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).
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 skill description that excels across all dimensions. It provides highly specific concrete actions, extensive natural trigger terms covering many user phrasings, explicit USE FOR/DO NOT USE FOR clauses that clearly delineate scope, and proactive conflict resolution by redirecting to alternative skills. The only minor concern is that the sheer volume of trigger terms borders on exhaustive listing, but each term is relevant and distinct.
| 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 extensive 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 phrasings. | 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 hub/dispatcher skill that excels at progressive disclosure and workflow clarity, routing users to appropriate sub-skills based on intent. Its main weakness is moderate verbosity in the metadata resolution section, which includes detailed legacy migration logic that adds length. The skill is more of an orchestration layer than a directly actionable skill, which limits its actionability score since the concrete execution details live in sub-skills.
Suggestions
Tighten the metadata resolution section (Steps 1-5) — the legacy testSuites/testCases migration logic and multi-environment rewrite rules could be moved to the agent-metadata-contract.md reference document to reduce the main skill's token footprint.
Consider condensing the repeated MANDATORY callouts into a single prominent section at the top rather than having two separate mandatory blocks.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-organized but includes some verbose sections that could be tightened. The metadata resolution steps (Steps 1-5) are quite detailed with legacy migration logic that adds significant length. The tables are efficient, but the mandatory pre-execution callouts are repeated, and some explanatory text could be trimmed. | 2 / 3 |
Actionability | The skill provides concrete routing tables and metadata resolution logic, but it's primarily a dispatcher to sub-skills rather than containing executable code or commands itself. The metadata resolution steps are specific but procedural/instructional rather than providing copy-paste ready commands. The actual actionable content lives in referenced sub-skills. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with explicit ordering (e.g., create → deploy → invoke), the metadata resolution has a well-defined 5-step process with clear priority ordering and fallback logic, and there are validation checkpoints (e.g., prompting user when ambiguous, checking for missing values). The infrastructure lifecycle includes disambiguation via AskUserQuestion. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure. The main skill serves as a clear routing hub with a well-organized table of 14+ sub-skills, each with a description and direct file reference. Content is appropriately split between the overview (routing, context resolution, conventions) and detailed sub-skills. References are one level deep and clearly signaled. | 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
771a666
- 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.