CtrlK
BlogDocsLog inGet started
Tessl Logo

hosted-agents-v2-py

Build hosted agents using Azure AI Projects SDK with ImageBasedHostedAgentDefinition. Use when creating container-based agents in Azure AI Foundry.

56

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/hosted-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 content is highly actionable with comprehensive executable code and good error/best-practice guidance, but it is held back by repetition across sections, a lack of validation checkpoints around destructive operations, and a monolithic structure with no progressive disclosure into reference files.

Suggestions

Add an explicit validation/verification step before delete_version (e.g., list versions, confirm the target, then delete) and wrap creation in try/except with a retry hint to lift workflow_clarity past the destructive-operation cap of 3.

De-duplicate the ImageBasedHostedAgentDefinition examples by showing the full block once and referencing it from Resource Allocation / Tools / Complete Example sections, removing the redundant Best Practices padding to improve conciseness.

Move the complete example, async pattern, and parameter/protocol reference tables into separate reference files (e.g., EXAMPLES.md, REFERENCE.md) and link to them from a leaner overview to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is mostly concrete code but notably repetitive: the ImageBasedHostedAgentDefinition block recurs across Core Workflow, Resource Allocation, Tools Configuration, and a near-identical Complete Example, and the Best Practices section adds generic advice, fitting 'mostly efficient but includes some unnecessary explanation or could be tightened'; it is not 4 because the duplication is substantial for a 325-line skill.

3 / 5

Actionability

It provides fully executable, copy-paste-ready code covering imports, creation, listing, deletion, tools, env vars, a complete example, and an async variant, matching the anchor for fully executable guidance that covers the common cases; only trivial gaps (e.g., an early snippet uses os.environ before the os import is shown) keep it from being questionable.

5 / 5

Workflow Clarity

A numbered Core Workflow sequences imports, create, list, and delete, but the destructive delete step and creation lack explicit validation checkpoints or feedback loops; per the rubric cap for destructive/batch operations without validation, workflow clarity cannot exceed 3, and it fits the 'steps listed but validation gaps' anchor.

3 / 5

Progressive Disclosure

The document has clear section headers but is a monolithic ~325-line file with no bundle/reference files (references/, scripts/, assets/ are absent) and content like the full complete example and async pattern inlined rather than split out, matching 'some structure but could be better organized; content that should be separate is inline'; the simple-skill exception does not apply given its length.

3 / 5

Total

14

/

20

Passed

Description

62%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 concise, third-person, and clearly states both capability and trigger context, with a well-scoped niche. Its main weakness is limited action breadth and somewhat technical trigger terms that miss natural synonyms.

Suggestions

Expand the 'what' with one or two more concrete actions (e.g., list/delete agent versions, configure CPU/memory) to lift specificity from 3 to 4-5.

Add more natural user-facing trigger phrases and synonyms (e.g., 'container agents', 'deploy an agent container', 'Azure AI Foundry hosted agents') to broaden trigger-term coverage.

Make the 'Use when' clause more explicit by enumerating concrete scenarios (creating, deploying, or managing container-based agents in Azure AI Foundry) to push completeness toward 5.

DimensionReasoningScore

Specificity

The description names the domain ('hosted agents', 'Azure AI Projects SDK') and one concrete action tied to a specific class ('Build hosted agents ... with ImageBasedHostedAgentDefinition'), matching the anchor that names domain and 1-2 concrete actions without being comprehensive; it does not list multiple distinct actions so it stays below 4.

3 / 5

Completeness

It answers both 'what' ('Build hosted agents using Azure AI Projects SDK with ImageBasedHostedAgentDefinition') and 'when' ('Use when creating container-based agents in Azure AI Foundry'), matching the anchor where both are present but the 'when' could be more explicit; it is not a 5 because the trigger guidance is brief and not richly enumerated.

4 / 5

Trigger Term Quality

It includes relevant terms like 'hosted agents', 'container-based agents', and 'Azure AI Foundry' that users might say, but lacks common synonyms or variations and leans on technical jargon ('ImageBasedHostedAgentDefinition'), fitting the 'some relevant keywords but missing common variations' anchor rather than the fuller coverage of 4.

3 / 5

Distinctiveness Conflict Risk

The niche is clear (container-based hosted agents in Azure AI Foundry) with distinct triggers and low conflict risk, matching 'mostly distinct; minor overlap risk with closely related skills'; it is not 5 because it could still overlap with broader Azure AI agent skills.

4 / 5

Total

14

/

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.