agents-v2-py
Build container-based Foundry Agents using Azure AI Projects SDK with ImageBasedHostedAgentDefinition. Use when creating hosted agents that run custom code in Azure AI Foundry with your own container images. Triggers: "ImageBasedHostedAgentDefinition", "hosted agent", "container agent", "Foundry Agent", "create_version", "ProtocolVersionRecord", "AgentProtocol.RESPONSES", "custom agent image".
Install with Tessl CLI
npx tessl i github:haniakrim21/everything-claude-code --skill agents-v2-py84
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 100%
↑ 1.31xAgent success when using this skill
Validation for skill structure
Discovery
89%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 a well-structured skill description with strong completeness and excellent trigger term coverage for Azure AI Foundry container agents. The main weakness is limited specificity in describing concrete actions - it focuses on 'build' but doesn't enumerate specific capabilities like deployment, versioning, or configuration operations that the skill might support.
Suggestions
Add 2-3 more concrete actions beyond 'build' (e.g., 'deploy container agents, manage versions, configure agent protocols') to improve specificity
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Azure AI Foundry container agents) and mentions specific SDK components like 'ImageBasedHostedAgentDefinition' and 'Azure AI Projects SDK', but doesn't list multiple concrete actions beyond 'build' - lacks detail on what operations can be performed. | 2 / 3 |
Completeness | Clearly answers both what ('Build container-based Foundry Agents using Azure AI Projects SDK') and when ('Use when creating hosted agents that run custom code in Azure AI Foundry with your own container images') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural and technical terms users would say: 'hosted agent', 'container agent', 'Foundry Agent', plus specific API terms like 'ImageBasedHostedAgentDefinition', 'create_version', 'ProtocolVersionRecord', and 'custom agent image'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific Azure AI Foundry terminology and container-based agent focus. The combination of 'ImageBasedHostedAgentDefinition', 'Foundry Agent', and container-specific triggers creates a clear niche unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%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 skill with excellent executable code examples and comprehensive parameter documentation. The main weaknesses are some content redundancy (duplicate environment variables section, repeated authentication patterns) and missing validation checkpoints in the workflow. The document would benefit from splitting detailed reference material into separate files.
Suggestions
Add validation steps after agent creation (e.g., verify agent.state, poll until ready, handle creation failures with retry logic)
Remove the duplicate 'Environment Variables (2)' section and consolidate environment variable guidance in one place
Move detailed reference tables (parameters, resource limits, common errors) to a separate REFERENCE.md file and link to it
Add error handling wrapper around the core workflow example showing how to catch and recover from common errors
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with good code examples, but includes some redundancy (e.g., 'Environment Variables' section appears twice, authentication shown multiple times, and the complete example largely duplicates earlier code snippets). | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready Python code with complete imports, proper async patterns, and specific parameter tables. All examples are concrete and immediately usable. | 3 / 3 |
Workflow Clarity | Steps are clearly numbered (1-4) for the core workflow, but lacks validation checkpoints for the multi-step process. No verification that the agent was created successfully beyond printing state, and no error handling in the main workflow examples. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear sections and tables, but the document is quite long (~250 lines) with detailed API reference inline. The async pattern, tools configuration, and resource allocation details could be split into separate reference files. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%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 | |
- 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.