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 well-crafted skill description that excels across all dimensions. It provides comprehensive specific actions, extensive natural trigger terms in the 'USE FOR' section, and explicitly defines boundaries with 'DO NOT USE FOR' exclusions to prevent skill conflicts. The description is thorough without being padded with fluff.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Docker build, ACR push, hosted/prompt agent create, container start, batch eval, prompt optimization, prompt optimizer workflows, agent.yaml, dataset curation from traces'. These are detailed, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (deploy, evaluate, manage Foundry agents with specific actions) AND when (explicit 'USE FOR:' clause with comprehensive trigger scenarios, plus 'DO NOT USE FOR:' exclusions to prevent misuse). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'deploy agent', 'create agent', 'evaluate agent', 'optimize prompt', 'improve prompt', 'troubleshoot agent', 'deployment failure', 'RBAC', 'permissions'. Includes both technical and conversational variations. | 3 / 3 |
Distinctiveness Conflict Risk | Explicitly carves out its niche with 'DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy)' which directly prevents conflicts with related skills. The Foundry-specific focus is clear and distinct. | 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-organized orchestration skill that excels at routing users to appropriate sub-skills and providing clear workflow sequences. Its main weaknesses are moderate verbosity (some redundant explanations and tables) and limited direct actionability since most concrete guidance is delegated to sub-skills. The progressive disclosure and workflow clarity are strong points.
Suggestions
Remove redundant explanations like the agent types table (Claude knows what prompt vs hosted agents are) and consolidate the multiple 'mandatory reading' notices into one clear statement
Add at least one concrete executable example in the main skill (e.g., a quick MCP tool invocation pattern) rather than deferring all actionable content to sub-skills
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundant explanations (e.g., the mandatory reading notice is repeated in different forms, and some tables could be consolidated). The agent types table explains concepts Claude likely knows. | 2 / 3 |
Actionability | Provides good structural guidance with tables mapping intents to workflows, but lacks concrete executable code examples. The skill relies heavily on references to sub-skills rather than providing direct actionable commands in the main document. | 2 / 3 |
Workflow Clarity | Excellent workflow sequencing with clear step-by-step processes for project context resolution (Steps 1-5), explicit decision points (one match vs multiple vs none), and clear intent-to-workflow mapping tables with ordered reading requirements. | 3 / 3 |
Progressive Disclosure | Well-structured with a clear overview and one-level-deep references to sub-skills. The sub-skill table clearly signals when to use each reference, and content is appropriately split between the main skill and specialized documents. | 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
1f4304b
- 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.