Name: skill-creator-ms
Rating: 54.400000000000006 (1 reviews)
Author: administrakt0r

skill-creator-ms

Guide for creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services. Use when creating new skills or updating existing skills.

Quality

63%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/skill-creator-ms/SKILL.md

The canonical home for this skill is skill-creator-ms in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

63%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 is a thorough, actionable guide with a clear multi-step workflow and real commands, but it violates its own conciseness/length guidance and references bundle files that are not shipped. Progressive disclosure is preached but not practiced.

Suggestions

Trim the body under 500 lines by moving the multi-language authentication snippets, the acceptance-criteria template, and the scenarios.yaml template into actual files under references/.

Create the referenced bundle files (azure-sdk-patterns.md, workflows.md, output-patterns.md, acceptance-criteria.md) so signaled references resolve to real content.

De-duplicate the DefaultAzureCredential examples — keep one language inline and point to a references/auth-patterns.md for the others.

Dimension	Reasoning	Score
Conciseness	The body runs ~620 lines, exceeding its own 'Keep SKILL.md under 500 lines' rule, and inlines repeated material (DefaultAzureCredential shown in four languages then again in the worked example) plus large templates that could be trimmed, though most content is relevant rather than padded.	3 / 5
Actionability	Provides concrete, mostly executable guidance — real commands ('pip install', 'ln -s', 'pnpm harness', 'npx tsx') and copy-paste auth code in multiple languages — but some examples use placeholder clients ('ExampleClient', 'MyClient') that are illustrative rather than runnable.	4 / 5
Workflow Clarity	The 8-step Skill Creation Process is clearly sequenced with verification checkpoints (symlink 'ls -la' check, test run with success criteria, Ralph Loop feedback for iteration) and a closing checklist, with only minor validation gaps.	4 / 5
Progressive Disclosure	References are clearly signaled ('See references/azure-sdk-patterns.md', a Design Pattern References table) but none of the referenced files (azure-sdk-patterns.md, workflows.md, output-patterns.md, acceptance-criteria.md) actually exist in the bundle, and large reference-grade content (multi-language auth, acceptance-criteria and scenarios.yaml templates) is inlined in a 620-line monolith.	3 / 5
	Total	14 / 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 clearly states its purpose and includes a 'Use when' clause, satisfying the what/when requirement with a focused Azure/Foundry niche. It is held back by limited trigger-term variety and only modest action specificity.

Suggestions

Add concrete trigger phrases users would naturally say, e.g. 'Triggers: "create Azure SDK skill", "Foundry skill", "skill template", "update skill"'.

Broaden the action list to reflect the body's full scope (e.g., 'create, categorize, test, and document skills for Azure SDKs and Microsoft Foundry').

Include synonym/file-extension style terms ('skill template', '.github/skills') to improve natural trigger matching.

Dimension	Reasoning	Score
Specificity	Names the domain ('creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services') and two concrete actions ('creating new skills', 'updating existing skills'), but coverage is not comprehensive — no mention of testing, categorization, or documentation work the body actually covers.	3 / 5
Completeness	Explicitly answers both what ('Guide for creating effective skills...') and when ('Use when creating new skills or updating existing skills'), but the 'when' trigger guidance could be more specific with concrete trigger phrases.	4 / 5
Trigger Term Quality	Includes relevant phrases ('creating new skills', 'updating existing skills', 'Azure SDKs', 'Microsoft Foundry') but misses natural variations a user might say ('make a skill', 'skill template', 'Foundry skill') and lacks file-extension or synonym coverage.	3 / 5
Distinctiveness Conflict Risk	The Azure SDK / Microsoft Foundry niche is mostly distinct with low overlap risk, though the generic 'creating new skills or updating existing skills' trigger could overlap with a non-Azure skill-creator.	4 / 5
	Total	14 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (620 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 13 missing	Warning

	Total	13 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/skill-creator-ms/SKILL.md
Commit: 57c135b

Reviewed: 20 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.