azure-storage

Azure Storage Services including Blob Storage, File Shares, Queue Storage, Table Storage, and Data Lake. Answers questions about storage access tiers (hot, cool, cold, archive), when to use each tier, and tier comparison. Provides object storage, SMB file shares, async messaging, NoSQL key-value, and big data analytics. Includes lifecycle management. USE FOR: blob storage, file shares, queue storage, table storage, data lake, upload files, download blobs, storage accounts, access tiers, storage tiers, hot cool cold archive, storage tier comparison, when to use storage tiers, lifecycle management, Azure Storage concepts. DO NOT USE FOR: SQL databases, Cosmos DB (use azure-prepare), messaging with Event Hubs or Service Bus (use azure-messaging).

Quality

86%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

72%

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

A well-organized, actionable reference skill: executable CLI/MCP commands and clean tables make it immediately usable. The main weaknesses are a redundant pair of SDK pointer sections and the absence of validation checkpoints for destructive write operations.

Suggestions

Merge the duplicate '## SDK Quick References' and '## Azure SDKs' sections — both point to references/sdk-usage.md with overlapping 'For building applications…' prose; keep a single section with the per-language links and drop the redundant intro to tighten conciseness.

Add a brief validation checkpoint after write operations, e.g. after `az storage blob upload` verify with `az storage blob list --account-name ACCOUNT --container-name CONTAINER` or check the command response, since blob overwrite is effectively destructive — this lifts workflow clarity above 2.

Link references/auth-best-practices.md from the body (e.g., a short '## Authentication' pointer) so every bundle file is discoverable from the overview rather than orphaned.

Dimension	Reasoning	Score
Conciseness	The body is largely lean tables and commands, but the trailing '## SDK Quick References' and '## Azure SDKs' sections are redundant — both open with 'For building applications…' and both point to references/sdk-usage.md, so not every token earns its place. Not 3 because of this duplicative prose; not 1 because there is no concept-explaining verbosity.	2 / 3
Actionability	The CLI Fallback block gives fully executable, copy-paste-ready commands with all flags (e.g., 'az storage blob download --account-name ACCOUNT --container-name CONTAINER --name BLOB --file LOCAL_PATH'), and MCP commands are named concretely. Not 2 because the examples are complete rather than pseudocode or missing key details.	3 / 3
Workflow Clarity	A preference/fallback sequence is present (MCP Server preferred, then 'If Azure MCP is not enabled: Run /azure:setup…', then CLI Fallback), but there are no validation checkpoints, and blob upload/overwrite is effectively destructive — the rubric caps such cases at 2. Not 1 because a real branch sequence exists; not 3 because no validate/verify steps are given.	2 / 3
Progressive Disclosure	SKILL.md is a clear overview that links to one-level-deep, well-signaled references (references/sdk/*.md and references/sdk-usage.md), and all 12 cited paths resolve to real files. Not 2 because the structure is well organized and navigation is easy despite a minor orphan (references/auth-best-practices.md is not linked) and the duplicated SDK section.	3 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-structured description: it states concrete capabilities, supplies a rich set of natural trigger terms, and explicitly delineates both when to use and when not to use the skill with routing to adjacent skills. No changes needed.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'Provides object storage, SMB file shares, async messaging, NoSQL key-value, and big data analytics', 'upload files, download blobs', 'Includes lifecycle management' — matching the 'lists multiple specific concrete actions' anchor. Not 2 because the action coverage is comprehensive rather than partial.	3 / 3
Completeness	Explicitly answers both what ('Azure Storage Services including Blob Storage, File Shares… Provides object storage…') and when ('USE FOR: …' plus 'DO NOT USE FOR: …'), with explicit triggers. Not 2 because the 'when' is explicit, not merely implied.	3 / 3
Trigger Term Quality	The USE FOR list ('blob storage, file shares, queue storage, table storage, data lake, upload files, download blobs, storage accounts, access tiers, hot cool cold archive') is a strong set of natural terms a user would actually say. Not 2 because it goes beyond 'some relevant keywords' to broad coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Clear Azure Storage niche with distinct triggers and an explicit DO NOT USE FOR clause routing conflicts away ('SQL databases, Cosmos DB (use azure-prepare), messaging with Event Hubs or Service Bus (use azure-messaging)'). Not 2 because active conflict routing makes overlap with sibling skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 11 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 11 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: microsoft/azure-skills
Commit: 39464cb

Reviewed: about 5 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.