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.

80

2.56x
Quality

71%

Does it follow best practices?

Impact

100%

2.56x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/agents-v2-py/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

65%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 body is highly actionable with executable code and useful reference tables, and it is logically sectioned. Its main weaknesses are duplicated content, missing validation steps for destructive agent-version operations, and bulk reference material inlined in a single file rather than progressively disclosed.

Suggestions

Add a validation/confirmation step before delete_version (e.g., verify the targeted version/state, confirm intent) and a validate->fix->retry loop where errors can occur.

De-duplicate the body: collapse the near-identical 'Create Hosted Agent' and 'Complete Example' snippets and merge the two 'Environment Variables' sections.

Move bulk reference material (the parameter, protocol, and resource-limit tables and the async/tools variants) into one-level-deep reference files (e.g., references/parameters.md, references/async.md) and link from the body.

DimensionReasoningScore

Conciseness

Mostly efficient and free of basic-concept padding, but noticeably duplicated (two near-identical full creation examples, two 'Environment Variables' sections, repeated code_interpreter tool dicts) that could be tightened.

3 / 5

Actionability

Fully executable, copy-paste-ready code with complete imports, concrete install/env commands, a parameter table, error-cause-solution table, and sync plus async variants covering the common cases.

5 / 5

Workflow Clarity

A clear numbered sequence (imports, create, list, delete) with prerequisites exists, but destructive operations like delete_version lack validation checkpoints; per the rubric cap, destructive workflows without validation cannot score above 3.

3 / 5

Progressive Disclosure

Well-organized with clear headers, but at ~318 lines with no bundle files present, substantial reference-style material (parameter/protocol/resource tables, multiple full code examples) is inlined rather than split into one-level-deep reference files.

3 / 5

Total

14

/

20

Passed

Description

78%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 clearly states what the skill does and when to use it, with concrete, domain-specific trigger terms and low conflict risk. It could be strengthened by broadening the 'when' clause beyond agent creation and adding more natural-sounding synonyms.

Suggestions

Broaden the 'Use when' clause to cover the full lifecycle (e.g., listing, updating, deleting hosted agent versions), not just creation.

Add more user-natural synonyms alongside SDK jargon (e.g., 'container agents', 'deploy an agent image') to improve trigger coverage.

DimensionReasoningScore

Specificity

Names the domain and several concrete specifics ('container-based Foundry Agents', 'Azure AI Projects SDK', 'ImageBasedHostedAgentDefinition', 'custom container images'), sitting above anchor 3 but short of fully comprehensive action coverage.

4 / 5

Completeness

Explicitly answers both what ('Build container-based Foundry Agents with Azure AI Projects SDK') and when ('Use when creating hosted agents with custom container images'), with the 'when' concrete but narrowly scoped to creation only.

4 / 5

Trigger Term Quality

Contains natural trigger phrases ('hosted agents', 'custom container images', 'Azure AI Foundry') a user might say, though the phrasing leans technical and omits common synonyms.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche ('container-based Foundry Agents', 'ImageBasedHostedAgentDefinition', 'custom container images in Azure AI Foundry') with distinct triggers and minimal overlap risk.

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
administrakt0r/AI-Agents-Safe-Coding-Skills
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.