azure-containerregistry-py

Azure Container Registry SDK for Python. Use for managing container images, artifacts, and repositories.

Quality

61%

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-containerregistry-py/SKILL.md

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 delivers strong, concrete code examples for the full CRUD surface of the SDK, but it is an inlined monolith: ~250 lines of API reference with no progressive disclosure, redundant boilerplate sections, and no validation checkpoints around its destructive and batch operations. Splitting detailed operation docs into a reference file and adding verify steps to delete workflows are the highest-leverage fixes.

Suggestions

Move the per-operation API detail (repository/tag/manifest operations, client operations table) into a one-level-deep reference file (e.g. references/operations.md), keeping SKILL.md as an overview with quick-start and pointers.

Add validation checkpoints to destructive/batch workflows: e.g. a dry-run pass that prints what would be deleted, an explicit confirmation gate, and verification after deletion — the cleanup recipe currently deletes immediately after printing.

Delete the boilerplate 'When to Use' and 'Limitations' sections and the 'Client Operations' table that duplicates the preceding sections, and fix the 'Upload and Download Artifacts' heading to match the download-only content.

Dimension	Reasoning	Score
Conciseness	The code examples themselves are lean, but the 'Client Operations' table (~14 lines) fully duplicates the preceding sections, and the 'When to Use' ('This skill is applicable to execute the workflow or actions described in the overview') and 'Limitations' sections are boilerplate that add no skill-specific value. This is more than minor trimming, matching 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the efficient anchor at 4.	3 / 5
Actionability	Concrete, near copy-paste-ready Python covers auth, listing, property updates, deletes, downloads, the async client, and a cleanup recipe. Minor gaps keep it below 5: several snippets use an undefined `endpoint` variable, and the 'Upload and Download Artifacts' heading promises upload but only shows download.	4 / 5
Workflow Clarity	The body centers on destructive and batch operations (delete_repository, delete_manifest, bulk cleanup of untagged manifests) but provides no validation or verification checkpoints — no dry-run, confirmation, or post-delete verification. The cleanup example's `not manifest.tags` guard is partial, but the rubric caps destructive/batch skills without validation at 3, which takes precedence.	3 / 5
Progressive Disclosure	The file is well-sectioned but is a ~250-line monolithic API reference inlined in SKILL.md with no bundle files at all (no references/, scripts/, or assets/ exist). This matches 'some structure... content that should be separate is inline' — the per-operation API detail clearly belongs in a one-level-deep reference file.	3 / 5
	Total	13 / 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 identifies a distinct niche and includes both a what and a use-for clause, but it relies on the single generic verb 'managing' and omits natural trigger synonyms (ACR, push/pull, tags, manifests). Adding concrete operations and user-facing trigger phrases would lift specificity and completeness.

Suggestions

Replace the generic verb 'managing' with 2-3 concrete operations, e.g. 'List, delete, and lock container images, tags, and manifests'.

Add natural trigger terms users would actually say — 'ACR', 'push/pull images', 'tags', 'manifests', 'clean up old images' — to the use-for clause.

Make the 'when' clause scenario-oriented rather than restating the what, e.g. 'Use when working with Azure Container Registry (ACR), pushing or pruning container images, or managing image tags and manifests.'

Dimension	Reasoning	Score
Specificity	Names the domain and objects ("container images, artifacts, and repositories") but the only action is the generic verb "managing"; it never lists concrete operations like list, delete, or upload, so it matches 'names domain and 1-2 concrete actions, but not comprehensive' rather than the several-specific-actions anchor at 4.	3 / 5
Completeness	A clear 'what' (Azure Container Registry SDK for Python, managing images/artifacts/repositories) is paired with an explicit 'Use for managing...' trigger clause, satisfying the 'when' requirement. Not 5 because the when-clause restates the what rather than giving concrete trigger phrases a user would actually say.	4 / 5
Trigger Term Quality	"container images", "artifacts", and "repositories" are relevant keywords, but common natural variations are missing — users would say "ACR", "push/pull images", "tags", "manifests", or "docker images", none of which appear. Not 4 because the coverage lacks more than 'a few' natural terms.	3 / 5
Distinctiveness Conflict Risk	"Azure Container Registry SDK for Python" carves out a clear niche — a named Azure service plus language — with triggers unlikely to fire for generic Docker/container or other Azure SDK skills, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.	5 / 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/agentic-awesome-skills
Path: skills/azure-containerregistry-py/SKILL.md
Commit: 7b534bc

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.