Name: azure-openai-service
Rating: 56.8 (1 reviews)
Author: membranedev

azure-openai-service

Azure OpenAI Service integration. Manage Models, Deployments, Prompts, Completions. Use when the user wants to interact with Azure OpenAI Service data.

Quality

65%

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-openai-service/SKILL.md

Quality

Content

67%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.

A well-structured, actionable integration guide with concrete CLI commands and a clear connection-readiness workflow. The main weakness is an unnecessary marketing-fluff intro paragraph that wastes tokens.

Suggestions

Replace the marketing-fluff intro paragraph ("powerful language models", "enterprise-grade security, compliance, and scalability") with a one-line statement of what the skill does, since Claude already knows what Azure OpenAI is.

Label the workflow steps explicitly (Step 1: install/auth, Step 2: search actions, Step 3: run) so the "skip to Step 2" reference resolves unambiguously.

Move the popular-actions table and proxy-options reference into a separate references file to keep SKILL.md a lean overview, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The core CLI workflow sections are tight and command-driven, but the opening paragraph ("Azure OpenAI Service provides access to OpenAI's powerful language models... enterprise-grade security, compliance, and scalability") is marketing fluff that pads the skill with concepts Claude already knows.	3 / 5
Actionability	Mostly executable, copy-paste-ready commands with concrete flags (e.g. `membrane connection ensure "..." --json`, `membrane action run <actionId> --input '{...}'`) plus a full proxy-options table; minor gaps from placeholders and the vague directive "Use action names and parameters as needed."	4 / 5
Workflow Clarity	A clear sequenced flow (install → login → connect → search → run) with an explicit state-polling feedback loop (BUILDING/CLIENT_ACTION_REQUIRED/READY) for error recovery; the "skip to Step 2" reference points at an unlabeled step, a minor checkpoint gap.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections with no nested external references and no bundle files to manage; the popular-actions table and proxy options are somewhat reference-like and could be split out, but single-file inlining is acceptable here.	4 / 5
	Total	15 / 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 answers both what and when with a distinct named-service trigger, but its capabilities are stated through one generic verb and it omits the natural model/task terms users would actually say.

Suggestions

Replace the single generic verb "Manage" with concrete actions (e.g. "Create chat and text completions, generate images, transcribe audio, list and deploy models").

Add natural trigger terms users say, such as "GPT", "chat completions", "embeddings", "DALL-E", or "Whisper", not just resource nouns.

Sharpen the "Use when" clause beyond the circular "interact with Azure OpenAI Service data" to name concrete intents (e.g. generating completions, transcribing audio, creating embeddings).

Dimension	Reasoning	Score
Specificity	"Manage Models, Deployments, Prompts, Completions" names the domain and several resource nouns but applies only one generic verb ("Manage"), so concrete actions are implied rather than enumerated — matching the domain-plus-1-2-actions anchor rather than comprehensive coverage.	3 / 5
Completeness	It has both a clear "what" ("Manage Models, Deployments, Prompts, Completions") and an explicit "when" ("Use when the user wants to interact with Azure OpenAI Service data"), but the trigger is somewhat circular and could be more specific, fitting the both-present-but-when-could-be-sharper anchor.	4 / 5
Trigger Term Quality	"Azure OpenAI Service", "Models, Deployments, Prompts, Completions", and "interact with Azure OpenAI Service data" give some relevant keywords, but common natural variations the body itself uses (chat, GPT, embeddings, DALL-E, Whisper) are absent.	3 / 5
Distinctiveness Conflict Risk	"Azure OpenAI Service" is a clearly named niche with distinct triggers and low conflict risk, though a generic OpenAI or broader Azure AI skill could still overlap on closely related requests.	4 / 5
	Total	14 / 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: membranedev/application-skills
Path: skills/azure-openai-service/SKILL.md
Commit: f484c82

Reviewed: 8 minutes 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.