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.
55
62%
Does it follow best practices?
Impact
—
No eval scenarios have been run
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.
This is a solid, focused description that clearly identifies its niche (container-based Foundry Agents) and includes an explicit 'Use when' clause. Its main weakness is that it describes only one action ('build') rather than listing multiple concrete capabilities, and it could benefit from additional natural trigger terms users might use.
Suggestions
Add more specific actions beyond 'build', such as 'configure container settings, define environment variables, set up agent endpoints'.
Include additional natural trigger terms users might say, such as 'Docker image', 'deploy agent', 'containerized agent', or 'hosted agent deployment'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (container-based Foundry Agents) and a key action (build), and mentions a 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 using ImageBasedHostedAgentDefinition) 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 terms like 'container', 'Foundry Agents', 'Azure AI Projects SDK', 'custom container images', and 'Azure AI Foundry', but misses common variations users might say such as 'Docker', 'hosted agent', 'deploy agent', or 'container image agent'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly specific niche targeting container-based hosted agents in Azure AI Foundry with a named SDK class (ImageBasedHostedAgentDefinition), making it very unlikely to conflict with other skills. | 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 is highly actionable with executable code and specific SDK details, but suffers from significant redundancy—the complete example, authentication, and core workflow sections overlap heavily. It lacks validation checkpoints for what is essentially a deployment operation (checking agent state after creation, verifying ACR connectivity). The monolithic structure would benefit from splitting reference material (parameter tables, async patterns, tool configs) into separate files.
Suggestions
Remove the 'Complete Example' section or the 'Core Workflow' section—they are largely duplicative. Keep one canonical example that combines imports, creation, and verification.
Add a validation step after agent creation: poll or check `agent.state` to confirm successful deployment, and show error handling with retry logic for common failures like ImagePullBackOff.
Move the parameter reference table, resource limits table, tool configuration examples, and async pattern into a separate REFERENCE.md file, keeping only the core workflow and quick-start example in SKILL.md.
Remove the 'Authentication' standalone section since it's already demonstrated in every code example—this is redundant content Claude doesn't need repeated.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Significant verbosity throughout. The 'Complete Example' section largely duplicates the 'Core Workflow' section. The 'Resource Allocation' section repeats what's already in the parameters table. The 'Authentication' section is shown separately then repeated in every code block. Multiple tool configuration examples are overly granular for what Claude can infer. The 'Protocol Versions' section restates what's already shown in the workflow. Overall, the skill could be cut by 40-50% without losing information. | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste ready Python code with correct imports, concrete parameter values, and specific SDK class names. The parameter table, error table, and tool configuration examples give precise, actionable guidance. | 3 / 3 |
Workflow Clarity | The core workflow is clearly sequenced (imports → create → list → delete), but there are no validation checkpoints. For an operation involving container deployment and ACR permissions, there's no guidance on verifying the agent is actually running, no feedback loop for checking deployment state, and no error handling shown in the workflow steps themselves. | 2 / 3 |
Progressive Disclosure | The content is a monolithic document with no bundle files to offload detailed reference material. The parameter tables, async patterns, tool configuration examples, and complete example could all be in separate reference files. External links are provided but all substantive content is inline, making the skill unnecessarily long. | 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
95574f3
- 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.