microsoft

1,771 mods in 74 plugins, 141 repositories, 1333k stars between them.

patch-verification

337

microsoft/AutoSaddler

Skill Claude Code ✓ vendor

Use after applying any patch to thoroughly verify the agent codebase has no bugs — checks syntax, imports, runtime behavior, docstrings, templates, hooks, and logical correctness.

not rated 250 +4 4d ago A SkillSpector: pass 38 tokens original MIT

steering-patch

338

microsoft/AutoSaddler

Skill Claude Code ✓ vendor

Selected during the steering phase — refines agent behavior by modifying prompts, tool descriptions, or hook reminders without changing executable code.

not rated 250 +4 4d ago A SkillSpector: pass 29 tokens original MIT

causal-diagnosis

339

microsoft/AutoSaddler

Skill Claude CodeCodex ✓ vendor

Use before proposing a mutation to diagnose measured failures from evaluator outcomes, traces, history, and the controlling candidate surfaces.

not rated 250 +4 4d ago A SkillSpector: pass 29 tokens original MIT

verification-baseline

340

microsoft/AutoSaddler

Skill Claude CodeCodex ✓ vendor

Use after applying a candidate change to verify its diff, scope, syntax, integration behavior, and consistency before returning it.

not rated 250 +4 4d ago A SkillSpector: pass 28 tokens original MIT

bcquality

341

microsoft/BCQuality

Plugin Claude Code ✓ vendor

Bundles 3 skills · 130 tokens together

Business Central AL quality knowledge base and review skills, packaged as an installable plugin. Exposes AL code review, cited knowledge consultation and preview plan guidance skills while preserving BCQuality's internal Entry and action-skill protocols.

not rated 241 +3 changed 3d ago A tokens not measured original MIT

caira

342

microsoft/CAIRA

Skill Claude CodeCodex ✓ vendor

Primary entrypoint for coding agents using CAIRA as reference material to design and build generative AI solutions with Azure AI Foundry, Azure OpenAI-compatible endpoints, agent frameworks, APIs, and frontends tailored to a user's scenario.

not rated 229 1mo ago A SkillSpector: warn 49 tokens original MIT

awesome-copilot

343

microsoft/mcp-dotnet-samples

MCP server Claude CodeCodexCursor +2 ✓ vendor

MCP server "awesome-copilot" as configured in microsoft/mcp-dotnet-samples. Runs in Docker (ghcr.io/microsoft/mcp-dotnet-samples/awesome-copilot:1.0.2026102300).

not rated 201 changed 13d ago A tokens not measured original MIT

microsoft/sre-agent

Skill Claude CodeCodex ✓ vendor

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.

not rated 187 +2 6d ago C 49 tokens original MIT

microsoft/sre-agent

Skill Claude CodeCodex ✓ vendor

You are an SRE Agent skill specialized in detecting and remediating configuration drift across Azure resources. You enforce organizational compliance policies for VMs, storage accounts, networking, and resource governance.

not rated 187 +2 6d ago A SkillSpector: pass 0 tokens original MIT

microsoft/sre-agent

Skill Claude CodeCodex ✓ vendor

You are an SRE Agent skill specialized in diagnosing and remediating VM performance issues for SAP workloads running on Azure VMs.

not rated 187 +2 6d ago A SkillSpector: pass 0 tokens original MIT

deploying-demo

347

microsoft/sre-agent

Skill Claude CodeCodex ✓ vendor

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

not rated 187 +2 changed 1mo ago A SkillSpector: pass 29 tokens original MIT

managing-sre-agent

348

microsoft/sre-agent

Skill Claude Code ✓ vendor

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.

not rated 187 +2 changed 1mo ago A SkillSpector: pass 49 tokens original MIT

running-demo

349

microsoft/sre-agent

Skill Claude CodeCodex ✓ vendor

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

not rated 187 +2 changed 1mo ago A SkillSpector: pass 31 tokens original MIT

connectivity-triage

350

microsoft/sre-agent

Skill Claude CodeCodex ✓ vendor

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 -> NSG -> Container Apps internal load balancer -> APIs)…

not rated 187 +2 6d ago A SkillSpector: pass 91 tokens original MIT

cost-analysis

351

microsoft/sre-agent

Skill Claude CodeCodex ✓ vendor

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; produces findings for a report.

not rated 187 +2 6d ago A SkillSpector: pass 57 tokens original MIT

evidence-before-after

352

microsoft/sre-agent

Skill Claude CodeCodex ✓ vendor

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 time-series comparison charts for performance/availability faults …

not rated 187 +2 6d ago A SkillSpector: pass 98 tokens original MIT

nsg-audit

353

microsoft/sre-agent

Skill Claude CodeCodex ✓ vendor

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, DNS, and any firewall), flag overly-permissive, shadowed…

not rated 187 +2 6d ago A SkillSpector: pass 100 tokens original MIT

microsoft/sre-agent

Skill Claude CodeCodex ✓ vendor

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, links to the PR / Change Request), and resolve the incident…

not rated 187 +2 6d ago A SkillSpector: pass 100 tokens original MIT

microsoft/sre-agent

Skill Claude CodeCodex ✓ vendor

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. nightly grade exports). Diagnoses from Application Insights…

not rated 187 +2 6d ago A SkillSpector: pass 84 tokens original MIT

pr-delivery

356

microsoft/sre-agent

Skill Claude CodeCodex ✓ vendor

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 requests; applies after live mitigation and root-cause…

not rated 187 +2 6d ago A SkillSpector: pass 83 tokens original MIT

rbac-audit

357

microsoft/sre-agent

Skill Claude CodeCodex ✓ vendor

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 standing access that is never used, flag over-privileged and…

not rated 187 +2 6d ago A SkillSpector: warn 100 tokens original MIT

rca-analysis

358

microsoft/sre-agent

Skill Claude CodeCodex ✓ vendor

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 is used in the before/after, recommendations, and reporting…

not rated 187 +2 6d ago A SkillSpector: pass 73 tokens original MIT

microsoft/sre-agent

Skill Claude CodeCodex ✓ vendor

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.

not rated 187 +2 6d ago A SkillSpector: pass 57 tokens original MIT

redaction-guard

360

microsoft/sre-agent

Skill Claude CodeCodex ✓ vendor

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, tokens, private keys, URI-embedded passwords, and PII so they…

not rated 187 +2 6d ago A SkillSpector: warn 105 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: