20 Microsoft Foundry alternatives
Microsoft Foundry: Microsoft's official skill for building, deploying, evaluating, fine-tuning and operating agents and models on Microsoft Foundry with azd and the Foundry MCP tools, from project setup and RBAC to quota, tracing and CI/CD. 20 agent skills do similar work, most sharing Official, Agents and Azure, ranked by how much they have in common with Microsoft Foundry.
-
by Microsoft
Microsoft's official skill for troubleshooting Azure production issues: App Service, Container Apps, Functions, AKS, VMs and messaging, using AppLens, Azure Monitor, resource health and KQL.
-
by Microsoft
Microsoft's official AKS planning skill: separates the Day-0 decisions you cannot undo (networking, API server) from the Day-1 features you can switch on later.
-
by Microsoft
Microsoft's official Azure skill for cost work: query historical spend, forecast it, and hunt down waste like orphaned disks and oversized VMs.
-
by NVIDIA
NVIDIA's official skill for building synthetic datasets with NeMo Data Designer — describe the data you want and the agent writes a declarative generation pipeline, column by column.
Also: Evaluation, Fine-tuning
-
by Microsoft
Microsoft's official skill that turns an agent into an Azure solution architect — 10 design principles, 6 architecture styles, 44 design patterns and a Well-Architected review workflow.
-
by Microsoft
Microsoft's official skill for registering a Microsoft Entra ID app: OAuth 2.0 flows, redirect URIs, API permissions, service principals and MSAL wiring.
-
by Anthropic
Create, edit, and optimize Agent Skills — scaffold new skills, refine existing ones, run evals, and tune descriptions for reliable triggering.
Also: Agents, Evaluation
-
by SerpApi
A protocol for measuring whether agents can discover and use your tool without being told about it — WITH/WITHOUT trials, binary scoring, and lift as the only metric. The subject under test is your docs, not the model.
Also: Agents, Evaluation
-
by AMD
AMD's official skill for benchmarking vLLM/SGLang inference and driving GPU kernel optimization with Magpie and TraceLens trace analysis.
Also: Evaluation, Official
-
by Anthropic
Anthropic's official skill that appends 2-3 targeted follow-up questions to a substantive answer, prompting the reader to check facts, probe assumptions and spot missing context.
Also: Evaluation, Official
-
by Inngest
Build crash-safe AI agents on AgentKit and step.ai — durable tool calls, human-in-the-loop approval, realtime progress, and when not to reach for an agent loop at all.
-
by Vercel
Vercel's official skill for the AI SDK (the ai package): it makes the agent check the version-matched docs bundled in node_modules instead of memory, set up AI Gateway, list current model IDs and build agents with ToolLoopAgent.
-
by Google
Google's skill for deploying agents with agents-cli to Agent Runtime, Cloud Run or GKE: choosing a target, CI/CD pipelines, service accounts, secrets, rollback, Agent Gateway and production troubleshooting.
-
by Composio
Composio's official skill for reaching 1,000+ external apps from an agent — CLI-driven actions, Tool Router sessions, per-user auth and trigger events.
-
by VoltAgent
VoltAgent's official conventions skill — when to reach for an agent versus a workflow, the expected project layout, and the core snippets for agents, workflows, memory and servers.
-
by Pillar Security
Pillar Security's SAIL V2 framework as an agent skill: a 91-risk catalogue across seven lifecycle phases, for AI security gap assessments, roadmaps, and ISO 42001 / EU AI Act compliance checklists.
-
by Hugging Face
Train bi-encoders, rerankers, SPLADE sparse encoders and ColBERT multi-vector models with the loss, evaluator and template each type actually needs.
Also: Fine-tuning
-
by Hugging Face
Fine-tune object detection, image classification and SAM/SAM2 segmentation models on Hugging Face Jobs cloud GPUs, with dataset validation before you spend GPU minutes.
Also: Fine-tuning
-
by NVIDIA
Trains, distils, quantises, evaluates, exports and runs inference for RT-DETR real-time object detection in NVIDIA TAO, routing training through AutoML hyperparameter search by default.
Also: Fine-tuning
-
by Hugging Face
Fine-tune language and vision models with TRL or Unsloth — supervised, preference, and reinforcement training methods.
Also: Fine-tuning
