agents-v2-py
Build container-based Foundry Agents with Azure AI Projects SDK (ImageBasedHostedAgentDefinition). Use when creating hosted agents with custom container images in Azure AI Foundry.
75
62%
Does it follow best practices?
Impact
100%
2.56xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/antigravity-agents-v2-py/SKILL.mdQuality
Discovery
75%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 well-structured with a clear 'Use when' clause and targets a very specific niche (container-based hosted agents in Azure AI Foundry). Its main weakness is limited specificity of actions—it only mentions 'build' without elaborating on sub-tasks—and the trigger terms lean heavily on technical jargon without covering natural language variations users might employ.
Suggestions
Add more specific concrete actions beyond 'build', such as 'configure container images, set environment variables, define agent endpoints, deploy hosted agents'.
Include natural language trigger variations users might say, such as 'Docker agent', 'containerized agent', 'deploy agent container', or 'agent hosting'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (container-based Foundry Agents) and a key action (build), and mentions the specific SDK class (ImageBasedHostedAgentDefinition), but only describes one action rather than listing multiple concrete capabilities. | 2 / 3 |
Completeness | Clearly answers both 'what' (build container-based Foundry Agents with Azure AI Projects SDK) and 'when' (Use when creating hosted agents with custom container images in Azure AI Foundry) with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes relevant technical terms like 'container', 'Foundry Agents', 'Azure AI Projects SDK', 'ImageBasedHostedAgentDefinition', and 'custom container images', but these are fairly specialized jargon. Missing more natural variations a user might say like 'Docker', 'deploy agent', 'hosted container', or 'agent deployment'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly specific niche targeting ImageBasedHostedAgentDefinition and container-based agents in Azure AI Foundry. Very unlikely to conflict with other skills due to the narrow, well-defined scope and specific SDK class reference. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill excels at actionability with concrete, executable code examples and useful reference tables, but suffers from significant verbosity and redundancy—the same agent creation pattern appears three times with minor variations. The workflow lacks validation checkpoints (e.g., checking agent state after creation, verifying container health), and the document is too long for a SKILL.md, with content that should be split into referenced files.
Suggestions
Eliminate redundancy by showing the agent creation pattern once in the core workflow and removing the duplicate 'Complete Example' and 'Authentication' sections.
Add a validation step after agent creation (e.g., poll agent.state until it reaches 'Running' or handle failure states) to create a proper feedback loop.
Move the parameter reference table, tools configuration details, async pattern, and resource limits into a separate REFERENCE.md file, keeping only the core workflow in SKILL.md.
Remove the meaningless 'When to Use' section and trim explanatory text like 'The container_protocol_versions parameter specifies which protocols your agent supports' that Claude can infer from the code.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Significant redundancy throughout: the authentication section repeats in the core workflow and complete example, the ImageBasedHostedAgentDefinition parameters are shown in code then repeated in a table, resource allocation is explained twice, tools configuration shows three near-identical examples, and the complete example is essentially a copy of the core workflow. The 'When to Use' section is meaningless filler. | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste ready Python code with concrete imports, specific SDK classes, and real parameter values. The parameter tables, error tables, and tool configuration examples give Claude everything needed to generate working code. | 3 / 3 |
Workflow Clarity | The core workflow has clear numbered steps (imports, create, list, delete), but there are no validation checkpoints—no step to verify the agent reached a running state, no feedback loop for handling deployment failures, and no guidance on checking container health after creation. | 2 / 3 |
Progressive Disclosure | The content has reasonable section headers and some structure, but it's a monolithic document with ~200+ lines of inline content that could be split (e.g., async pattern, tools configuration, complete example could be separate references). The reference links at the bottom are good but the inline content is too heavy for a SKILL.md overview. | 2 / 3 |
Total | 8 / 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 | |
- Repository
- boisenoise/skills-collections
- Commit
636b862
- 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.