[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-azure-pagerduty":3,"mdc-wm5x8t-key":38,"related-repo-azure-pagerduty":563,"related-org-azure-pagerduty":678},{"slug":4,"name":5,"fn":6,"description":7,"org":8,"tags":13,"stars":27,"repoUrl":28,"updatedAt":29,"license":30,"forks":31,"topics":32,"repo":33,"sourceUrl":36,"mdContent":37},"pagerduty","pager_duty","manage incidents with PagerDuty","Load this skill for expertise in PagerDuty's incident management platform including incidents, on-call schedules, services, teams, escalation policies, event orchestration, incident workflows, and status pages. Use for managing incidents, checking on-call status, investigating alerts, escalating issues, and navigating PagerDuty data via the PagerDuty MCP server.",{"slug":9,"name":10,"logoUrl":11,"githubOrg":12},"azure","Azure (Microsoft)","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fazure.png","Azure",[14,18,21,24],{"name":15,"slug":16,"type":17},"SRE","sre","tag",{"name":19,"slug":20,"type":17},"Alerting","alerting",{"name":22,"slug":23,"type":17},"Monitoring","monitoring",{"name":25,"slug":26,"type":17},"Incident Response","incident-response",2,"https:\u002F\u002Fgithub.com\u002FAzure\u002Fsre-agent-plugins","2026-07-12T08:20:44.017673",null,5,[],{"repoUrl":28,"stars":27,"forks":31,"topics":34,"description":35},[],"Azure SRE Agent Plugins","https:\u002F\u002Fgithub.com\u002FAzure\u002Fsre-agent-plugins\u002Ftree\u002FHEAD\u002Fplugins\u002Fpager-duty\u002Fskills\u002Fpager_duty","---\nname: pager_duty\ndescription: Load this skill for expertise in PagerDuty's incident management platform including incidents, on-call schedules, services, teams, escalation policies, event orchestration, incident workflows, and status pages. Use for managing incidents, checking on-call status, investigating alerts, escalating issues, and navigating PagerDuty data via the PagerDuty MCP server.\n---\n\n# PagerDuty Incident Management for Azure Resources\n\n## Core Capabilities\n\n- List incidents for a mapped Azure resource\u002Fservice (focus on active first)\n- Retrieve an incident by ID (status, responders, notes, timeline)\n- Acknowledge (establish ownership) and document current hypothesis + next update ETA\n- Add structured diagnostic\u002Fupdate notes (context, evidence, action, next steps)\n- Resolve (after verified recovery) with cause, fix, and follow‑up tasks\n- Query PagerDuty AI assistant for runbook steps, differential diagnosis, known issues, validation & rollback guidance\n\n## Required Context Inputs\n\n- Azure resource identifier (full resource ID or name + subscription\u002Fresource group)\n- PagerDuty incident ID (if direct action) OR resource → mapped PagerDuty service\n- Incident attributes: status, urgency, responders, escalation policy, recent notes\n- Telemetry snapshot (alerts, metrics, logs, recent deployments\u002Fchanges) when diagnosing or resolving\n\n## Lightweight Workflow\n\n1. Target: Incident ID given? → act on it. Else map Azure resource → service → active incidents.\n2. Validate: Confirm status, service mapping, recent notes\u002Ftimeline, ownership.\n3. Decide Action: situational awareness, acknowledge, add note, resolve, or AI guidance.\n4. Execute: Perform action using appropriate tool(s); keep communication concise (system prompt style).\n5. Document: Add\u002Fupdate note (especially for acknowledge\u002Fresolve) with clear evidence + next step.\n6. Follow-Up: Ensure stakeholders informed; link telemetry or change records if relevant.\n\n## Action Guidance\n\n### List \u002F Filter by Azure Resource\n\n- Map resource → PagerDuty service\u002Fintegration.\n- Return active (triggered\u002Facknowledged) first; include resolved only if user requests history.\n- Present essentials: ID, title, status, urgency, service, primary assignee\u002Fresponders, brief timeline summary.\n\n### Retrieve by Incident ID\n\n- Show: status, responders, escalation policy, last 2–3 notes, triggers (alerts\u002Fmetrics), recent changes.\n- Provide concise status + any blocking investigation context.\n\n### Acknowledge\n\n- **CRITICAL**: Before acknowledging, ALWAYS fetch the latest incident details using GetPagerDutyIncidentById and check the incident status.\n- **Only acknowledge incidents in \"triggered\" status**. Do NOT acknowledge incidents that are already \"acknowledged\", \"resolved\", or \"closed\".\n- Acknowledging a resolved incident will reactivate it and trigger unnecessary alerts to on-call engineers.\n- Do when taking ownership or starting active investigation of a triggered incident.\n- Note template:\n  \"Acknowledged at [UTC timestamp]. Observations: [key signal]. Hypothesis: [initial]. Next update: [ETA].\"\n\n### Add Note\n\n- Use structured mini-format:\n  Context: what was looked at \u002F changed\n  Evidence: metrics\u002Flogs\u002Ferror signatures\u002Ftrace IDs\n  Action: commands, config adjust, rollback, none\n  Next: monitoring step, verification window, escalation trigger\n- Keep each section to a sentence or compact list; link Azure artifacts when clarifying.\n\n### Resolve\n\n- Preconditions: symptom cleared, metrics\u002Falerts normal, fix or rollback validated, no residual impact.\n- Resolution note:\n  \"Resolved at [UTC]. Cause: [root\u002Ftrigger]. Fix: [action]. Verification: [metrics\u002Ftests]. Follow-up: [RCA task \u002F runbook update].\"\n\n### Query PagerDuty AI Assistant\n\n- Provide: incident ID\u002Ftitle, service, resource type, key error patterns, recent note summary.\n- Ask for specific output (e.g., \"runbook steps for storage latency\", \"differential diagnosis for CPU spike\", \"rollback procedure for failed deployment\").\n- Cross-check AI suggestions against live telemetry before acting.\n\n## Best Practices\n\n- Ownership: Ensure exactly one active owner post-ack.\n- Brevity: Notes should accelerate future decisions; avoid narrative fluff.\n- Auditability: Reference change IDs, deployment timestamps, or query links when relevant.\n- Escalation: If no progress within SLA window or repeated blockers → escalate per policy.\n- Consistency: Use UTC timestamps; avoid subjective language (\"seems fine\").\n\n## Error Handling (Condensed)\n\n| Scenario | Response |\n|----------|----------|\n| Incident or resource not found | Revalidate IDs; confirm subscription\u002Fresource group; clarify mapping. |\n| Permission denied | Surface need for authorized responder; pause action. |\n| Ambiguous AI output | Request clarification or narrower query; verify with telemetry. |\n| Action tool failure | Parse error → 1 retry if transient; after 2 failures escalate (aligns with system prompt). |\n\n## Examples\n\n### List incidents for Azure VM\n\nInput: VM resource ID → map service → list active incidents (ID, title, status, urgency, assignee).\n\n### Acknowledge + Diagnostic Note\n\n\"Acknowledged at 10:04 UTC. Observations: sustained 95% CPU on scale set. Hypothesis: autoscale lag. Next update: 10:19 UTC.\"\n\n### Resolve After Fix\n\n\"Resolved at 11:22 UTC. Cause: misconfigured autoscale profile. Fix: adjusted min\u002Fmax instances. Verification: CPU stable \u003C60% for 20m, alerts cleared. Follow-up: update autoscale runbook & add guardrail validation.\"\n\n## Quick Reference Checklists\n\nAcknowledgment: fetch latest incident → verify status is \"triggered\" → acknowledge → ownership established → diagnostic outline → ETA set.\nResolution: impact ended → metrics normal → cause identified → fix validated → follow-up logged.\nAI Query: clear question → incident context packaged → narrow objective → verify output.\n\n---\nUse this skill only for PagerDuty incident lifecycle and diagnostics enrichment; defer all general Azure discovery & configuration behaviors to the core system instructions.\n",{"data":39,"body":40},{"name":5,"description":7},{"type":41,"children":42},"root",[43,52,59,94,100,123,129,163,169,176,194,200,213,219,287,293,306,312,359,365,383,389,417,423,503,509,515,521,527,532,538,543,549,554,558],{"type":44,"tag":45,"props":46,"children":48},"element","h1",{"id":47},"pagerduty-incident-management-for-azure-resources",[49],{"type":50,"value":51},"text","PagerDuty Incident Management for Azure Resources",{"type":44,"tag":53,"props":54,"children":56},"h2",{"id":55},"core-capabilities",[57],{"type":50,"value":58},"Core Capabilities",{"type":44,"tag":60,"props":61,"children":62},"ul",{},[63,69,74,79,84,89],{"type":44,"tag":64,"props":65,"children":66},"li",{},[67],{"type":50,"value":68},"List incidents for a mapped Azure resource\u002Fservice (focus on active first)",{"type":44,"tag":64,"props":70,"children":71},{},[72],{"type":50,"value":73},"Retrieve an incident by ID (status, responders, notes, timeline)",{"type":44,"tag":64,"props":75,"children":76},{},[77],{"type":50,"value":78},"Acknowledge (establish ownership) and document current hypothesis + next update ETA",{"type":44,"tag":64,"props":80,"children":81},{},[82],{"type":50,"value":83},"Add structured diagnostic\u002Fupdate notes (context, evidence, action, next steps)",{"type":44,"tag":64,"props":85,"children":86},{},[87],{"type":50,"value":88},"Resolve (after verified recovery) with cause, fix, and follow‑up tasks",{"type":44,"tag":64,"props":90,"children":91},{},[92],{"type":50,"value":93},"Query PagerDuty AI assistant for runbook steps, differential diagnosis, known issues, validation & rollback guidance",{"type":44,"tag":53,"props":95,"children":97},{"id":96},"required-context-inputs",[98],{"type":50,"value":99},"Required Context Inputs",{"type":44,"tag":60,"props":101,"children":102},{},[103,108,113,118],{"type":44,"tag":64,"props":104,"children":105},{},[106],{"type":50,"value":107},"Azure resource identifier (full resource ID or name + subscription\u002Fresource group)",{"type":44,"tag":64,"props":109,"children":110},{},[111],{"type":50,"value":112},"PagerDuty incident ID (if direct action) OR resource → mapped PagerDuty service",{"type":44,"tag":64,"props":114,"children":115},{},[116],{"type":50,"value":117},"Incident attributes: status, urgency, responders, escalation policy, recent notes",{"type":44,"tag":64,"props":119,"children":120},{},[121],{"type":50,"value":122},"Telemetry snapshot (alerts, metrics, logs, recent deployments\u002Fchanges) when diagnosing or resolving",{"type":44,"tag":53,"props":124,"children":126},{"id":125},"lightweight-workflow",[127],{"type":50,"value":128},"Lightweight Workflow",{"type":44,"tag":130,"props":131,"children":132},"ol",{},[133,138,143,148,153,158],{"type":44,"tag":64,"props":134,"children":135},{},[136],{"type":50,"value":137},"Target: Incident ID given? → act on it. Else map Azure resource → service → active incidents.",{"type":44,"tag":64,"props":139,"children":140},{},[141],{"type":50,"value":142},"Validate: Confirm status, service mapping, recent notes\u002Ftimeline, ownership.",{"type":44,"tag":64,"props":144,"children":145},{},[146],{"type":50,"value":147},"Decide Action: situational awareness, acknowledge, add note, resolve, or AI guidance.",{"type":44,"tag":64,"props":149,"children":150},{},[151],{"type":50,"value":152},"Execute: Perform action using appropriate tool(s); keep communication concise (system prompt style).",{"type":44,"tag":64,"props":154,"children":155},{},[156],{"type":50,"value":157},"Document: Add\u002Fupdate note (especially for acknowledge\u002Fresolve) with clear evidence + next step.",{"type":44,"tag":64,"props":159,"children":160},{},[161],{"type":50,"value":162},"Follow-Up: Ensure stakeholders informed; link telemetry or change records if relevant.",{"type":44,"tag":53,"props":164,"children":166},{"id":165},"action-guidance",[167],{"type":50,"value":168},"Action Guidance",{"type":44,"tag":170,"props":171,"children":173},"h3",{"id":172},"list-filter-by-azure-resource",[174],{"type":50,"value":175},"List \u002F Filter by Azure Resource",{"type":44,"tag":60,"props":177,"children":178},{},[179,184,189],{"type":44,"tag":64,"props":180,"children":181},{},[182],{"type":50,"value":183},"Map resource → PagerDuty service\u002Fintegration.",{"type":44,"tag":64,"props":185,"children":186},{},[187],{"type":50,"value":188},"Return active (triggered\u002Facknowledged) first; include resolved only if user requests history.",{"type":44,"tag":64,"props":190,"children":191},{},[192],{"type":50,"value":193},"Present essentials: ID, title, status, urgency, service, primary assignee\u002Fresponders, brief timeline summary.",{"type":44,"tag":170,"props":195,"children":197},{"id":196},"retrieve-by-incident-id",[198],{"type":50,"value":199},"Retrieve by Incident ID",{"type":44,"tag":60,"props":201,"children":202},{},[203,208],{"type":44,"tag":64,"props":204,"children":205},{},[206],{"type":50,"value":207},"Show: status, responders, escalation policy, last 2–3 notes, triggers (alerts\u002Fmetrics), recent changes.",{"type":44,"tag":64,"props":209,"children":210},{},[211],{"type":50,"value":212},"Provide concise status + any blocking investigation context.",{"type":44,"tag":170,"props":214,"children":216},{"id":215},"acknowledge",[217],{"type":50,"value":218},"Acknowledge",{"type":44,"tag":60,"props":220,"children":221},{},[222,233,243,248,253],{"type":44,"tag":64,"props":223,"children":224},{},[225,231],{"type":44,"tag":226,"props":227,"children":228},"strong",{},[229],{"type":50,"value":230},"CRITICAL",{"type":50,"value":232},": Before acknowledging, ALWAYS fetch the latest incident details using GetPagerDutyIncidentById and check the incident status.",{"type":44,"tag":64,"props":234,"children":235},{},[236,241],{"type":44,"tag":226,"props":237,"children":238},{},[239],{"type":50,"value":240},"Only acknowledge incidents in \"triggered\" status",{"type":50,"value":242},". Do NOT acknowledge incidents that are already \"acknowledged\", \"resolved\", or \"closed\".",{"type":44,"tag":64,"props":244,"children":245},{},[246],{"type":50,"value":247},"Acknowledging a resolved incident will reactivate it and trigger unnecessary alerts to on-call engineers.",{"type":44,"tag":64,"props":249,"children":250},{},[251],{"type":50,"value":252},"Do when taking ownership or starting active investigation of a triggered incident.",{"type":44,"tag":64,"props":254,"children":255},{},[256,258,264,266,271,273,278,280,285],{"type":50,"value":257},"Note template:\n\"Acknowledged at ",{"type":44,"tag":259,"props":260,"children":261},"span",{},[262],{"type":50,"value":263},"UTC timestamp",{"type":50,"value":265},". Observations: ",{"type":44,"tag":259,"props":267,"children":268},{},[269],{"type":50,"value":270},"key signal",{"type":50,"value":272},". Hypothesis: ",{"type":44,"tag":259,"props":274,"children":275},{},[276],{"type":50,"value":277},"initial",{"type":50,"value":279},". Next update: ",{"type":44,"tag":259,"props":281,"children":282},{},[283],{"type":50,"value":284},"ETA",{"type":50,"value":286},".\"",{"type":44,"tag":170,"props":288,"children":290},{"id":289},"add-note",[291],{"type":50,"value":292},"Add Note",{"type":44,"tag":60,"props":294,"children":295},{},[296,301],{"type":44,"tag":64,"props":297,"children":298},{},[299],{"type":50,"value":300},"Use structured mini-format:\nContext: what was looked at \u002F changed\nEvidence: metrics\u002Flogs\u002Ferror signatures\u002Ftrace IDs\nAction: commands, config adjust, rollback, none\nNext: monitoring step, verification window, escalation trigger",{"type":44,"tag":64,"props":302,"children":303},{},[304],{"type":50,"value":305},"Keep each section to a sentence or compact list; link Azure artifacts when clarifying.",{"type":44,"tag":170,"props":307,"children":309},{"id":308},"resolve",[310],{"type":50,"value":311},"Resolve",{"type":44,"tag":60,"props":313,"children":314},{},[315,320],{"type":44,"tag":64,"props":316,"children":317},{},[318],{"type":50,"value":319},"Preconditions: symptom cleared, metrics\u002Falerts normal, fix or rollback validated, no residual impact.",{"type":44,"tag":64,"props":321,"children":322},{},[323,325,330,332,337,339,344,346,351,353,358],{"type":50,"value":324},"Resolution note:\n\"Resolved at ",{"type":44,"tag":259,"props":326,"children":327},{},[328],{"type":50,"value":329},"UTC",{"type":50,"value":331},". Cause: ",{"type":44,"tag":259,"props":333,"children":334},{},[335],{"type":50,"value":336},"root\u002Ftrigger",{"type":50,"value":338},". Fix: ",{"type":44,"tag":259,"props":340,"children":341},{},[342],{"type":50,"value":343},"action",{"type":50,"value":345},". Verification: ",{"type":44,"tag":259,"props":347,"children":348},{},[349],{"type":50,"value":350},"metrics\u002Ftests",{"type":50,"value":352},". Follow-up: ",{"type":44,"tag":259,"props":354,"children":355},{},[356],{"type":50,"value":357},"RCA task \u002F runbook update",{"type":50,"value":286},{"type":44,"tag":170,"props":360,"children":362},{"id":361},"query-pagerduty-ai-assistant",[363],{"type":50,"value":364},"Query PagerDuty AI Assistant",{"type":44,"tag":60,"props":366,"children":367},{},[368,373,378],{"type":44,"tag":64,"props":369,"children":370},{},[371],{"type":50,"value":372},"Provide: incident ID\u002Ftitle, service, resource type, key error patterns, recent note summary.",{"type":44,"tag":64,"props":374,"children":375},{},[376],{"type":50,"value":377},"Ask for specific output (e.g., \"runbook steps for storage latency\", \"differential diagnosis for CPU spike\", \"rollback procedure for failed deployment\").",{"type":44,"tag":64,"props":379,"children":380},{},[381],{"type":50,"value":382},"Cross-check AI suggestions against live telemetry before acting.",{"type":44,"tag":53,"props":384,"children":386},{"id":385},"best-practices",[387],{"type":50,"value":388},"Best Practices",{"type":44,"tag":60,"props":390,"children":391},{},[392,397,402,407,412],{"type":44,"tag":64,"props":393,"children":394},{},[395],{"type":50,"value":396},"Ownership: Ensure exactly one active owner post-ack.",{"type":44,"tag":64,"props":398,"children":399},{},[400],{"type":50,"value":401},"Brevity: Notes should accelerate future decisions; avoid narrative fluff.",{"type":44,"tag":64,"props":403,"children":404},{},[405],{"type":50,"value":406},"Auditability: Reference change IDs, deployment timestamps, or query links when relevant.",{"type":44,"tag":64,"props":408,"children":409},{},[410],{"type":50,"value":411},"Escalation: If no progress within SLA window or repeated blockers → escalate per policy.",{"type":44,"tag":64,"props":413,"children":414},{},[415],{"type":50,"value":416},"Consistency: Use UTC timestamps; avoid subjective language (\"seems fine\").",{"type":44,"tag":53,"props":418,"children":420},{"id":419},"error-handling-condensed",[421],{"type":50,"value":422},"Error Handling (Condensed)",{"type":44,"tag":424,"props":425,"children":426},"table",{},[427,446],{"type":44,"tag":428,"props":429,"children":430},"thead",{},[431],{"type":44,"tag":432,"props":433,"children":434},"tr",{},[435,441],{"type":44,"tag":436,"props":437,"children":438},"th",{},[439],{"type":50,"value":440},"Scenario",{"type":44,"tag":436,"props":442,"children":443},{},[444],{"type":50,"value":445},"Response",{"type":44,"tag":447,"props":448,"children":449},"tbody",{},[450,464,477,490],{"type":44,"tag":432,"props":451,"children":452},{},[453,459],{"type":44,"tag":454,"props":455,"children":456},"td",{},[457],{"type":50,"value":458},"Incident or resource not found",{"type":44,"tag":454,"props":460,"children":461},{},[462],{"type":50,"value":463},"Revalidate IDs; confirm subscription\u002Fresource group; clarify mapping.",{"type":44,"tag":432,"props":465,"children":466},{},[467,472],{"type":44,"tag":454,"props":468,"children":469},{},[470],{"type":50,"value":471},"Permission denied",{"type":44,"tag":454,"props":473,"children":474},{},[475],{"type":50,"value":476},"Surface need for authorized responder; pause action.",{"type":44,"tag":432,"props":478,"children":479},{},[480,485],{"type":44,"tag":454,"props":481,"children":482},{},[483],{"type":50,"value":484},"Ambiguous AI output",{"type":44,"tag":454,"props":486,"children":487},{},[488],{"type":50,"value":489},"Request clarification or narrower query; verify with telemetry.",{"type":44,"tag":432,"props":491,"children":492},{},[493,498],{"type":44,"tag":454,"props":494,"children":495},{},[496],{"type":50,"value":497},"Action tool failure",{"type":44,"tag":454,"props":499,"children":500},{},[501],{"type":50,"value":502},"Parse error → 1 retry if transient; after 2 failures escalate (aligns with system prompt).",{"type":44,"tag":53,"props":504,"children":506},{"id":505},"examples",[507],{"type":50,"value":508},"Examples",{"type":44,"tag":170,"props":510,"children":512},{"id":511},"list-incidents-for-azure-vm",[513],{"type":50,"value":514},"List incidents for Azure VM",{"type":44,"tag":516,"props":517,"children":518},"p",{},[519],{"type":50,"value":520},"Input: VM resource ID → map service → list active incidents (ID, title, status, urgency, assignee).",{"type":44,"tag":170,"props":522,"children":524},{"id":523},"acknowledge-diagnostic-note",[525],{"type":50,"value":526},"Acknowledge + Diagnostic Note",{"type":44,"tag":516,"props":528,"children":529},{},[530],{"type":50,"value":531},"\"Acknowledged at 10:04 UTC. Observations: sustained 95% CPU on scale set. Hypothesis: autoscale lag. Next update: 10:19 UTC.\"",{"type":44,"tag":170,"props":533,"children":535},{"id":534},"resolve-after-fix",[536],{"type":50,"value":537},"Resolve After Fix",{"type":44,"tag":516,"props":539,"children":540},{},[541],{"type":50,"value":542},"\"Resolved at 11:22 UTC. Cause: misconfigured autoscale profile. Fix: adjusted min\u002Fmax instances. Verification: CPU stable \u003C60% for 20m, alerts cleared. Follow-up: update autoscale runbook & add guardrail validation.\"",{"type":44,"tag":53,"props":544,"children":546},{"id":545},"quick-reference-checklists",[547],{"type":50,"value":548},"Quick Reference Checklists",{"type":44,"tag":516,"props":550,"children":551},{},[552],{"type":50,"value":553},"Acknowledgment: fetch latest incident → verify status is \"triggered\" → acknowledge → ownership established → diagnostic outline → ETA set.\nResolution: impact ended → metrics normal → cause identified → fix validated → follow-up logged.\nAI Query: clear question → incident context packaged → narrow objective → verify output.",{"type":44,"tag":555,"props":556,"children":557},"hr",{},[],{"type":44,"tag":516,"props":559,"children":560},{},[561],{"type":50,"value":562},"Use this skill only for PagerDuty incident lifecycle and diagnostics enrichment; defer all general Azure discovery & configuration behaviors to the core system instructions.",{"items":564,"total":677},[565,585,606,625,644,657,670],{"slug":566,"name":567,"fn":568,"description":569,"org":570,"tags":571,"stars":27,"repoUrl":28,"updatedAt":584},"atlassianrovo","atlassian_rovo","manage Atlassian Jira and Confluence tasks","Expertise in Atlassian Cloud products including Jira, Confluence, Compass, and Jira Service Management. Use for searching issues with JQL, creating and updating pages, managing service components, investigating ops alerts, and navigating Atlassian workspaces via the Rovo MCP server.",{"slug":9,"name":10,"logoUrl":11,"githubOrg":12},[572,575,578,581],{"name":573,"slug":574,"type":17},"Atlassian","atlassian",{"name":576,"slug":577,"type":17},"Confluence","confluence",{"name":579,"slug":580,"type":17},"Jira","jira",{"name":582,"slug":583,"type":17},"Project Management","project-management","2026-07-12T08:20:33.735452",{"slug":586,"name":587,"fn":588,"description":589,"org":590,"tags":591,"stars":27,"repoUrl":28,"updatedAt":605},"awscloudoperations","aws_cloud_operations","manage and troubleshoot AWS cloud operations","Expertise in AWS cloud operations including infrastructure management, troubleshooting, documentation search, API execution, and operational procedures. Use for querying AWS resources, investigating incidents, following SOPs, searching documentation, checking service availability, and executing AWS API calls via the AWS MCP Server.",{"slug":9,"name":10,"logoUrl":11,"githubOrg":12},[592,595,598,601,602],{"name":593,"slug":594,"type":17},"AWS","aws",{"name":596,"slug":597,"type":17},"Debugging","debugging",{"name":599,"slug":600,"type":17},"Infrastructure","infrastructure",{"name":22,"slug":23,"type":17},{"name":603,"slug":604,"type":17},"Operations","operations","2026-07-12T08:20:14.702793",{"slug":607,"name":608,"fn":609,"description":610,"org":611,"tags":612,"stars":27,"repoUrl":28,"updatedAt":624},"azuremanagedgrafana","azure_managed_grafana","monitor Azure infrastructure with Grafana","Expertise in Azure Managed Grafana including dashboards, Azure Monitor metrics, Application Insights failures and traces, Azure Data Explorer (Kusto) queries, SQL Server queries, and Azure Resource Graph. Use for querying observability data, searching dashboards, investigating failures, analyzing GenAI agent telemetry, and running KQL or SQL queries via the AMG-MCP endpoint.",{"slug":9,"name":10,"logoUrl":11,"githubOrg":12},[613,616,617,620,621],{"name":614,"slug":615,"type":17},"Application Insights","application-insights",{"name":12,"slug":9,"type":17},{"name":618,"slug":619,"type":17},"Dashboards","dashboards",{"name":22,"slug":23,"type":17},{"name":622,"slug":623,"type":17},"Observability","observability","2026-07-12T08:19:37.659849",{"slug":626,"name":627,"fn":628,"description":629,"org":630,"tags":631,"stars":27,"repoUrl":28,"updatedAt":643},"datadogobservability","datadog_observability","query Datadog telemetry and investigate behavior","Expertise in Datadog's observability platform including logs, metrics, APM, monitors, incidents, dashboards, hosts, and services. Use for searching logs, querying metrics, investigating incidents, analyzing traces, inspecting monitors, and navigating Datadog data via the Datadog MCP server.",{"slug":9,"name":10,"logoUrl":11,"githubOrg":12},[632,635,638,641,642],{"name":633,"slug":634,"type":17},"Datadog","datadog",{"name":636,"slug":637,"type":17},"Logs","logs",{"name":639,"slug":640,"type":17},"Metrics","metrics",{"name":22,"slug":23,"type":17},{"name":622,"slug":623,"type":17},"2026-07-12T08:20:41.400308",{"slug":645,"name":646,"fn":647,"description":648,"org":649,"tags":650,"stars":27,"repoUrl":28,"updatedAt":656},"dynatraceobservability","dynatrace_observability","query Dynatrace observability data","Query Dynatrace observability data including logs, metrics, problems, and vulnerabilities using DQL",{"slug":9,"name":10,"logoUrl":11,"githubOrg":12},[651,652,653,654,655],{"name":12,"slug":9,"type":17},{"name":636,"slug":637,"type":17},{"name":639,"slug":640,"type":17},{"name":22,"slug":23,"type":17},{"name":622,"slug":623,"type":17},"2026-07-12T08:19:00.664087",{"slug":658,"name":658,"fn":659,"description":660,"org":661,"tags":662,"stars":27,"repoUrl":28,"updatedAt":669},"elasticsearch","query and analyze Elasticsearch data","Query and analyze Elasticsearch data including logs, indices, mappings, and cluster health using ES|QL",{"slug":9,"name":10,"logoUrl":11,"githubOrg":12},[663,666,667,668],{"name":664,"slug":665,"type":17},"Analytics","analytics",{"name":12,"slug":9,"type":17},{"name":636,"slug":637,"type":17},{"name":622,"slug":623,"type":17},"2026-07-12T08:20:22.325954",{"slug":4,"name":5,"fn":6,"description":7,"org":671,"tags":672,"stars":27,"repoUrl":28,"updatedAt":29},{"slug":9,"name":10,"logoUrl":11,"githubOrg":12},[673,674,675,676],{"name":19,"slug":20,"type":17},{"name":25,"slug":26,"type":17},{"name":22,"slug":23,"type":17},{"name":15,"slug":16,"type":17},7,{"items":679,"total":854},[680,699,718,737,752,765,778,793,804,818,829,842],{"slug":681,"name":681,"fn":682,"description":683,"org":684,"tags":685,"stars":696,"repoUrl":697,"updatedAt":698},"azure-arg-external-evaluation-policy-author","author and test Azure Resource Graph policies","Use when the user wants to author, design, or test an Azure Policy that queries Azure Resource Graph (ARG) at request-time — i.e. a policy whose deny\u002Faudit decision depends on data from elsewhere in the subscription (sibling\u002Fparent resource state, RG-wide invariants, multi-hop relationships, etc.). Formally called Azure Policy External Evaluation; sometimes referred to colloquially as \"Invoke\". Drives an iterative KQL co-design loop against the user's real subscription via `az graph query`, then emits a policy definition, assignment, `.http` test flow, and an `EXPLANATION.md` companion. Read-only; never provisions anything.",{"slug":9,"name":10,"logoUrl":11,"githubOrg":12},[686,687,690,693],{"name":12,"slug":9,"type":17},{"name":688,"slug":689,"type":17},"Compliance","compliance",{"name":691,"slug":692,"type":17},"Governance","governance",{"name":694,"slug":695,"type":17},"Policy","policy",1686,"https:\u002F\u002Fgithub.com\u002FAzure\u002Fazure-policy","2026-07-12T08:17:48.378432",{"slug":700,"name":700,"fn":701,"description":702,"org":703,"tags":704,"stars":715,"repoUrl":716,"updatedAt":717},"azure-blueprints-migration","migrate Azure Blueprints to Template Specs","Use when a user needs to migrate off Azure Blueprints (definitions and\u002For assignments) to Template Specs and Deployment Stacks before the January 31, 2027 retirement. Covers inventory, export, conversion to Bicep, policy decoupling, Template Spec publishing, Deployment Stack deployment with deny-settings, validation, and cutover.",{"slug":9,"name":10,"logoUrl":11,"githubOrg":12},[705,706,709,712],{"name":12,"slug":9,"type":17},{"name":707,"slug":708,"type":17},"Deployment","deployment",{"name":710,"slug":711,"type":17},"Infrastructure as Code","infrastructure-as-code",{"name":713,"slug":714,"type":17},"Migration","migration",260,"https:\u002F\u002Fgithub.com\u002FAzure\u002Fazure-blueprints","2026-07-12T08:17:49.646405",{"slug":719,"name":719,"fn":720,"description":721,"org":722,"tags":723,"stars":734,"repoUrl":735,"updatedAt":736},"apiview-feedback-resolution","resolve APIView feedback on Azure SDKs","Analyze and resolve APIView review feedback on Azure SDK PRs. **UTILITY SKILL**. USE FOR: APIView comments, API review feedback, SDK API surface changes. DO NOT USE FOR: general code review, non-APIView feedback. INVOKES: azure-sdk-mcp:azsdk_apiview_get_comments, azure-sdk-mcp:azsdk_typespec_customized_code_update.",{"slug":9,"name":10,"logoUrl":11,"githubOrg":12},[724,727,728,731],{"name":725,"slug":726,"type":17},"API Development","api-development",{"name":12,"slug":9,"type":17},{"name":729,"slug":730,"type":17},"Code Review","code-review",{"name":732,"slug":733,"type":17},"Documentation","documentation",133,"https:\u002F\u002Fgithub.com\u002FAzure\u002Fazure-sdk-tools","2026-07-12T08:17:43.350876",{"slug":738,"name":738,"fn":739,"description":740,"org":741,"tags":742,"stars":734,"repoUrl":735,"updatedAt":751},"azsdk-common-live-and-recorded-tests","deploy resources and run Azure SDK tests","Deploy test resources and run Azure SDK tests in live, record, or playback mode. WHEN: \"run live tests\", \"run recorded tests\", \"deploy test resources\", \"record tests\", \"run tests in record mode\", \"clean up test resources\", \"run tests against live resources\". DO NOT USE FOR: writing new tests, authoring Bicep templates, playback-only test runs without resource deployment. INVOKES: azure-sdk-mcp:azsdk_package_run_tests.",{"slug":9,"name":10,"logoUrl":11,"githubOrg":12},[743,744,745,748],{"name":12,"slug":9,"type":17},{"name":707,"slug":708,"type":17},{"name":746,"slug":747,"type":17},"SDK","sdk",{"name":749,"slug":750,"type":17},"Testing","testing","2026-07-12T08:17:44.718943",{"slug":753,"name":753,"fn":754,"description":755,"org":756,"tags":757,"stars":734,"repoUrl":735,"updatedAt":764},"azsdk-common-prepare-release-plan","manage Azure SDK release plan work items","Create, get, update, abandon, and link SDK PRs to release plan work items for Azure SDK releases. **UTILITY SKILL**. USE FOR: \"create release plan\", \"get release plan\", \"update release plan\", \"update API spec in release plan\", \"update SDK details in release plan\", \"abandon release plan\", \"link SDK PR to plan\", \"namespace approval\", \"check release plan status\". DO NOT USE FOR: SDK code generation, pipeline troubleshooting, API review feedback. INVOKES: azure-sdk-mcp:azsdk_create_release_plan, azure-sdk-mcp:azsdk_get_release_plan, azure-sdk-mcp:azsdk_get_release_plan_for_spec_pr, azure-sdk-mcp:azsdk_update_release_plan, azure-sdk-mcp:azsdk_update_api_spec_pull_request_in_release_plan, azure-sdk-mcp:azsdk_update_sdk_details_in_release_plan, azure-sdk-mcp:azsdk_abandon_release_plan, azure-sdk-mcp:azsdk_link_sdk_pull_request_to_release_plan, azure-sdk-mcp:azsdk_link_namespace_approval_issue.",{"slug":9,"name":10,"logoUrl":11,"githubOrg":12},[758,759,762,763],{"name":12,"slug":9,"type":17},{"name":760,"slug":761,"type":17},"GitHub","github",{"name":582,"slug":583,"type":17},{"name":746,"slug":747,"type":17},"2026-07-12T08:17:38.345387",{"slug":766,"name":766,"fn":767,"description":768,"org":769,"tags":770,"stars":734,"repoUrl":735,"updatedAt":777},"azsdk-common-sdk-release","release Azure SDK packages","Check release readiness and trigger the release pipeline for Azure SDK packages. **UTILITY SKILL**. USE FOR: \"release SDK\", \"trigger release\", \"check release readiness\", \"release pipeline\", \"publish package\", \"ship SDK\". DO NOT USE FOR: SDK development, code generation, pipeline debugging, release plan creation. INVOKES: azure-sdk-mcp:azsdk_release_sdk.",{"slug":9,"name":10,"logoUrl":11,"githubOrg":12},[771,772,775,776],{"name":12,"slug":9,"type":17},{"name":773,"slug":774,"type":17},"CI\u002FCD","ci-cd",{"name":707,"slug":708,"type":17},{"name":746,"slug":747,"type":17},"2026-07-12T08:17:34.27607",{"slug":779,"name":779,"fn":780,"description":781,"org":782,"tags":783,"stars":734,"repoUrl":735,"updatedAt":792},"azure-typespec-author","author and modify Azure TypeSpec API specifications","Authors and modifies Azure TypeSpec (.tsp) API specifications. USE FOR: any TypeSpec\u002Ftsp change — api versions (add, bump, preview, stable, promote), resources, operations, models, properties, decorators, visibility, constraints, breaking changes, LRO, suppressions, operationId, spread model. Covers ARM resource-manager and data-plane services. DO NOT USE FOR: SDK generation, releasing SDK packages, or single MCP tool calls. INVOKES: azure-sdk-mcp:azsdk_typespec_generate_authoring_plan, azure-sdk-mcp:azsdk_run_typespec_validation.",{"slug":9,"name":10,"logoUrl":11,"githubOrg":12},[784,785,786,789],{"name":725,"slug":726,"type":17},{"name":12,"slug":9,"type":17},{"name":787,"slug":788,"type":17},"OpenAPI","openapi",{"name":790,"slug":791,"type":17},"Technical Writing","technical-writing","2026-07-12T08:17:39.603232",{"slug":794,"name":794,"fn":795,"description":796,"org":797,"tags":798,"stars":734,"repoUrl":735,"updatedAt":803},"generate-sdk-locally","generate and test Azure SDKs locally","Generate, build, and test Azure SDKs locally from TypeSpec with automatic customization. WHEN: \"generate SDK locally\", \"build SDK\", \"run SDK tests\", \"run CI checks\", \"validate package\", \"run checks\", \"update changelog\", \"fix SDK build errors\", \"fix breaking changes\", \"resolve SDK generation errors\", \"customize TypeSpec\", \"rename SDK client\", \"rename SDK model\", \"hide operation from SDK\", \"fix analyzer errors\", \"resolve customization drift\", \"create subclient\", \"update metadata\", \"update version\". DO NOT USE FOR: publishing to package registries, CI pipeline configuration, API design review. INVOKES: azsdk_verify_setup, azsdk_package_generate_code, azsdk_package_build_code, azsdk_package_run_check, azsdk_package_run_tests, azsdk_customized_code_update, azsdk_package_update_changelog_content, azsdk_package_update_metadata, azsdk_package_update_version.",{"slug":9,"name":10,"logoUrl":11,"githubOrg":12},[799,800,801,802],{"name":12,"slug":9,"type":17},{"name":773,"slug":774,"type":17},{"name":746,"slug":747,"type":17},{"name":749,"slug":750,"type":17},"2026-07-12T08:17:37.08523",{"slug":805,"name":805,"fn":806,"description":807,"org":808,"tags":809,"stars":734,"repoUrl":735,"updatedAt":817},"markdown-token-optimizer","optimize markdown files for token efficiency","Analyze markdown files for token efficiency and reduce context-window bloat. **UTILITY SKILL**. DO NOT USE FOR: code optimization, general file editing, non-markdown files. TRIGGERS: optimize markdown, reduce tokens, token count, token bloat, too many tokens, make concise, shrink file, file too large, optimize for AI, token efficiency, verbose markdown, reduce file size. INVOKES: waza CLI.",{"slug":9,"name":10,"logoUrl":11,"githubOrg":12},[810,813,816],{"name":811,"slug":812,"type":17},"LLM","llm",{"name":814,"slug":815,"type":17},"Performance","performance",{"name":790,"slug":791,"type":17},"2026-07-12T08:17:42.080413",{"slug":819,"name":819,"fn":820,"description":821,"org":822,"tags":823,"stars":734,"repoUrl":735,"updatedAt":828},"pipeline-troubleshooting","troubleshoot Azure SDK CI pipelines","Diagnose and resolve failures in Azure SDK CI and generation pipelines. **UTILITY SKILL**. USE FOR: \"pipeline failed\", \"build failure\", \"CI check failing\", \"SDK generation error\", \"reproduce pipeline locally\", \"debug SDK pipeline\". DO NOT USE FOR: local build issues without pipeline context, API design review, SDK publishing. INVOKES: azure-sdk-mcp:azsdk_analyze_pipeline, azure-sdk-mcp:azsdk_package_build_code, azure-sdk-mcp:azsdk_package_run_check.",{"slug":9,"name":10,"logoUrl":11,"githubOrg":12},[824,825,826,827],{"name":12,"slug":9,"type":17},{"name":773,"slug":774,"type":17},{"name":596,"slug":597,"type":17},{"name":746,"slug":747,"type":17},"2026-07-12T08:17:40.821512",{"slug":830,"name":830,"fn":831,"description":832,"org":833,"tags":834,"stars":734,"repoUrl":735,"updatedAt":841},"sensei","improve skill frontmatter compliance","**WORKFLOW SKILL** — Iteratively improve skill frontmatter compliance using the Ralph loop pattern. WHEN: \"run sensei\", \"sensei help\", \"improve skill\", \"fix frontmatter\", \"skill compliance\", \"frontmatter audit\", \"score skill\", \"check skill tokens\". INVOKES: token counting tools, test runners, git commands. FOR SINGLE OPERATIONS: use token CLI directly for counts\u002Fchecks.",{"slug":9,"name":10,"logoUrl":11,"githubOrg":12},[835,836,837,840],{"name":12,"slug":9,"type":17},{"name":688,"slug":689,"type":17},{"name":838,"slug":839,"type":17},"Process Optimization","process-optimization",{"name":790,"slug":791,"type":17},"2026-07-12T08:17:32.970921",{"slug":843,"name":843,"fn":844,"description":845,"org":846,"tags":847,"stars":734,"repoUrl":735,"updatedAt":853},"skill-authoring","author agent skills for agentskills.io","Write Agent Skills that comply with the agentskills.io specification. WHEN: \"create a skill\", \"new skill\", \"write a skill\", \"skill template\", \"skill structure\", \"review skill\", \"skill PR\", \"skill compliance\", \"SKILL.md format\", \"skill frontmatter\", \"skill best practices\". DO NOT USE FOR: improving existing skills (use sensei), general documentation. INVOKES: waza CLI.",{"slug":9,"name":10,"logoUrl":11,"githubOrg":12},[848,849,852],{"name":732,"slug":733,"type":17},{"name":850,"slug":851,"type":17},"Plugin Development","plugin-development",{"name":790,"slug":791,"type":17},"2026-07-12T08:17:35.873862",109]