Name: skill-creator
Rating: 72.8 (1 reviews)
Author: microsoft

skill-creator

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.

4.57x

Quality

72%

Does it follow best practices?

Impact

96%

4.57x

Average score across 2 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/skill-creator/SKILL.md

Quality

Content

62%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 highly actionable and the creation workflow is exceptionally clear with strong validation loops, but it badly violates its own conciseness and progressive-disclosure rules: a 1313-line monolith with repeated callouts and six-language auth samples that the skill itself would flag for extraction to references.

Suggestions

Move the six full per-language authentication samples and the large Best-Practices variant table into references/auth-strategies.md (or per-language files), keeping only the Python canonical example inline, to bring the body under its own 500-line target.

De-duplicate the verbatim '🔑 Two rules' callout: state it once and reference it from the other locations instead of repeating the full block two to three times.

Extract the full 'Example: Azure SDK Skill Structure' and the deprecated/rebranded-SDK migration templates into references/output-patterns.md, leaving a one-line pointer from the main body.

Dimension	Reasoning	Score
Conciseness	At 1313 lines the body grossly exceeds its own 'Keep SKILL.md under 500 lines' rule, with the verbatim auth callout repeated ~3 times, six full language auth samples, and large variant tables that restates what an expert agent already knows; it is densely actionable but noticeably verbose with several padded/repeated sections.	2 / 5
Actionability	Provides concrete executable guidance across six languages, exact commands (pip/cargo/symlink/vally), specific file paths, verbatim callouts, and checklists; held back from a 5 because many examples use placeholder clients (ServiceClient, ExampleClient) rather than real, copy-paste-ready SDK code.	4 / 5
Workflow Clarity	The 8-step Skill Creation Process is clearly sequenced with explicit validation checkpoints (Efficiency Validation checklist, harness mock runs, vally lint/eval gates) and feedback loops for batch/regeneration operations, matching the anchor for clear sequence plus error-recovery loops.	5 / 5
Progressive Disclosure	It links to real, verified reference files (azure-sdk-patterns.md, output-patterns.md, workflows.md) and prescribes a one-level-deep structure, but inlines ~1300 lines of content that its own rules say belongs in references, leaving bulk content that should be separate inline rather than appropriately split.	3 / 5
	Total	14 / 20 Passed

Description

82%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 cleanly states both what the skill does and when to use it with concrete triggers, landing a strong, distinguishable niche. The only real gap is specificity: it names the domain and two actions but does not enumerate the broader set of concrete activities the skill actually covers.

Dimension	Reasoning	Score
Specificity	Names the domain (skill creation for AI coding agents on Azure SDKs/Foundry) and two concrete actions ('creating effective skills', 'updating existing skills'), but does not enumerate the several specific sub-activities the body covers, so it stops short of anchor 4.	3 / 5
Completeness	Explicitly answers both 'what' (guide for creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services) and 'when' ('Use when creating new skills or updating existing skills') with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Includes natural trigger phrases a user would say ('creating new skills', 'updating existing skills', 'Azure SDKs', 'Microsoft Foundry') with good coverage, but misses common synonyms like 'authoring skills' or 'skill templates' that anchor 5 expects.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (skill authoring for Azure SDK/Foundry agents) with distinct triggers and minimal overlap risk against general coding skills.	5 / 5
	Total	17 / 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 (1314 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 6 missing, 1 suspicious	Warning
referenced_paths_exist	Referenced path issues: 30 missing, 1 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: microsoft/agent-skills
Path: .github/skills/skill-creator/SKILL.md
Commit: 02e0b2f

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.