Name: skill-creator
Rating: 70.28 (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

68%

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 1-3

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

The body is highly actionable with clear, validated workflows and well-organized one-level references, but it is severely over-length and verbose, explaining known concepts and repeating material its own rules say to externalize.

Suggestions

Trim the body under its stated 500-line ceiling by moving the per-language authentication code blocks and the Rust best-practices deep-dive into references/azure-sdk-patterns.md.

Remove or de-duplicate the verbatim auth callout and Rust rule repetitions; reference a single canonical source instead of restating.

Cut conceptual framing ("Skills are modular knowledge packages...", token-cost justifications on every anti-pattern) since Claude already knows this; keep only guidance Claude would not infer.

Dimension	Reasoning	Score
Conciseness	At ~1,313 lines the body is far beyond its own 500-line ceiling, explains concepts Claude already knows ("Skills are modular knowledge packages that transform general-purpose agents into specialized experts"), and repeats content verbatim (the auth callout and Rust rules appear multiple times), matching the "verbose; explains concepts Claude knows; padded" anchor.	1 / 3
Actionability	Provides fully executable, copy-paste-ready code in six languages, real bash commands (pip install, ln -s, pnpm harness, rg), bundled scripts (init_skill.py, package_skill.py, quick_validate.py), frontmatter templates, and concrete checklists, matching the top anchor.	3 / 3
Workflow Clarity	The Skill Creation Process (Steps 1-8) and Regeneration Workflow are explicitly sequenced with validation gates (vally lint/eval, harness mock runs, API-surface parity checks) and error-recovery feedback loops, matching the "clear sequence with explicit validation steps" anchor.	3 / 3
Progressive Disclosure	References are real, one level deep, and well signaled (Design Pattern References table points to azure-sdk-patterns.md, output-patterns.md, workflows.md; scripts present), but the main file is overstuffed with content its own Reference Extraction Guide says belongs in /references/ (multi-language auth blocks, Rust deep-dive, batch recipe), fitting the "content that should be separate is inline" anchor.	2 / 3
	Total	9 / 12 Passed

Description

75%Weight 40%Scale 1-3

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 answers what and when in third person with a clear, low-conflict niche. Its weaknesses are narrow trigger term coverage and a lack of multiple specific concrete actions.

Suggestions

Broaden trigger terms to include natural phrasings users would say, e.g. "Azure SDK skill", "skill template", "Foundry skill", "skill scaffolding".

Add 2-3 concrete actions the skill performs (e.g., "scaffold skill folders, generate acceptance criteria, validate token budgets") to raise specificity to the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain ("AI coding agents", "Azure SDKs", "Microsoft Foundry services") and an action ("creating effective skills"), but does not enumerate multiple concrete actions like extraction/filling/merging, matching the "names domain and some actions" anchor.	2 / 3
Completeness	Explicitly answers both what ("Guide for creating effective skills...") and when ("Use when creating new skills or updating existing skills"), matching the "clearly answers both what AND when" anchor.	3 / 3
Trigger Term Quality	Includes "Use when creating new skills or updating existing skills" with reasonable natural phrases, but trigger coverage is narrow and omits common variations users might say (e.g., Azure SDK skill templates, Foundry skill authoring).	2 / 3
Distinctiveness Conflict Risk	The Azure SDK / Microsoft Foundry skill-authoring niche is specific and tied to distinct triggers, making it unlikely to fire for unrelated skills.	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 (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: 4a2873f

Reviewed: 3 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.