agent-framework-azure-ai-py

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

Quality

62%

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

Quality

Content

71%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 body is highly actionable with complete, executable examples and a clear setup workflow, but it is inflated by a duplicative complete example and filler sections, and its progressive disclosure is undermined by references to files that are missing from the bundle.

Suggestions

Ship the referenced files (references/tools.md, references/mcp.md, references/threads.md, references/advanced.md) or remove the 'Reference Files' section — dead pointers are worse than no references.

Cut or drastically trim the 'Complete Example' section, which re-demonstrates the weather function, hosted tools, streaming, and structured outputs already covered, and replace the content-free 'When to Use'/'Limitations' boilerplate with substantive guidance or remove it.

Add a lightweight validation checkpoint after agent creation (e.g., retrieving the agent by ID with get_agent(agent_id) to confirm it exists) to close the workflow's verification gap.

Dimension	Reasoning	Score
Conciseness	The core sections are lean and code-first, but the ~75-line 'Complete Example' duplicates patterns already shown (weather function, hosted tools, streaming, structured outputs) and the 'When to Use'/'Limitations' sections are content-free boilerplate ('This skill is applicable to execute the workflow or actions described in the overview').	3 / 5
Actionability	Fully executable, copy-paste-ready code throughout: install commands, environment variables, authentication, six complete runnable patterns, and quick-reference tables for provider methods and hosted tools.	5 / 5
Workflow Clarity	A coherent setup-to-run sequence (Installation → Environment Variables → Authentication → Core Workflow) reinforced by an architecture diagram; minor gap in that there is no verification step (e.g., confirming the agent was created) or error-handling guidance.	4 / 5
Progressive Disclosure	Section structure is good and the 'Reference Files' section clearly signals one-level-deep references, but all four referenced files (references/tools.md, mcp.md, threads.md, advanced.md) do not exist in the bundle, leaving dead pointers and inlining detail the references were meant to hold.	3 / 5
	Total	15 / 20 Passed

Description

53%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 clearly states what the skill does and targets a specific platform/SDK niche, but it lacks any 'when to use' trigger guidance and has thin keyword coverage. It reads as a topic label rather than a trigger-rich skill description.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to build agents on Azure AI Foundry, Azure AI Agent Service, or with the Microsoft Agent Framework Python SDK.'

Enumerate the concrete capabilities to raise specificity, e.g. 'create persistent agents, attach function/hosted/MCP tools, stream responses, and manage multi-turn conversation threads.'

Include natural synonyms users might say — 'AI agents', 'autonomous agents', 'multi-turn chatbot', 'Azure agent service' — to broaden trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Azure AI Foundry', 'Microsoft Agent Framework Python SDK') and one concrete action ('Build persistent agents'), but does not list several specific actions as the level-4 anchor requires.	3 / 5
Completeness	Has a clear 'what' ('Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK') but no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Contains relevant keywords like 'agents', 'Azure AI Foundry', and 'persistent', but misses natural variations users would actually say such as 'AI agents', 'chatbot', 'multi-turn', or 'autonomous agents'.	3 / 5
Distinctiveness Conflict Risk	The 'Azure AI Foundry' + 'Microsoft Agent Framework' pairing is a clear niche with mostly distinct triggers, though adjacent agent-SDK skills (OpenAI Agents, Semantic Kernel) pose minor overlap risk.	4 / 5
	Total	13 / 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: sickn33/agentic-awesome-skills
Path: skills/agent-framework-azure-ai-py/SKILL.md
Commit: 7b534bc

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.