91,"sourceHtmlUrl":92},"examples\u002Fmissing-instructions.md",1581,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fmicrosoft-365-agents-toolkit\u002Fskills\u002Fm365-agent-evaluator\u002Fexamples\u002Fmissing-instructions.md",{"path":94,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":95,"sourceHtmlUrl":96},"examples\u002Fnot-atk-project.md",1452,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fmicrosoft-365-agents-toolkit\u002Fskills\u002Fm365-agent-evaluator\u002Fexamples\u002Fnot-atk-project.md",{"path":98,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":99,"sourceHtmlUrl":100},"examples\u002Frun-and-analyze.md",1660,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fmicrosoft-365-agents-toolkit\u002Fskills\u002Fm365-agent-evaluator\u002Fexamples\u002Frun-and-analyze.md",{"path":102,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":103,"sourceHtmlUrl":104},"references\u002Fazure-setup.md",5927,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fmicrosoft-365-agents-toolkit\u002Fskills\u002Fm365-agent-evaluator\u002Freferences\u002Fazure-setup.md",{"path":106,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":107,"sourceHtmlUrl":108},"references\u002Feval-templates.md",5176,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fmicrosoft-365-agents-toolkit\u002Fskills\u002Fm365-agent-evaluator\u002Freferences\u002Feval-templates.md",{"path":110,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":111,"sourceHtmlUrl":112},"references\u002Fguardrails.md",4221,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fmicrosoft-365-agents-toolkit\u002Fskills\u002Fm365-agent-evaluator\u002Freferences\u002Fguardrails.md",{"path":114,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":115,"sourceHtmlUrl":116},"references\u002Foutput-schema.json",4051,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fmicrosoft-365-agents-toolkit\u002Fskills\u002Fm365-agent-evaluator\u002Freferences\u002Foutput-schema.json",{"path":118,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":119,"sourceHtmlUrl":120},"references\u002Foutput-schema.md",2711,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fmicrosoft-365-agents-toolkit\u002Fskills\u002Fm365-agent-evaluator\u002Freferences\u002Foutput-schema.md",{"path":122,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":123,"sourceHtmlUrl":124},"references\u002Fpra-framework.md",3319,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fmicrosoft-365-agents-toolkit\u002Fskills\u002Fm365-agent-evaluator\u002Freferences\u002Fpra-framework.md",{"path":126,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":127,"sourceHtmlUrl":128},"references\u002Fprofiling-tools.md",9988,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002F_collections\u002Frsmdt-the-startup\u002Fplugins\u002Fteam\u002Fskills\u002Fquality\u002Fperformance-analysis\u002Freferences\u002Fprofiling-tools.md",{"path":130,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":131,"sourceHtmlUrl":132},"references\u002Fprompts-schema.json",15760,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fmicrosoft-365-agents-toolkit\u002Fskills\u002Fm365-agent-evaluator\u002Freferences\u002Fprompts-schema.json",{"path":134,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":135,"sourceHtmlUrl":136},"references\u002Fremediation-patterns.md",3675,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fmicrosoft-365-agents-toolkit\u002Fskills\u002Fm365-agent-evaluator\u002Freferences\u002Fremediation-patterns.md",{"path":138,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":139,"sourceHtmlUrl":140},"references\u002Fresult-analysis.md",4514,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fmicrosoft-365-agents-toolkit\u002Fskills\u002Fm365-agent-evaluator\u002Freferences\u002Fresult-analysis.md",{"path":142,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":143,"sourceHtmlUrl":144},"references\u002Fworkflow.md",6623,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fmicrosoft-365-agents-toolkit\u002Fskills\u002Fm365-agent-evaluator\u002Freferences\u002Fworkflow.md",[146,154,179,217,243,264],{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":152,"publishedAt":153},"01M741JBE1VH8A2Y3FXX2P7386","azure-advisor-cost-optimization","Analyze Azure Advisor Cost\u002FIdleResources findings and prevalidate deletion safety, including Service Groups. WHEN: \"find unused Azure resources\", \"what resources am I paying for but no longer using\", \"idle-resource savings\", \"historical idle-resource savings\", \"are these idle resources safe to delete\". Generic Cost, other subcategories, and cross-category requests use azure-advisor.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-advisor\u002Fskills\u002Fazure-advisor-cost-optimization\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":161,"publishedAt":46},"01M69B4JCRQV5SPXAFCKXQRV0H","skill-creator","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.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fskill-creator\u002FSKILL.md",[160],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[162,163,164,165,9,166,167,168,169,170,171,172,173,174,175,30,176,177,178],"skill creator","creator","ai coding agents","coding agents","azure","foundry","microsoft foundry","coding","guide","for","use","Existing","services","new","sdks","with","ai coding",{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":195,"publishedAt":46},"01M69B4FD57V1MYKRWAJJECTZ7","podcast-generation","Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket. Use when building text-to-speech features, audio narrative generation, podcast creation from content, or integrating with Azure OpenAI Realtime API for real audio output. Covers full-stack implementation from React frontend to Python FastAPI backend with WebSocket streaming.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fpodcast-generation\u002FSKILL.md",[185,188,191,194],{"categoryNo":186,"categoryName":187,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":189,"categoryName":190,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":192,"categoryName":193,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[196,197,198,199,166,200,201,202,203,204,205,206,207,208,209,30,210,211,212,213,214,215,216],"podcast generation","generation","podcast","frontend","azure openai","realtime","react","python","Audio","creation","model","fastapi backend","python fastapi","fastapi","api","streaming","text","narrative","stack","generate","features",{"skillNo":218,"name":219,"nameZh":6,"description":220,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":221,"categories":222,"keywords":224,"publishedAt":46},"01M69B4CYPM5SESY5ZWEFDXEQZ","microsoft-docs","Understand Microsoft technologies by querying official documentation. Use whenever the user asks how something works, wants tutorials, needs configuration options, limits, quotas, or best practices for any Microsoft technology (Azure, .NET, M365, Windows, Power Platform, etc.)—even if they don't mention \"docs.\" If the question is about understanding a concept rather than writing code, this is the right skill.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fmicrosoft-docs\u002FSKILL.md",[223],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[225,9,226,227,228,229,37,166,230,231,232,233,234,235,236,237,171,238,64,239,172,240,241,242],"microsoft docs","docs","documentation","windows","official","MCP","writing","power platform","mcp server","back","concept","power","platform","technology","question","learn mcp","learn","best practices",{"skillNo":244,"name":245,"nameZh":6,"description":246,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":247,"categories":248,"keywords":250,"publishedAt":46},"01M69B49C3YPD1ZJ3NC0HPCY58","mcp-builder","Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP), Node\u002FTypeScript (MCP SDK), or C#\u002F.NET (Microsoft MCP SDK).","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fmcp-builder\u002FSKILL.md",[249],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[251,230,252,253,254,9,203,255,256,206,257,30,258,259,260,170,261,262,171,263,172,177],"mcp builder","builder","llms","sdk","typescript","model context protocol","building mcp servers","node","integrate","Tools","context","fastmcp","mcp sdk",{"skillNo":265,"name":266,"nameZh":6,"description":267,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":268,"categories":269,"keywords":282,"publishedAt":46},"01M69B467A7CDMFQ0T6Q0ZA12Q","kql","KQL language expertise for writing correct, efficient Kusto Query Language queries. Covers syntax gotchas, join patterns, dynamic types, datetime pitfalls, regex patterns, serialization, memory management, result-size discipline, and advanced functions (geo, vector, graph). USE THIS SKILL whenever writing, debugging, or reviewing KQL queries — even simple ones — because the gotchas section prevents the most common errors that waste tool calls and cause expensive retry cascades. Trigger on: KQL, Kusto, ADX, Azure Data Explorer, Fabric Real-Time Intelligence, EventHouse, Log Analytics, log analysis, data exploration, time series, anomaly detection, summarize, where clause, join, extend, project, let statement, parse operator, extract function, any mention of pipe-forward query syntax.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fkql\u002FSKILL.md",[270,273,274,279],{"categoryNo":271,"categoryName":272,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":275,"categoryName":276,"taxonomyType":277,"taxonomyTypeDesc":278},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",{"categoryNo":280,"categoryName":281,"taxonomyType":277,"taxonomyTypeDesc":278},"01JBSEEDCAT000000000000036","内容创作者",[266,166,231,283,284,285,286,287,288,289,290,291,292,293,294,295,296,297,298,171,299,300,301],"analytics","memory","summarize","exploration","parse","project","time","vector","join","log","pipe","datetime","discipline","time series","regex","anomaly","section","tool","geo"]