CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

63

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/antigravity-agents-v2-py/SKILL.md

The canonical home for this skill is agents-v2-py in sickn33/antigravity-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

68%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 content is highly actionable with executable code and helpful error tables, and is well structured, but it loses points for redundant example repetition, generic closing boilerplate, and a missing validation checkpoint before the destructive delete operation.

Suggestions

Remove the standalone 'Complete Example' (or replace it with only the delta) since it duplicates the 'Create Hosted Agent' workflow, and rewrite the generic 'When to Use'/'Limitations' boilerplate into skill-specific guidance to tighten conciseness.

Add an explicit validation/checkpoint before delete_version (e.g., list_versions to confirm state, then delete only when state is as expected) to lift workflow clarity above the destructive-operation cap of 3.

Consider moving the full parameter reference, async pattern, and multi-tool variants into separate reference files linked from SKILL.md to improve progressive disclosure toward 5.

DimensionReasoningScore

Conciseness

The body is mostly code and tables with little concept-explanation padding, but the 'Complete Example' largely repeats the 'Create Hosted Agent' snippet and the 'When to Use'/'Limitations' sections are generic boilerplate ('applicable to execute the workflow or actions described in the overview'), so it is mostly efficient but has notable redundancy that could be tightened — matching level 3 rather than the 'minor instances' level 4.

3 / 5

Actionability

It provides fully executable, copy-paste-ready code (install command, auth, create/list/delete, async pattern), parameter tables, and a Common Errors table with causes and solutions covering the common cases, matching the 'fully executable; copy-paste ready' anchor.

5 / 5

Workflow Clarity

Steps are clearly sequenced (Prerequisites, Core Workflow 1-4, Complete Example), but the destructive delete_version operation has no validation checkpoint or confirm-state-before-delete step, so per the rubric's destructive-operation cap workflow clarity cannot exceed 3 even though the sequence is otherwise clear.

3 / 5

Progressive Disclosure

Content is well-organized into clearly headed sections with external reference links and no nested/broken references; no bundle files exist to split further. It sits at 'good structure; minor organization gaps' rather than 5 because the long single-file body (async, multiple tool variants, full API parameter reference) could plausibly be split into reference files.

4 / 5

Total

15

/

20

Passed

Description

82%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 is well-formed with a clear what/when structure, third-person voice, and a distinctive niche. Its only weakness is listing a single concrete action rather than several, which limits the specificity score.

Suggestions

Expand the 'what' clause to list 2-3 concrete actions (e.g., create, list, and delete hosted agent versions) to lift specificity from 3 toward 4-5.

Add a couple of natural synonyms or related phrasings (e.g., 'containerized agents', 'image-based hosted agents') to push trigger term coverage from good to comprehensive.

DimensionReasoningScore

Specificity

It names the domain and one concrete action ('Build container-based Foundry Agents') plus the specific construct (ImageBasedHostedAgentDefinition), but lists only a single action rather than several, matching the '1-2 concrete actions, not comprehensive' anchor and falling below the 'several specific actions' level 4.

3 / 5

Completeness

It explicitly states what it does ('Build container-based Foundry Agents with Azure AI Projects SDK...') and when to use it ('Use when creating hosted agents with custom container images...') with concrete trigger phrases, matching the 'clearly and explicitly answers both what AND when' anchor.

5 / 5

Trigger Term Quality

'Use when creating hosted agents with custom container images in Azure AI Foundry' gives good, natural keyword coverage (hosted agents, custom container images, Azure AI Foundry), missing only minor synonyms/variations, so it sits above level 3 but below the comprehensive-synonym level 5.

4 / 5

Distinctiveness Conflict Risk

The niche is narrow and distinctive (Azure AI Foundry hosted agents with custom container images via a specific SDK class), making conflict with other skills unlikely, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.

5 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
boisenoise/skills-collections
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.