Name: microsoft-foundry
Rating: 73.6 (1 reviews)
Author: microsoft

microsoft-foundry

Deploy, evaluate, fine-tune, and manage Foundry agents end-to-end with azd: hosted agent scaffold/run/deploy, prompt agent create, batch eval, continuous eval, prompt optimizer, Agent Optimizer scaffold, agent.yaml, dataset curation from traces, model fine-tuning (SFT/DPO/RFT). USE FOR: azd ai agent, azd provision/deploy, deploy agent, hosted agent, create agent, add tool to agent, invoke agent, evaluate agent, continuous eval, continuous monitoring, optimize prompt, improve prompt, optimize agent instructions, agent optimizer, deploy model, Foundry project, RBAC, role assignment, permissions, quota, capacity, region, troubleshoot agent, deployment failure, AI Services, create Foundry resource, provision, knowledge index, customize deployment, onboard, availability, fine-tune, SFT, DPO, RFT, training-data, grader, distillation, fine-tuned model, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Failed to scan

The risk profile of this skill

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured routing and context-resolution skill: actionable commands, a sequenced 7-step procedure with validation gates, and clean one-level-deep references. Its only weakness is repetition of routing intent across several tables that could be consolidated.

Suggestions

Consolidate the overlapping Sub-Skills, Infrastructure Lifecycle, and Agent Development Lifecycle routing tables into a single decision table to reduce repeated routing tokens.

Move the long azd-variable resolution table (Step 2) or the legacy-metadata normalization detail into a reference file so the core SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	Content is mostly efficient and free of basic-concept padding, but routing information is repeated across the Sub-Skills table, Infrastructure Lifecycle table, and Agent Development Lifecycle table, so it could be tightened.	2 / 3
Actionability	Provides concrete executable guidance — a real 'az cognitiveservices account show' command with a specific JMESPath query, azd-variable-to-resolution mapping tables, and ordered precedence rules — matching the fully-executable anchor.	3 / 3
Workflow Clarity	The 7-step context-resolution procedure is clearly sequenced with explicit precedence, one/multiple/no-match decision branches, and verification checkpoints ('verify it matches', 'verify with evaluator_catalog_get before treating', 'stop and ask which source is authoritative').	3 / 3
Progressive Disclosure	SKILL.md acts as a clear overview routing to well-signaled, one-level-deep references — the references/agent-metadata-contract.md, references/standard-agent-setup.md, and references/sdk/foundry-sdk-py.md files exist and are linked cleanly, with sub-skills organized in a navigable table.	3 / 3
	Total	11 / 12 Passed

Description

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.

The description is exemplary: concrete capabilities, an extensive natural-language trigger list, and explicit use/don't-use routing. It fully satisfies all four dimensions with no vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — 'Deploy, evaluate, fine-tune, and manage Foundry agents end-to-end with azd', 'hosted agent scaffold/run/deploy', 'prompt agent create', 'batch eval', 'continuous eval', 'SFT/DPO/RFT' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	It states what the skill does and gives explicit 'USE FOR:' and 'DO NOT USE FOR:' trigger guidance, clearly answering both what and when with explicit triggers.	3 / 3
Trigger Term Quality	The USE FOR clause gives broad natural-language coverage users would actually say ('azd ai agent', 'deploy agent', 'hosted agent', 'add tool to agent', 'fine-tune', 'optimize prompt'), matching the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	A clear Foundry-agent-via-azd niche with a 'DO NOT USE FOR' clause routing Azure Functions/App Service and general Azure deploy to other skills makes it unlikely to trigger for the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 30 missing, 28 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 1 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: microsoft/azure-skills
Commit: 2cd48ca

Reviewed: about 8 hours ago

Table of Contents

Discovery Implementation Validation

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.