foundry-sdk-python

Build AI applications using the Azure AI Projects Python SDK (azure-ai-projects). Use when working with Foundry project clients, creating versioned agents with PromptAgentDefinition, running evaluations, managing connections/deployments/datasets/indexes, or using OpenAI-compatible clients. This is the high-level Foundry SDK - for low-level agent operations, use azure-ai-agents-python skill.

Install with Tessl CLI

npx tessl i github:microsoft/agent-skills --skill foundry-sdk-python

What are skills?

Overall
score

98%

Review — 100%

Does it follow best practices?

Validation — 13 / 16 Passed

Validation for skill structure

SKILL.md

Review

Evals

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 an excellent skill description that hits all the marks. It provides specific concrete actions, includes natural trigger terms users would search for, explicitly states both what it does and when to use it, and clearly distinguishes itself from a related skill. The explicit differentiation from the azure-ai-agents-python skill is particularly valuable for avoiding conflicts.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'creating versioned agents with PromptAgentDefinition, running evaluations, managing connections/deployments/datasets/indexes, using OpenAI-compatible clients'. These are precise, actionable capabilities.	3 / 3
Completeness	Clearly answers both what ('Build AI applications using the Azure AI Projects Python SDK') and when ('Use when working with Foundry project clients, creating versioned agents...'). Includes explicit 'Use when' clause with specific trigger scenarios.	3 / 3
Trigger Term Quality	Includes natural keywords users would say: 'Azure AI Projects', 'Python SDK', 'azure-ai-projects', 'Foundry', 'agents', 'PromptAgentDefinition', 'evaluations', 'connections', 'deployments', 'datasets', 'indexes', 'OpenAI-compatible'. Good coverage of technical terms users would naturally use.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with clear niche: explicitly names the SDK package 'azure-ai-projects', distinguishes itself from the related 'azure-ai-agents-python skill' for low-level operations. Clear boundary between high-level Foundry SDK and low-level agent operations.	3 / 3
	Total	12 / 12 Passed

Implementation

100%

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

This is an exemplary skill file that demonstrates excellent technical documentation practices. It provides comprehensive coverage of the Azure AI Projects SDK with executable code examples, clear organization through tables and sections, and appropriate progressive disclosure to reference files. The SDK comparison table is particularly valuable for helping users choose the right tool.

Dimension	Reasoning	Score
Conciseness	The content is lean and efficient, providing code examples without explaining basic concepts Claude already knows. Every section delivers actionable information without padding or unnecessary context.	3 / 3
Actionability	All code examples are fully executable and copy-paste ready with proper imports, environment variable usage, and complete method calls. The tables provide quick reference for operations and tools.	3 / 3
Workflow Clarity	The Thread and Message Flow section provides a clear numbered sequence with status checking before proceeding. The best practices section reinforces proper patterns like cleanup and context managers.	3 / 3
Progressive Disclosure	Excellent structure with a comprehensive overview in the main file and clear one-level-deep references to detailed documentation (references/agents.md, references/tools.md, etc.). Each section provides enough to get started while pointing to deeper resources.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata' field is not a dictionary	Warning
license_field	'license' field is missing	Warning
body_output_format	No obvious output/return/format terms detected; consider specifying expected outputs	Warning

	Total	13 / 16 Passed

Reviewed: about 1 month 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.