azure-ai-projects-py

Build AI applications on Microsoft Foundry using the azure-ai-projects SDK.

Quality

48%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/antigravity-awesome-skills/skills/azure-ai-projects-py/SKILL.md

Quality

Content

64%Scale 1-3

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

This is a solid, actionable SDK skill with comprehensive executable code examples covering the major features of the azure-ai-projects SDK. Its main weaknesses are the lack of error handling/validation steps in workflows and some verbosity in areas like the SDK comparison table and boilerplate sections. The progressive disclosure structure is well-conceived with many reference files but cannot be verified without the bundle.

Suggestions

Add error handling and validation checkpoints to the Thread and Message Flow section (e.g., check run.status for 'failed'/'requires_action' and show recovery steps).

Convert reference file paths to proper markdown links (e.g., `[agents](references/agents.md)`) and trim inline content that duplicates what the reference files should cover.

Remove the boilerplate 'When to Use' and 'Limitations' sections, and trim the SDK Comparison table—Claude can infer when to use which SDK from the feature descriptions.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient with good code examples, but includes some unnecessary sections like 'When to Use' and 'Limitations' boilerplate, the SDK Comparison table explaining azure-ai-agents (which isn't the focus), and the 'Best Practices' section contains guidance Claude could infer. The overall length (~250 lines) is reasonable for the breadth of coverage but could be tightened.	2 / 3
Actionability	Nearly all guidance is backed by concrete, executable Python code snippets covering authentication, agent creation, thread/message flow, tools, connections, deployments, evaluation, async usage, and memory stores. Code is copy-paste ready with proper imports and environment variable references.	3 / 3
Workflow Clarity	The Thread and Message Flow section provides a clear numbered sequence, but there's no validation or error handling for agent creation, no feedback loops for failed runs, and no guidance on what to do when run.status is not 'completed'. For operations involving resource creation and cleanup, the lack of explicit error recovery caps this at 2.	2 / 3
Progressive Disclosure	The skill references 11 separate reference files and a script, which is excellent structure in principle. However, no bundle files were provided, so these references are unverifiable. The references are listed as plain text paths rather than markdown links, and the main file includes substantial inline content that could arguably be delegated to references (e.g., the full tools overview table, SDK comparison table).	2 / 3
	Total	9 / 12 Passed

Description

32%Scale 1-3

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 identifies a specific platform and SDK but is too terse and lacks concrete actions and explicit trigger guidance. It would benefit significantly from listing specific capabilities and adding a 'Use when...' clause to help Claude distinguish this skill from other AI/Azure-related skills.

Suggestions

Add a 'Use when...' clause with trigger terms like 'Azure AI Foundry', 'azure-ai-projects', 'AI agents', 'Azure AI Studio', or 'Foundry project'.

List specific concrete actions such as 'create AI agents, manage connections, deploy models, configure evaluations, run prompt flows'.

Include common user phrasing variations like 'Azure AI', 'Foundry SDK', 'AI project', and relevant file extensions or package names to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (AI applications on Microsoft Foundry) and mentions a specific SDK (azure-ai-projects), but does not list concrete actions like 'create agents', 'deploy models', 'manage datasets', etc.	2 / 3
Completeness	Provides a brief 'what' (build AI applications using the SDK) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also weak, so this scores a 1.	1 / 3
Trigger Term Quality	Includes relevant keywords like 'Microsoft Foundry', 'azure-ai-projects', 'AI applications', and 'SDK', but misses common variations users might say such as 'Azure AI Foundry', 'Azure AI Studio', 'foundry agent', or specific task-related terms.	2 / 3
Distinctiveness Conflict Risk	The mention of 'Microsoft Foundry' and 'azure-ai-projects SDK' provides some distinctiveness, but 'Build AI applications' is broad enough to potentially overlap with other Azure or AI-related skills.	2 / 3
	Total	7 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: popey/claude-code-skills
Path: plugins/antigravity-awesome-skills/skills/azure-ai-projects-py/SKILL.md
Commit: a5a6601

Reviewed: 5 days 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.