azure-ai-projects-ts

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

Quality

69%

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 ./skills/azure-ai-projects-ts/SKILL.md

Quality

Content

72%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 TypeScript examples and no concept over-explanation. Its weaknesses are missing validation checkpoints around destructive operations and a large volume of inlined API reference that would benefit from progressive disclosure into separate files.

Suggestions

Add explicit validation/verification steps before destructive calls (e.g. confirm a resource exists or prompt before deleting agents, datasets, indexes, and conversations) to lift workflow clarity above 3.

Move the bulk API reference (tool-type examples and per-resource CRUD) into a separate REFERENCE.md, keeping SKILL.md as a concise overview with one-level-deep, clearly signaled links.

Remove the redundant getOpenAIClient/conversations.create block (shown in both "Getting OpenAI Client" and "Run Agent") and tighten the generic "When to Use"/"Limitations" boilerplate.

Dimension	Reasoning	Score
Conciseness	The body is dense executable code with no over-explanation of concepts Claude already knows; minor redundancy (getOpenAIClient shown in both "Getting OpenAI Client" and "Run Agent") and generic "When to Use"/"Limitations" boilerplate keep it just below lean 5-level efficiency.	4 / 5
Actionability	Fully executable, copy-paste-ready TypeScript covering the common cases—agent creation with six tool types, running/cleanup, and CRUD for connections, deployments, datasets, and indexes—matching the "fully executable, covers common cases" anchor.	5 / 5
Workflow Clarity	A sequence is present in "Run Agent" (create conversation → generate response → cleanup), but destructive operations (deleteVersion, dataset/index/conversation deletes) appear without validation checkpoints, which the rubric caps at 3.	3 / 5
Progressive Disclosure	The ~290-line body inlines substantial API reference (six tool examples and CRUD for five resources) that would naturally live in a separate reference file; section headers give some structure, but content that should be split out is inline and no bundle files exist, matching the anchor 3 case.	3 / 5
	Total	15 / 20 Passed

Description

66%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 distinct niche, with good natural keyword coverage. Its main weakness is the missing explicit "Use when…" trigger guidance, which caps completeness at 3.

Suggestions

Add a "Use when…" clause naming concrete trigger situations, e.g. "Use when building or managing Azure AI Foundry agents, connections, deployments, or evaluations in TypeScript."

Include a couple of natural synonyms/users' phrases such as "Azure AI Foundry models", "OpenAI deployments", or "TypeScript SDK" to broaden trigger coverage toward 5.

Reframe capabilities as actions (e.g. "Create and manage agents, list connections, deploy models, run evaluations") to lift specificity toward 5.

Dimension	Reasoning	Score
Specificity	Names the domain and four concrete capability areas ("agents, connections, deployments, and evaluations"), listing several specific capabilities with only minor framing gaps; not a 5 because capabilities are stated as nouns rather than concrete actions.	4 / 5
Completeness	It clearly answers "what" (a high-level SDK for Azure AI Foundry projects) but provides no "Use when…" clause or equivalent trigger guidance, which the rubric caps at 3.	3 / 5
Trigger Term Quality	"Azure AI Foundry", "agents", "deployments", and "evaluations" are natural terms a user of this stack would say; a few natural terms ("models", "OpenAI", "TypeScript", "SDK") are missing, so it stops short of comprehensive 5-level coverage.	4 / 5
Distinctiveness Conflict Risk	The Azure AI Foundry TypeScript SDK is a clear niche with low conflict risk, but the absence of an explicit trigger phrase leaves minor overlap risk with adjacent AI/SDK skills, keeping it below 5.	4 / 5
	Total	15 / 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: sickn33/antigravity-awesome-skills
Path: skills/azure-ai-projects-ts/SKILL.md
Commit: 1f67c44

Reviewed: about 15 hours 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.