microsoft-foundry
Deploy, evaluate, and manage Foundry agents end-to-end: Docker build, ACR push, hosted/prompt agent create, container start, batch eval, continuous eval, 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, continuous eval, continuous monitoring, continuous eval status, optimize prompt, improve prompt, prompt optimizer, optimize agent instructions, improve 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).
70
85%
Does it follow best practices?
Impact
—
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 skill description that excels across all dimensions. It provides highly specific concrete actions, comprehensive trigger terms covering many natural user phrasings, explicit 'USE FOR' and 'DO NOT USE FOR' clauses that clearly delineate scope, and proactive conflict avoidance by redirecting to alternative skills. The only minor weakness is that the description is quite dense and long, but the content is substantive rather than padded.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: Docker build, ACR push, hosted/prompt agent create, container start, batch eval, continuous eval, prompt optimizer workflows, dataset curation from traces. These are highly specific and actionable. | 3 / 3 |
Completeness | Clearly answers both 'what' (deploy, evaluate, manage Foundry agents with specific workflows) and 'when' (explicit USE FOR and DO NOT USE FOR clauses with comprehensive trigger terms). The DO NOT USE FOR clause with alternative skill references adds extra clarity. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'deploy agent', 'create agent', 'evaluate agent', 'run batch eval', 'optimize prompt', 'improve prompt', 'troubleshoot agent', 'deployment failure', 'create dataset from traces', etc. Covers many natural variations and synonyms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche around Foundry agents specifically. The explicit DO NOT USE FOR clause with redirects to 'azure-deploy' and 'azure-prepare' directly addresses potential conflicts with similar Azure-related 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 effectively routes users to appropriate sub-skills across a complex domain. Its strengths are in workflow clarity and progressive disclosure — the routing tables and lifecycle sequences are excellent. Its main weakness is that the metadata resolution section (Steps 1-5) is verbose and procedural without concrete executable examples, and could benefit from being extracted to a reference document to keep the main skill leaner.
Suggestions
Extract the detailed 'Project Context Resolution' steps (Steps 1-5) into a separate reference document (e.g., references/context-resolution.md) and replace with a concise summary in the main skill, reducing the main document by ~40%.
Add a concrete executable example for the mandatory pre-execution foundry tool discovery call, showing what the actual MCP invocation looks like rather than just describing it in prose.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured as a routing/orchestration document, but includes some verbose sections that could be tightened — particularly the lengthy metadata resolution steps (Steps 1-5) with detailed legacy migration logic and azd bootstrapping rules that could be offloaded to a reference document. The tables and routing logic are efficient, but the overall document is heavy for what is essentially a dispatcher. | 2 / 3 |
Actionability | The skill provides clear routing tables and workflow sequences, but the main document itself contains no executable code or concrete commands — it's primarily procedural prose about metadata resolution and environment selection. The actionable content is deferred to sub-skills, making this document more of an index with detailed procedural rules rather than directly executable guidance. | 2 / 3 |
Workflow Clarity | The multi-step workflows are clearly sequenced with explicit ordering (create → deploy → invoke), the project context resolution has a well-defined 5-step process with clear decision trees and fallback logic, and the infrastructure lifecycle section disambiguates user intent with explicit routing. Validation checkpoints are present (e.g., 'stop and ask the user', metadata file selection priority). | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure — the main skill serves as a clear routing hub with a well-organized table of 15+ sub-skills, each with a description and direct file reference. Content is appropriately split between the orchestration layer (this file) and specialized sub-skills. References are one level deep and clearly signaled with consistent formatting. | 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
d02fd24
- 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.