azure-ai-projects-ts

High-level SDK for Azure AI Foundry projects with agents, connections, deployments, and evaluations.

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/azure-ai-projects-ts/SKILL.md

The canonical home for this skill is azure-ai-projects-ts in sickn33/agentic-awesome-skills

Quality

Content

57%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 a concrete, mostly copy-paste-ready TypeScript reference across all operation groups, but it repeats boilerplate and keeps the full API detail inlined rather than progressively disclosed. Destructive and batch operations lack validation checkpoints, capping workflow clarity.

Suggestions

Factor the repeated agent-creation boilerplate (kind: 'prompt', model: 'gpt-4o') into a single base example and show only the differing tool fields, to reduce conciseness noise.

Add validation/checkpoint steps for destructive and batch operations (e.g., confirm a deployment exists before deleting, check dataset version list before delete), or document a verify-then-delete feedback loop.

Move the bulk per-tool agent examples and API reference into a references file (e.g., references/agents.md) and signal it one level deep from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly example-driven and avoids concept over-explanation, but repeats boilerplate agent-creation code across six tool examples and re-shows getOpenAIClient() under Run Agent, which could be tightened.	3 / 5
Actionability	Provides concrete, copy-paste TypeScript with real imports, method signatures, and parameter shapes for every operation group, with only minor gaps such as undefined helper variables (vectorStoreId, connectionId).	4 / 5
Workflow Clarity	The Run Agent section gives a rough create-respond-cleanup sequence, but destructive/batch operations (deleteVersion, dataset/index delete, list iterations) lack validation checkpoints, capping workflow clarity at 3.	3 / 5
Progressive Disclosure	The body has clear section headers and is navigable, but ~285 lines of per-tool examples and API reference are inlined in SKILL.md with no external references signaled and no bundle files to split the detail into.	3 / 5
	Total	13 / 20 Passed

Description

71%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 specific and well-scoped to a named SDK with four concrete capability areas, but it omits any 'when to use' trigger guidance, leaving completeness capped at 3. Trigger-term coverage is good but lacks natural synonyms and variations.

Suggestions

Add an explicit 'Use when...' clause naming the trigger situations (e.g., 'Use when building TypeScript apps on Azure AI Foundry that need agents, connections, deployments, or evaluations').

Include natural synonyms and variations users might say, such as 'Azure AI', 'AI Foundry', 'TypeScript SDK', and 'models', to broaden trigger-term coverage.

Reduce overlap risk with generic agent skills by leading with the 'Azure AI Foundry' product qualifier before the broad terms 'agents' and 'evaluations'.

Dimension	Reasoning	Score
Specificity	Names the domain (Azure AI Foundry SDK) and enumerates four concrete capability areas — agents, connections, deployments, and evaluations — giving comprehensive coverage of the SDK's operation groups.	5 / 5
Completeness	Clearly states what the SDK does but provides no 'Use when...' trigger clause, so per the missing-trigger guidance completeness is capped at 3.	3 / 5
Trigger Term Quality	Includes good domain keywords a user would say ('Azure AI Foundry', 'agents', 'connections', 'deployments', 'evaluations') but misses common natural variations and synonyms (e.g., 'Azure AI', 'TypeScript', 'models', file extensions).	4 / 5
Distinctiveness Conflict Risk	Tied to a specific named product niche with distinct triggers, but the broad terms 'agents' and 'evaluations' create minor overlap risk with general AI/agent skills.	4 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/azure-ai-projects-ts/SKILL.md
Commit: debb2ec

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.