build-sample-matrix

Build the matrix of all the samples throughout different frameworks.

Quality

62%

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

71%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 well-structured and actionable with a concrete example matrix and a validation step, though the workflow sequence is implicit and only link-level. The main defect is a dangling reference to a validate_links.py script that is not provided in the bundle.

Suggestions

Add the missing validate_links.py to a scripts/ bundle directory (or remove the reference) so the validation step is actually executable.

Lay out the workflow as an explicit numbered sequence (analyze via github-mcp-server → build matrix per rules → validate links → fix and re-run if broken) to add a clear feedback loop.

Fix typos ('Repositary' → 'Repository', 'packagfes' → 'packages') and tighten the longer table notes to lift conciseness toward 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence; the repository-table notes carry substantive domain info (sync/async conventions, folder layout) rather than restating basics, with only minor typos and slightly trimmable verbosity.	4 / 5
Actionability	It names the github-mcp-server tool, gives a copy-paste-ready example matrix template, and an explicit validation command; gaps are minor—the referenced validate_links.py is not in the bundle and matrix generation itself is an LLM task without a script.	4 / 5
Workflow Clarity	An analyze → build → validate-links sequence is present with an explicit validation checkpoint, so the batch-operation cap does not apply; minor gaps are the implicit sequence and that validation covers links rather than matrix completeness, with no retry feedback loop.	4 / 5
Progressive Disclosure	It is a short single-file skill with reasonable sections, but it references validate_links.py which is absent from the empty bundle—a broken reference—placing it at the 'some structure but references not cleanly resolved' level rather than a clean 4.	3 / 5
	Total	15 / 20 Passed

Description

53%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 clearly conveys the skill's purpose but lacks any 'when to use' trigger guidance, which caps completeness. It is specific enough to be distinct but would benefit from natural trigger phrases and synonyms.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases, e.g. 'Use when the user needs to inventory or compare SDK samples across languages and frameworks.'

Include natural synonyms a user might say ('sample matrix', 'sample inventory', 'coverage matrix') to improve trigger term quality.

Optionally list a second concrete action (e.g. 'identify missing samples') to raise specificity beyond a single action.

Dimension	Reasoning	Score
Specificity	The description names the domain ('samples throughout different frameworks') and one concrete action ('Build the matrix'), matching the anchor for domain plus 1-2 concrete actions that is not comprehensive.	3 / 5
Completeness	It clearly states what the skill does ('Build the matrix of all the samples throughout different frameworks') but provides no 'Use when...' trigger clause, so per the guidelines completeness is capped at 3.	3 / 5
Trigger Term Quality	'samples' and 'frameworks' are relevant keywords a user might say, but 'matrix' is jargon and common synonyms or variations are missing, fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Building a cross-framework sample matrix is a clear niche with minor overlap risk against related SDK skills, matching the 'mostly distinct; minor overlap risk' anchor; not a 5 because the triggers are less explicit than the 5-anchor example.	4 / 5
	Total	13 / 20 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: b82d2f2

Reviewed: 1 day 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.