agent-framework-azure-ai-py

Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.

Quality

60%

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 ./skills/antigravity-agent-framework-azure-ai-py/SKILL.md

The canonical home for this skill is agent-framework-azure-ai-py in sickn33/antigravity-awesome-skills

Quality

Content

73%Weight 40%Scale 1-5

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

The content is highly actionable with executable code covering the main agent patterns and a logical progression, but it is weakened by missing referenced bundle files and inline bulk that belongs in separate files. Validation checkpoints are largely absent.

Suggestions

Create the referenced bundle files (references/tools.md, mcp.md, threads.md, advanced.md) so the signaled navigation is not broken, or remove the references if they do not exist.

Move the detailed hosted-tool and MCP reference material out of SKILL.md into those reference files to achieve genuine one-level-deep progressive disclosure.

Add an explicit validation/verification checkpoint (e.g. confirming the agent ran and inspecting result.text or error) in the core workflow to raise workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, code-forward, and assumes Claude's competence, with only minor over-explanation (e.g. the 'Conventions' bullets partly restate code). It avoids explaining basic concepts but repeats the provider/credential boilerplate across every example.	4 / 5
Actionability	It provides fully executable, copy-paste-ready async examples covering basic agents, function tools, hosted tools, streaming, threads, structured outputs, and a complete composite example, plus quick-reference tables for methods and tools.	5 / 5
Workflow Clarity	The progression from install -> env vars -> auth -> core workflow -> complete example is clearly sequenced, but there are no explicit validation/error-recovery checkpoints around the create-and-run operations, which keeps it just below a 5.	4 / 5
Progressive Disclosure	The body lists 'Reference Files' (tools.md, mcp.md, threads.md, advanced.md) but no references/, scripts/, or assets/ directories actually exist, so the signaled references are missing; meanwhile a large amount of API-reference-style content is inlined in the single file.	2 / 5
	Total	15 / 20 Passed

Description

46%Weight 40%Scale 1-5

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 concise and clearly names a distinct niche, but it lacks an explicit 'Use when...' trigger clause and natural user-facing trigger terms, leaving its 'when' guidance implicit. Specificity is adequate but not comprehensive.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when building or managing persistent agents on Azure AI Foundry with the Microsoft Agent Framework Python SDK.'

Broaden trigger term coverage with synonyms a user might say ('Azure AI agents', 'persistent agents', 'AI Foundry agent SDK').

Optionally list 1-2 more concrete actions (e.g. 'add tools and conversation threads') to raise specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain and one concrete action ('Build persistent agents') but offers no enumeration of the specific operations the skill enables (tools, threads, structured outputs), so coverage is not comprehensive.	3 / 5
Completeness	It gives a clear 'what' (build persistent agents on Azure AI Foundry) but no explicit 'when'/'Use when...' trigger clause, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	It uses the niche product names ('Azure AI Foundry', 'Microsoft Agent Framework Python SDK') but lacks the natural phrases a user would actually say, with no synonyms or common variations.	2 / 5
Distinctiveness Conflict Risk	The combination of 'Azure AI Foundry' and 'Microsoft Agent Framework Python SDK' carves a clear niche with minimal overlap risk against other skills, though it could still overlap with generic Azure-agent skills.	4 / 5
	Total	12 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	14 / 16 Passed

Repository: boisenoise/skills-collections
Path: skills/antigravity-agent-framework-azure-ai-py/SKILL.md
Commit: 19c310e

Reviewed: about 17 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.