microsoft/sre-agent

proactive-health-check

Assess ticket reservation availability, failures, latency, dependencies, and Azure resource health using read-only evidence.

原文语言：英语

ticketing-pr-validation

Validate ticket reservation pull requests using repository evidence and optional read-only production baselines.

原文语言：英语

onboarding-lab

Set up, resume, inspect or operate the Azure SRE Agent onboarding lab in this checkout. Use when a learner asks for help preparing the lab, understanding a setup failure, or saving their reviewed learner artifact.

原文语言：英语

azure-monitor-rca

Investigate Azure Monitor incidents using application, database, and network evidence without changing workload resources.

原文语言：英语

email-incident-followup

Draft an opted-in incident email and request approval before sending, with best-effort duplicate checks.

原文语言：英语

github-issue-followup

Draft an opted-in GitHub incident follow-up and request approval before publishing, with best-effort duplicate checks.

原文语言：英语

deploying-demo

Deploy the SRE Agent demo end-to-end. Use when asked to set up, deploy, or get this demo running.

原文语言：英语

running-demo

Run break/fix demo scenarios with browser verification. Use when asked to demo, break the app, or show the SRE Agent working.

原文语言：英语

managing-sre-agent

Manage Azure SRE Agent configuration for this demo: connectors, skills, guarded custom agents, response plans, and the knowledge base. Use when asked to create, list, update, or delete SRE Agent resources.

原文语言：英语

connectivity-triage

Use for any Zava Learning incident where students cannot reach the platform or actions fail at the network/edge layer — quiz launches failing, portal 5xx, requests timing out, or backends appearing unhealthy. Traces the full request path (Application Gateway…

原文语言：英语

cost-analysis

Use when an operator or a scheduled task requests a periodic cloud-cost / spend audit of the Zava Learning resource group — identify the top cost drivers, week-over-week trend, idle or oversized resources, and concrete savings opportunities. Read-only;…

原文语言：英语

evidence-before-after

Use to build the before-and-after visual evidence for a Zava Learning incident. First classify the fault, then render the ONE visual that actually explains what changed — a before/after path or topology diagram for connectivity/config/RBAC faults, or…

原文语言：英语

nsg-audit

Use when an operator or a scheduled task requests a periodic Network Security Group (NSG) and connectivity-path audit of the Zava Learning resource group — enumerate every NSG and its rules, trace the full path (NSGs, UDRs / route tables, Private Endpoints,…

原文语言：英语

pagerduty-incident-update

Use to keep the triggering PagerDuty incident in sync with the investigation and to close it out — acknowledge on engagement, mark the incident Mitigated the moment the live fix lands, post a concise symptom-only status/summary note (diagnosis, mitigation,…

原文语言：英语

performance-investigation

Use for Zava Learning incidents where the platform is reachable but a compute tier is degraded — elevated 5xx from the APIs, slow quiz responses, exceptions, an API with no healthy instances, or a back-office batch job failing on the reporting-worker VM (e.g.…

原文语言：英语

pr-delivery

Use to deliver a durable Zava Learning fix as a GitHub pull request once an incident has been root-caused — for either an Infrastructure-as-Code change (Bicep under infra/) or an application code change (under src/). The single skill that creates pull…

原文语言：英语

rbac-audit

Use when an operator or a scheduled task requests a periodic RBAC / least-privilege audit of the Zava Learning resource group — enumerate the real role assignments effective on the group, correlate each identity against actual Activity-Log usage to find…

原文语言：英语

rca-analysis

Use to produce the root-cause analysis narrative for a resolved or mitigated Zava Learning incident — the incident timeline, the trigger vs. latent root cause (5-Whys), contributing factors, and how to present them. Defines the RCA section format; its output…

原文语言：英语

recommendations-next-steps

Use to produce the forward-looking recommendations and next steps for a Zava Learning incident — prioritized preventive, detective, and process actions with owners, target dates, and the risk of inaction. Its output is used in the zava-reporting deliverables.

原文语言：英语

redaction-guard

Use whenever you are about to emit operator-visible content — a chat/thread message, a PagerDuty or ServiceNow note, a commit message or pull-request body, or any report artifact (HTML, PowerPoint, Teams card). Deterministically masks secrets, credentials,…

原文语言：英语

servicenow-change-management

Use whenever a Zava Learning investigation produces a durable fix that needs change management — after a GitHub PR is opened for an Infrastructure-as-Code or application code root cause, raise a ServiceNow Change Request referencing the PR and attach the RCA…

原文语言：英语

zava-audit-report

Use to package a completed Zava Learning weekly governance audit (NSG / network security, RBAC / least-privilege, or cloud cost) into a single branded, downloadable PowerPoint deck in the Zava house style. The calling audit agent passes its findings (a list…

原文语言：英语

zava-reporting

Use to package a completed Zava Learning incident analysis for the audience. First present a branded in-thread executive summary (markdown with the before/after visuals inline), then produce the downloadable deliverables — a PowerPoint deck, an HTML email,…

原文语言：英语

deployment-compliance-check

Checks whether Azure Container App deployments comply with the organization's CI/CD-only deployment policy. Uses three signals: Activity Log caller identity, Docker image labels (tamper-proof), and resource tags. QueryLogAnalyticsByWorkspaceId

原文语言：英语