Name: skill-creator
Rating: 58.4 (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.

Quality

68%

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 ./.github/skills/skill-creator/SKILL.md

Quality

Content

62%

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

The skill is highly actionable and workflow-clear, with concrete code, verbatim callouts, explicit validation gates, and real one-level-deep reference files. Its dominant weakness is conciseness: it is a 1311-line body that violates its own 500-line guidance and restates the same rules repeatedly.

Suggestions

Move the large embedded templates (Authentication Pattern multi-language samples, Example Azure SDK Skill Structure, Handling Deprecated SDKs) into reference files and keep SKILL.md as an overview with links, to bring the body back under its 500-line target.

De-duplicate the DefaultAzureCredential callout: state it once as a verbatim block and reference it instead of repeating the full text in the example structure and Best Practices sections.

Consolidate the overlapping checklists (Efficiency Validation, Step 4 QA, final Checklist) into a single canonical checklist to cut repetition and token cost.

Dimension	Reasoning	Score
Conciseness	At 1311 lines the body far exceeds its own stated 500-line limit and is heavily padded: it restates the DefaultAzureCredential callout verbatim multiple times, explains concepts an agent already knows, and includes verbose token-cost annotations and long checklists, matching the 'verbose; explains concepts Claude knows; padded with unnecessary context' anchor.	1 / 3
Actionability	It provides concrete, copy-paste-ready guidance — real multi-language code samples, an exact section order, a verbatim callout block to insert, specific token-budget tables, and executable commands such as 'pnpm harness <skill> --mock', 'cargo add', symlink commands, and 'vally lint' — matching the 'fully executable code/commands; specific examples; copy-paste ready' anchor despite some placeholder client names.	3 / 3
Workflow Clarity	The 8-step Skill Creation Process is clearly sequenced with explicit validation checkpoints and feedback loops — the REQUIRED Efficiency Validation checklists, API Surface Parity Gate, Scenario Coverage Gate, and 'validate then run Vally eval' flow — matching the 'clear sequence with explicit validation steps; feedback loops for error recovery; checklists' anchor.	3 / 3
Progressive Disclosure	It signals real one-level-deep references in a Design Pattern References table (workflows.md, output-patterns.md, azure-sdk-patterns.md — all verified present) plus bundled scripts, but the main body is a monolithic 1311-line wall of text containing large templates and guidance that should itself be split into reference files, fitting 'some structure but content that should be separate is inline' rather than the clean-overview anchor at 3.	2 / 3
	Total	9 / 12 Passed

Description

75%

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 is third-person, answers both what and when with an explicit 'Use when' trigger, and carves out a clear niche unlikely to conflict with other skills. It is held back only by abstract verb choice and limited concrete action enumeration in the trigger terms.

Suggestions

Replace the abstract 'Guide for creating' with concrete actions, e.g. 'Scaffold, structure, and validate skills for AI coding agents working with Azure SDKs and Microsoft Foundry services'.

Add trigger-term variations that surface the Azure/Foundry angle a user would naturally say, such as 'Use when creating or updating an Azure SDK skill, generating skill frontmatter, or organizing skill references.'

Dimension	Reasoning	Score
Specificity	The description names the domain ('creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services') and the broad action ('creating new skills or updating existing skills'), but uses the abstract verb 'Guide for creating' and does not list multiple specific concrete actions, matching the 'names domain and some actions' anchor rather than the multi-action anchor at 3.	2 / 3
Completeness	It answers both 'what' (guide for creating skills for AI coding agents working with Azure SDKs and Foundry) and 'when' via the explicit 'Use when creating new skills or updating existing skills' trigger, matching the 'clearly answers both what AND when with explicit triggers' anchor.	3 / 3
Trigger Term Quality	It includes relevant natural triggers ('creating new skills', 'updating existing skills') that a user might say, but lacks common variations and does not surface the Azure SDK / Foundry angle in the trigger, fitting 'some relevant keywords but missing common variations' rather than the full-coverage anchor at 3.	2 / 3
Distinctiveness Conflict Risk	'Creating skills for AI coding agents' is a clear niche with distinct triggers ('creating new skills', 'updating existing skills') scoped to Azure SDKs and Foundry, making it unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 12 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 (1312 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: 9ccaf7c

Reviewed: about 10 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.