azure-ai-agents-python
Build AI agents using the Azure AI Agents Python SDK (azure-ai-agents). Use when creating agents hosted on Azure AI Foundry with tools (File Search, Code Interpreter, Bing Grounding, Azure AI Search, Function Calling, OpenAPI, MCP), managing threads and messages, implementing streaming responses, or working with vector stores. This is the low-level SDK - for higher-level abstractions, use the agent-framework skill instead.
Install with Tessl CLI
npx tessl i github:microsoft/agent-skills --skill azure-ai-agents-python99
Does it follow best practices?
Validation for skill structure
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 capabilities, includes natural trigger terms with the SDK name, has an explicit 'Use when' clause with multiple scenarios, and proactively distinguishes itself from a related skill to prevent conflicts. The description is comprehensive yet concise.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Build AI agents', 'creating agents hosted on Azure AI Foundry', 'managing threads and messages', 'implementing streaming responses', 'working with vector stores'. Also enumerates specific tools (File Search, Code Interpreter, Bing Grounding, Azure AI Search, Function Calling, OpenAPI, MCP). | 3 / 3 |
Completeness | Clearly answers both what ('Build AI agents using the Azure AI Agents Python SDK') and when ('Use when creating agents hosted on Azure AI Foundry with tools...'). Includes explicit 'Use when' clause with multiple trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'Azure AI Agents', 'azure-ai-agents', 'Azure AI Foundry', specific tool names, 'threads', 'messages', 'streaming', 'vector stores'. Also includes the package name in parentheses for exact matching. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche (Azure AI Agents SDK specifically). Explicitly differentiates from related skills by noting 'This is the low-level SDK - for higher-level abstractions, use the agent-framework skill instead', reducing conflict risk. | 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 efficiently covers the Azure AI Agents SDK with executable code examples, clear workflow documentation, and well-organized progressive disclosure. The content assumes Claude's competence, provides actionable guidance throughout, and appropriately delegates detailed patterns to reference files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, providing only necessary code examples and configuration without explaining concepts Claude already knows. No padding or unnecessary context about what agents or SDKs are. | 3 / 3 |
Actionability | All examples are fully executable with complete imports, proper variable references, and copy-paste ready code. The minimal example shows the complete workflow with numbered steps. | 3 / 3 |
Workflow Clarity | The core workflow is explicitly stated ('create agent → create thread → create message → create run → get response') with numbered steps in the minimal example. Cleanup is included, and the workflow is clear for this non-destructive operation. | 3 / 3 |
Progressive Disclosure | Excellent structure with a concise overview in the main file and clear one-level-deep references to detailed documentation (tools.md, streaming.md, async-patterns.md). The tools table provides quick orientation before pointing to details. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
87%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 |
|---|---|---|
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
Total | 14 / 16 Passed | |
- Reviewed
Table of Contents
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.