microsoft-foundry

Deploy, evaluate, and manage Foundry agents end-to-end: Docker build, ACR push, hosted/prompt agent create, container start, batch eval, prompt optimization, agent.yaml, dataset curation from traces. USE FOR: deploy agent to Foundry, hosted agent, create agent, invoke agent, evaluate agent, run batch eval, optimize prompt, deploy model, Foundry project, RBAC, role assignment, permissions, quota, capacity, region, troubleshoot agent, deployment failure, create dataset from traces, dataset versioning, eval trending, create AI Services, Cognitive Services, create Foundry resource, provision resource, knowledge index, agent monitoring, customize deployment, onboard, availability, standard agent setup, capability host. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).

Quality

92%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Discovery

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong skill description that excels across all dimensions. It provides specific concrete actions, comprehensive trigger terms covering many natural user phrasings, explicit 'USE FOR' and 'DO NOT USE FOR' clauses that clearly define scope, and distinct boundaries that minimize conflict with related Azure skills. The only minor weakness is that the sheer density of keywords makes it slightly harder to parse at a glance, but this is a minor readability concern rather than a functional one.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: Docker build, ACR push, hosted/prompt agent create, container start, batch eval, prompt optimization, dataset curation from traces. These are clearly defined, actionable capabilities.	3 / 3
Completeness	Clearly answers 'what' (deploy, evaluate, manage Foundry agents with specific actions listed) and 'when' (explicit 'USE FOR' clause with extensive trigger terms, plus a 'DO NOT USE FOR' clause that further clarifies boundaries). Both dimensions are thoroughly addressed.	3 / 3
Trigger Term Quality	Excellent coverage of natural terms users would say: 'deploy agent to Foundry', 'hosted agent', 'create agent', 'invoke agent', 'evaluate agent', 'run batch eval', 'optimize prompt', 'troubleshoot agent', 'deployment failure', 'create dataset from traces', 'RBAC', 'permissions', 'quota', etc. These are terms users would naturally use.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with a clear niche (Foundry agents specifically), and explicitly delineates boundaries with 'DO NOT USE FOR' clauses pointing to alternative skills (azure-deploy, azure-prepare), which greatly reduces conflict risk.	3 / 3
	Total	12 / 12 Passed

Implementation

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-crafted hub skill that efficiently routes to sub-skills with clear lifecycle workflows, validation checkpoints, and on-demand reference loading. Its main strength is organization and progressive disclosure; its minor weakness is that the hub itself contains limited directly executable guidance, though this is appropriate given its routing purpose. The validation feedback loop and context resolution steps demonstrate thoughtful workflow design.

Dimension	Reasoning	Score
Conciseness	The skill is lean and well-structured. Every section serves a clear purpose — routing tables, lifecycle workflows, context resolution steps — with no unnecessary explanations of concepts Claude already knows. The descriptions in the sub-skill table are terse but informative.	3 / 3
Actionability	The skill provides clear routing to sub-skills and a concrete context resolution workflow (check azure.yaml, run azd env get-values, map variables), but the main file itself contains no executable code or commands beyond the azd reference. It relies heavily on sub-skills for actual execution details, which is appropriate for a hub skill but means this file alone isn't copy-paste actionable.	2 / 3
Workflow Clarity	Multi-step workflows are clearly sequenced in the Agent Lifecycle table and the Project Context Resolution section. The Validation section explicitly includes a feedback loop (run → check → diagnose via troubleshoot → fix → retry → proceed only when valid), which is critical for deployment operations.	3 / 3
Progressive Disclosure	Excellent hub structure with a clear sub-skill routing table, one-level-deep references with 'When to Use' and 'When to Load' guidance, and a separate Reference Index with explicit instructions to load on demand. No deeply nested references or monolithic content blocks.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: jonathan-vella/azure-agentic-infraops
Commit: ec7b8ff

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.