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-crafted 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 explicit redirects to alternative skills to minimize conflict. The only minor weakness is that the description is quite long and dense, though the information density is justified by the breadth of the skill's capabilities.
| 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, RBAC, role assignment, knowledge index, agent monitoring, etc. | 3 / 3 |
Completeness | Clearly answers 'what' (deploy, evaluate, manage Foundry agents with specific sub-tasks) and 'when' via an explicit 'USE FOR:' clause with extensive trigger terms, plus a 'DO NOT USE FOR:' clause that further clarifies boundaries. | 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', 'provision resource'. Covers many natural variations and phrasings. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Foundry agents specifically, with explicit exclusions ('DO NOT USE FOR: Azure Functions, App Service, general Azure deploy') and redirects to other skills (azure-deploy, azure-prepare), making it highly distinguishable and unlikely to conflict. | 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 routing/orchestration skill that excels at progressive disclosure and workflow clarity, serving as an effective dispatcher to specialized sub-skills. Its main weakness is that it's somewhat verbose in places (the context resolution section could be tighter) and lacks executable code examples in the main document, though this is partially justified by its role as a top-level router. The mandatory pre-read rule and lifecycle intent mapping are strong patterns.
Suggestions
Tighten the Project Context Resolution section — collapse the azd bootstrap table and missing-values collection into fewer lines, since Claude can infer fallback logic from concise rules.
Add a concrete one-liner command example for azd env get-values in Step 4 to make the bootstrap step immediately actionable without needing to read sub-skill docs.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient as a routing document, but includes some redundancy (e.g., the tips after the sub-skills table repeat information already in the table, and the Project Context Resolution section is quite verbose with steps that could be more terse). The agent types table and tool usage conventions are brief but borderline unnecessary for Claude. | 2 / 3 |
Actionability | The skill provides concrete workflow routing tables and a clear project context resolution procedure with specific field mappings and azd variable names. However, it delegates all actual execution to sub-skills, so the main document itself contains no executable code or commands — it's a dispatcher. The context resolution steps are actionable but lack concrete command examples (e.g., the actual azd command syntax). | 2 / 3 |
Workflow Clarity | The lifecycle table clearly maps user intents to ordered sequences of sub-skills. The Project Context Resolution is a well-sequenced 5-step process with clear decision logic (one match vs multiple vs none), fallback chains for environment resolution, and explicit bootstrap steps. The mandatory pre-read rule at the top establishes a strong validation checkpoint pattern. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure — the main skill is a clear overview/routing document with a well-organized table of 13+ sub-skills, each with a one-line description and direct link. References are one level deep and clearly signaled. Content is appropriately split between the main skill (routing, context resolution, conventions) and sub-skills (execution details). | 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/github-copilot-for-azure
- Commit
a46a937
- 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.