aiappsgbb/awesome-gbb

Curated collection of agentic Skills by AI Global Black Belts at Microsoft

This repository also configures its own agents. See what awesome-gbb tells them →

8Stars on the repository
50Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

auto-demo-producer

01

aiappsgbb/awesome-gbb

Skill Claude CodeCodex

Produce narrated video demos of web applications automatically. Uses Playwright for browser recording, edge-tts for narration, and ffmpeg for assembly. USE FOR: create demo video, record demo, auto demo, video demo, narrated walkthrough, product demo, screen recording with voiceover, demo producer, make a demo video…

not rated 8 +1 yesterday B 101 tokens original MIT

azd-patterns

02

aiappsgbb/awesome-gbb

Skill Claude CodeCodex needs its repo

Tips and patterns for Azure Developer CLI (azd) workflows, ACA job deployment, and infrastructure scripting conventions. USE FOR: azd hooks, postdeploy, postprovision, ACA job deployment, container app job image update, publishaca, deployjob, azure.yaml hooks, cross-platform deployment scripts, uv run, azd env, azd…

not rated 8 +1 changed 26d ago A SkillSpector: warn 191 tokens original MIT

aiappsgbb/awesome-gbb

Skill Claude CodeCodex

Audit Azure backup coverage at resource-group scope. Checks BOTH Recovery Services Vaults (RSV, azure-mgmt-recoveryservices) AND Backup Vaults (DataProtection, azure-mgmt-dataprotection). For each vault found, counts protected items (azure-mgmt-recoveryservicesbackup). Flags no-vaults-in-rg, vault-empty (vault present…

not rated 8 +1 yesterday A 241 tokens original MIT

aiappsgbb/awesome-gbb

Skill Claude CodeCodex

Probes Azure Monitor metric alert rules in a resource-group scope against one of three published baselines (foundrypilot, spokeminimum, production), returning a spec §4.3.1 sibling-skill dict with findingid "SRE-104", observations, remediation hints, confidence, and never raises. USE FOR: threadlight SRE-104…

not rated 8 +1 yesterday A 204 tokens original MIT

aiappsgbb/awesome-gbb

Skill Claude CodeCodex

Audit Azure diagnostic-settings coverage at resource-group scope. For each resource in the RG (optionally filtered by targetresourcetypes — ARM types or snakecase logical kinds like storageaccount), queries Microsoft.Insights/diagnosticSettings and reports whether ANY destination is configured (Log Analytics, Event…

not rated 8 +1 yesterday A 210 tokens original MIT

azure-sre-agent

06

aiappsgbb/awesome-gbb

Skill Claude CodeCodex needs its repo

Adopt Azure SRE Agent (Microsoft.App/agents) in GBB engagements without rebuilding what Microsoft already ships. Thin wrapper around the official microsoft/sre-agent toolchain and Azure/sre-agent-plugins marketplace. Adds 3 GBB recipes (Citadel-routed model traffic, Foundry hosted-agent ops, Threadlight pilot…

not rated 8 +1 changed 26d ago A SkillSpector: pass 248 tokens original MIT

aiappsgbb/awesome-gbb

Skill Claude CodeCodex

Diagnose 429 responses from the AI Citadel APIM gateway — identify which rate-limit policy tripped (per-product quota, per-named-value rate-limit-by-key, or backend pool TPM exhaustion).

not rated 8 +1 yesterday A 48 tokens original MIT

aiappsgbb/awesome-gbb

Skill Claude CodeCodex

Diagnose 401/403 responses at the AI Citadel APIM gateway — decode JWT claims, verify Access Contract scope grants, and validate Foundry managed-identity token audience.

not rated 8 +1 yesterday A 43 tokens original MIT

aiappsgbb/awesome-gbb

Skill Claude CodeCodex

Diagnose the silent BYOK 401 that Foundry hosted agents emit when "Foundry User" RBAC is assigned at PROJECT scope but missing at the underlying CognitiveServices ACCOUNT scope. Encodes the exact fix command.

not rated 8 +1 yesterday B 52 tokens original MIT

aiappsgbb/awesome-gbb

Skill Claude CodeCodex

Investigate failed Microsoft Foundry hosted-agent deployments — MAF SDK breaking changes, ACR push, ACA rollout, BYOK provisioning, and the azd ai agent extension's known envelope and RBAC quirks.

not rated 8 +1 changed 26d ago A 51 tokens original MIT

aiappsgbb/awesome-gbb

Skill Claude CodeCodex

Diagnose AOAI deployment TPM exhaustion behind Foundry hosted agents — pull capacity vs utilization, identify burst patterns, recommend scale-up or PTU migration.

not rated 8 +1 yesterday A 36 tokens original MIT

aiappsgbb/awesome-gbb

Skill Claude CodeCodex

Multi-tenant Azure CLI and AZD isolation for concurrent terminal sessions. Index-file driven, bare az CLI commands only — no wrapper scripts, no PowerShell modules. Mandatory two-layer guard: per-tenant AZURECONFIGDIR is the foundation, and az account show assertion is the extra gate that verifies tenant +…

not rated 8 +1 changed 28d ago C 200 tokens original MIT

citadel-hub-deploy

13

aiappsgbb/awesome-gbb

Skill Claude CodeCodex

Deploy the AI Citadel Governance Hub (Layer 1) — APIM AI Gateway, Microsoft Foundry control plane, telemetry, 4 LLM APIs (Azure OpenAI, OpenAI Realtime, Universal LLM, Unified AI), private endpoints, access contracts. Wraps Azure-Samples/ai-hub-gateway-solution-accelerator branch citadel-v1 (azd template) at a pinned…

not rated 8 +1 yesterday A SkillSpector: warn 268 tokens original MIT

aiappsgbb/awesome-gbb

Skill Claude CodeCodex needs its repo

Onboard a Foundry project as a spoke into an AI Citadel Governance Hub. Covers Access Contracts, APIM connections, product policies, JWT auth. USE FOR: citadel spoke onboarding, access contract, connect foundry to citadel, APIM connection, bring your own ai gateway, govern agent, citadel JWT auth, citadel product…

not rated 8 +1 changed 1mo ago A SkillSpector: warn 167 tokens original MIT

foundry-agt

15

aiappsgbb/awesome-gbb

Skill Claude CodeCodex

AGT 4.1 in-process message-policy and tool-governance middleware for Microsoft Agent Framework (MAF) agents on Foundry. Loads YAML policies (default / PII-deny, inbound message text only) into a PolicyEvaluator; AuditTrailMiddleware and GovernancePolicyMiddleware are always in the canonical policy path.…

not rated 8 +1 changed 1mo ago A SkillSpector: pass 222 tokens original MIT

aiappsgbb/awesome-gbb

Skill Claude CodeCodex

Day-2 lifecycle of Microsoft Foundry capability hosts — the operational layer on top of MS Learn's create-only guidance. Covers idempotent create (REST 2025-06-01), inspect/GET, delete, soft-delete + purge of the parent Cognitive Services account (the only op that releases the serviceAssociationLink on the agent…

not rated 8 +1 changed 26d ago A SkillSpector: warn 229 tokens original MIT

aiappsgbb/awesome-gbb

Skill Claude CodeCodex needs its repo

Continuous Foundry token-cost monitoring, chargeback, budget alerts, and FinOps automation. Joins genai.usage spans emitted by foundry-observability with the Azure Retail Prices API to compute per-agent / per-project / per-tenant cost projection. Wires Cost Management budgets + Action Groups, and uses Foundry's…

not rated 8 +1 yesterday A SkillSpector: pass 214 tokens original MIT

aiappsgbb/awesome-gbb

Skill Claude CodeCodex

Cross-resource model invocation in Microsoft Foundry via an Azure APIM AI Gateway, using the connectionName/deploymentName model string. Covers ApiKey and ProjectManagedIdentity (PMI) auth paths, multiple invocation patterns, APIM inbound policy, connection ARM/REST schema, and the metadata-stringification quirk. Read…

not rated 8 +1 yesterday A SkillSpector: pass 208 tokens original MIT

aiappsgbb/awesome-gbb

Skill Claude CodeCodex

Add vision (gpt-5.4 family), Document Intelligence v4, and Azure Speech (STT/TTS) capabilities to a Foundry hosted agent. Covers tool contracts, Bicep modules, runtime client code, and model selection for vision workloads. USE FOR: vision tool, image analysis, damage photo analysis, blueprint annotation, document…

not rated 8 +1 changed 26d ago A SkillSpector: warn 185 tokens original MIT

foundry-evals

20

aiappsgbb/awesome-gbb

Skill Claude CodeCodex

Evaluate Foundry agents with agent-target runs or an explicit invoke+score fallback. Covers sequential invocation, cold-start handling, dataset creation, evaluator configuration, RBAC for eval judges, result interpretation, and native suite/data/evaluator lifecycle with official optimizer handoffs. USE FOR: evaluate…

not rated 8 +1 changed 6d ago A SkillSpector: warn 192 tokens original MIT

foundry-iq

21

aiappsgbb/awesome-gbb

Skill Claude CodeCodex

Build enterprise RAG with Foundry IQ and Azure AI Search Knowledge Bases using agentic retrieval, multi-hop reasoning, query planning, and citation-backed responses. Distinguishes the stable 2026-04-01 programmatic API from preview portal experiences and preview-only knowledge-source integrations. USE FOR: knowledge…

not rated 8 +1 changed 26d ago A SkillSpector: warn 184 tokens original MIT

foundry-mcp-aca

22

aiappsgbb/awesome-gbb

Skill Claude CodeCodex needs its repo

Deploy custom MCP servers as Azure Container Apps or Azure Functions for use with Foundry hosted agents. Covers Cosmos DB MCPToolKit, Playwright MCP, custom MCP servers, protocol requirements, ACA configuration, and authentication + hardening (ACA built-in auth / Easy Auth, OAuth, managed identity). USE FOR: deploy…

not rated 8 +1 changed 26d ago A SkillSpector: warn 191 tokens original MIT

aiappsgbb/awesome-gbb

Skill Claude CodeCodex

Operational runbook for diagnosing Microsoft Foundry network-layer failures after a deploy succeeds — DNS, VNet peering, NSG / Azure Firewall denies, RBAC scope, capability host subnet exhaustion, agent NIC / MI provisioning, project-connection status. USE FOR: foundry network 503, InvalidPrivateDnsZoneIds at deploy…

not rated 8 +1 changed 26d ago A SkillSpector: pass 236 tokens original MIT

aiappsgbb/awesome-gbb

Skill Claude CodeCodex needs its repo

End-to-end observability for Azure AI pilots — App Insights + Log Analytics + OpenTelemetry across hosted agents, ACA MCP servers, ACA jobs, bot service, workspace UIs. Closes the silent telemetry gap where azd up returns 0 but zero traces ever reach App Insights. Covers Bicep modules, Foundry account-level telemetry…

not rated 8 +1 changed 26d ago A SkillSpector: warn 231 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: