Name: build-sample-matrix
Rating: 60 (1 reviews)
Author: Azure

Blog Docs Log in Get started

build-sample-matrix

Build the matrix of all the samples throughout different frameworks.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./sdk/ai/.github/skills/azure-ai-projects-sample-matrix/SKILL.md

Quality

Content

87%

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

The body is lean, actionable, and well-organized with a concrete example and a real validation script. Its main weakness is workflow clarity: the process is not explicitly sequenced and lacks an error-recovery loop for broken links.

Suggestions

Number the workflow steps explicitly (e.g. 1. enumerate samples via github-mcp-server, 2. build the matrix, 3. validate links) and add a feedback loop: if validate_links.py reports broken links, fix or remove them and re-run until all links pass.

Reference the script by its bundle path (`scripts/validate_links.py`) so the invocation is unambiguous.

Fix minor typos ("Repositary" → "Repository", "packagfes" → "packages") for clarity.

Dimension	Reasoning	Score
Conciseness	The body is lean and purposeful: a repository/samples table, a concrete example matrix, a few targeted rules, and a validation command. It assumes Claude's competence and does not pad with concepts Claude already knows. Minor typos ("Repositary", "packagfes") do not add token bloat.	3 / 3
Actionability	It gives a concrete example output matrix with real URLs, specific inclusion/exclusion rules, and a copy-paste-ready validation command (`python validate_links.py path/to/file.md`). The guidance is executable rather than abstract.	3 / 3
Workflow Clarity	Validation is present (run validate_links.py) so it is not capped for a missing checkpoint, but the analyze→build→validate sequence is implicit rather than numbered, and there is no error-recovery feedback loop describing what to do when links are broken. Not a 3 because checkpoints and recovery are not explicit; above 1 because the steps and validation are discernible.	2 / 3
Progressive Disclosure	The skill is under 50 lines with well-organized sections ("# Repositary information", "# Instruction") and a single one-level-deep script reference (scripts/validate_links.py, a real file). Per the simple-skills note, this is sufficient for a 3.	3 / 3
	Total	11 / 12 Passed

Description

50%

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 states a clear, specific purpose but lacks any "Use when..." trigger guidance and uses somewhat jargony terms. It is adequate but would benefit from explicit invocation triggers and broader natural keywords.

Suggestions

Add a "Use when..." clause naming natural triggers, e.g. "Use when building or auditing a cross-language sample matrix for the Azure AI SDKs."

Broaden trigger terms beyond "matrix" to include phrases users actually say, such as "sample inventory", "sample coverage", or "missing samples".

Optionally enumerate the concrete actions (e.g. enumerate samples per language, detect missing samples, validate links) to raise specificity.

Dimension	Reasoning	Score
Specificity	"Build the matrix of all the samples throughout different frameworks" names a single concrete action and its domain, but does not list multiple specific actions. It is not a 3 because only one action is given, and not a 1 because the action and domain are concrete rather than abstract.	2 / 3
Completeness	It states what the skill does (build a sample matrix) but has no "Use when..." or equivalent trigger guidance, which caps completeness at 2 per the judging guidelines. It is above 1 because the "what" is clearly stated.	2 / 3
Trigger Term Quality	"samples" and "frameworks" are relevant keywords a user might say, but "matrix" is somewhat jargony and common variations (e.g. "sample list", "sample inventory", "cross-language samples") are missing. Not a 3 due to thin coverage; not a 1 because the terms are natural enough.	2 / 3
Distinctiveness Conflict Risk	The niche (sample matrices across SDK frameworks) is fairly specific and unlikely to conflict broadly, but without explicit triggers it could overlap with general sample-listing skills. Not a 3 because distinct triggers are absent.	2 / 3
	Total	8 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Azure/azure-sdk-for-net
Path: sdk/ai/.github/skills/azure-ai-projects-sample-matrix/SKILL.md
Commit: fef8881

Reviewed: 2 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.