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, prompt optimizer workflows, 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, improve prompt, prompt optimization, prompt optimizer, improve agent instructions, optimize agent instructions, optimize system 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. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).
88
85%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
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, well-structured skill description that excels across all dimensions. It provides extensive concrete actions, comprehensive trigger terms covering many natural user phrasings, explicit 'USE FOR' and 'DO NOT USE FOR' clauses that clearly delineate scope, and clear differentiation from related skills. The only minor weakness is that the description is quite long and dense, bordering on a keyword dump, but the comprehensiveness serves the selection purpose well.
| 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, agent.yaml management, RBAC, quota management, and more. | 3 / 3 |
Completeness | Clearly answers 'what' (deploy, evaluate, manage Foundry agents with specific sub-tasks) 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', 'evaluate agent', 'optimize prompt', 'improve prompt', 'troubleshoot agent', 'deployment failure', 'create dataset from traces', 'Foundry project', 'RBAC', 'permissions'. These are terms users would naturally use when working with Foundry agents. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Foundry agents specifically, with explicit 'DO NOT USE FOR' exclusions directing Azure Functions, App Service, and general Azure deploy/prep to other skills. This makes it highly distinguishable and unlikely to conflict with adjacent skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
70%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-structured orchestration skill that excels at routing users to the correct sub-skill and providing clear workflow sequences. Its main weakness is that the hub document itself lacks concrete executable examples — nearly all actionable content is deferred to sub-skills. Some verbosity in mandatory notices and introductory text could be trimmed.
Suggestions
Add at least one concrete MCP tool invocation example in the main skill (e.g., showing the initial `foundry` discovery call mentioned in Pre-Execution Requirements) to improve actionability.
Trim the opening sentence ('This skill helps developers work with...') and consolidate the two MANDATORY blocks into one concise notice to improve token efficiency.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-organized but includes some verbose sections that could be tightened. The Project Context Resolution section (Steps 1-5) is detailed but justified given the complexity. However, some explanatory text like 'This skill helps developers work with Microsoft Foundry resources' and repeated mandatory notices add unnecessary tokens. | 2 / 3 |
Actionability | The skill provides structured workflows and clear routing tables, but the main SKILL.md itself contains almost no executable code or concrete commands — it delegates everything to sub-skills. The context resolution steps are procedural but lack concrete command examples (e.g., no actual MCP tool invocation syntax shown). The azd variable mapping table is helpful but still abstract. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with explicit ordering (create → deploy → invoke), the Agent Development Lifecycle table maps user intent to ordered workflow chains, and the Project Context Resolution has a clear 5-step sequence with conditional logic and fallback paths. Validation is handled by delegating to sub-skills that contain their own validation steps. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure — the main skill serves as a clear routing hub with a well-organized table of 13+ sub-skills, each with a description and one-level-deep reference link. Content is appropriately split between the overview and specialized sub-skill documents, with clear signaling about when to use each. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%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
- microsoft/azure-skills
- Commit
742d20b
- Reviewed
Table of Contents
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.