azure-ai-projects-ts

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

Quality

48%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/azure-ai-projects-ts/SKILL.md

Quality

Discovery

32%

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 identifies the domain (Azure AI Foundry) and lists high-level capability areas but lacks concrete action verbs, explicit trigger guidance, and a 'Use when...' clause. It reads more like a tagline than a functional description that would help Claude reliably select this skill from a large pool of options.

Suggestions

Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks about Azure AI Foundry projects, creating AI agents, managing Azure AI connections, or running model evaluations.'

Replace the abstract noun list with concrete action verbs, e.g., 'Creates and manages AI agents, configures project connections, deploys models, and runs evaluation pipelines in Azure AI Foundry.'

Include natural keyword variations users might say, such as 'azure-ai-projects SDK', 'Azure AI project', 'AI Foundry agent', or 'model deployment on Azure'.

Dimension	Reasoning	Score
Specificity	Names the domain (Azure AI Foundry) and lists some capabilities (agents, connections, deployments, evaluations), but these are high-level category names rather than concrete actions. No verbs describe what specific operations are performed.	2 / 3
Completeness	Partially addresses 'what' at a high level but completely lacks a 'when' clause or any explicit trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also weak, so this scores a 1.	1 / 3
Trigger Term Quality	Includes relevant keywords like 'Azure AI Foundry', 'agents', 'connections', 'deployments', and 'evaluations' that users might mention, but misses common variations like 'Azure AI SDK', 'AI project', 'azure-ai-projects', or specific task-oriented terms users would naturally say.	2 / 3
Distinctiveness Conflict Risk	The mention of 'Azure AI Foundry' provides some distinctiveness, but the broad terms like 'agents', 'deployments', and 'evaluations' could overlap with other Azure or AI-related skills. It's somewhat specific but not clearly delineated.	2 / 3
	Total	7 / 12 Passed

Implementation

64%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a solid API reference skill with excellent actionability—nearly every section provides executable TypeScript code. Its main weaknesses are the lack of validation/error-handling guidance in multi-step workflows and the monolithic structure that inlines extensive tool examples rather than splitting them into referenced files. Some generic boilerplate sections ('When to Use', 'Limitations') waste tokens without adding value.

Suggestions

Add error handling and validation checkpoints to the 'Run Agent' workflow (e.g., check agent creation success, handle authentication failures, verify conversation creation before generating responses).

Remove the generic 'When to Use' and 'Limitations' sections—they are boilerplate that Claude doesn't need and waste token budget.

Consider splitting the extensive 'Agent with Tools' examples into a separate AGENT_TOOLS.md reference file, keeping only one or two examples inline with pointers to the full reference.

Dimension	Reasoning	Score
Conciseness	The content is mostly efficient with executable code examples, but includes some unnecessary sections like 'When to Use' and 'Limitations' that are generic boilerplate adding no value. The 'Best Practices' section contains some obvious advice (e.g., 'don't hardcode credentials'). The operation groups table is useful but some sections like Connections and Deployments could be slightly tighter.	2 / 3
Actionability	Nearly all guidance is concrete and executable with copy-paste ready TypeScript code. Authentication, agent creation with multiple tool types, running agents, CRUD operations for datasets/indexes/connections/deployments are all demonstrated with specific, complete code examples.	3 / 3
Workflow Clarity	The 'Run Agent' section shows a multi-step workflow (create conversation → generate response → cleanup) which is clear, but lacks validation checkpoints. There's no error handling guidance, no verification that agent creation succeeded before running, and no feedback loops for common failure modes like authentication errors or missing deployments.	2 / 3
Progressive Disclosure	The content is well-structured with clear section headers and a logical progression from setup to specific operations. However, with no bundle files, the entire SDK reference is inlined in a single file (~250 lines), and sections like the extensive agent tools examples could benefit from being split into a separate reference file.	2 / 3
	Total	9 / 12 Passed

Validation

90%

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 — 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: sickn33/antigravity-awesome-skills
Commit: 9e5d4dd

Reviewed: 6 days 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.