Name: skill-creator
Rating: 68.47 (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.

2.29x

Quality

—

Does it follow best practices?

Impact

92%

2.29x

Average score across 1 eval scenario

Securityby

Passed

No known issues

Quality

Content

77%

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 concrete templates and a well-sequenced, validated workflow, but it is overlong and repeats the auth guidance across multiple sections rather than offloading detail to its reference files.

Suggestions

Move the verbatim auth callout block, the six-language authentication examples, and the Rust best-practices list into a reference file (e.g. references/azure-sdk-patterns.md) and link to it, cutting the body toward the 500-line target.

De-duplicate the DefaultAzureCredential / AZURE_TOKEN_CREDENTIALS guidance, which currently appears in the callout, the all-languages section, and the best-practices section.

Relocate the test-creation subsections (acceptance-criteria format and scenarios.yaml schema) to a reference file such as references/workflows.md, keeping only the harness command summary inline.

Dimension	Reasoning	Score
Conciseness	Most content is specialized Azure-SDK knowledge Claude would not already know, but the ~980-line body is nearly double its own 500-line limit and repeats the auth rules across the verbatim callout, the all-languages section, and the best-practices section, fitting "mostly efficient but could be tightened."	2 / 3
Actionability	It provides copy-paste-ready commands (symlink creation, `pnpm harness`, `rg` content checks, `npx tsx` extraction), a verbatim callout block, and concrete frontmatter/scenarios.yaml/acceptance-criteria templates; the placeholder service names are justified for a meta-skill teaching patterns.	3 / 3
Workflow Clarity	The 8-step creation process is clearly sequenced with explicit validation checkpoints (mock test runs with 100% pass criteria, a required Rust regeneration `rg` gate, symlink verification) plus a closing checklist, matching the anchor for clear sequence with explicit validation and feedback loops.	3 / 3
Progressive Disclosure	The three real references are well-signaled in a one-level-deep table, but the body holds large blocks that should be split out (verbatim callout, six-language auth examples, test-creation formats, regeneration), and at ~980 lines it badly exceeds the 500-line split threshold, fitting "content that should be separate is inline."	2 / 3
	Total	10 / 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 answers both what and when with an explicit trigger clause and carves out a distinct Azure/Foundry niche, but its action list is generic and its trigger-term coverage is thin.

Suggestions

Replace generic actions with concrete capabilities, e.g. "Generate SKILL.md frontmatter, scaffold bundled scripts/references, and author Azure SDK auth and best-practices sections."

Broaden trigger terms to natural variations users would say, e.g. "Use when creating, scaffolding, or updating Azure SDK or Microsoft Foundry skills, or when adding language-specific auth patterns."

Dimension	Reasoning	Score
Specificity	It names the domain ("Azure SDKs and Microsoft Foundry services") and two actions ("creating new skills or updating existing skills"), but the actions are generic and not a comprehensive list of concrete capabilities, matching the anchor that names a domain and some actions.	2 / 3
Completeness	It states both what ("Guide for creating effective skills...") and when via an explicit "Use when..." clause, satisfying the anchor for clearly answering both what AND when with explicit triggers.	3 / 3
Trigger Term Quality	The single "Use when creating new skills or updating existing skills" clause supplies a couple of natural trigger phrases, but coverage is narrow with no common variations, fitting "some relevant keywords but missing common variations."	2 / 3
Distinctiveness Conflict Risk	The combination of skill-authoring triggers tied specifically to Azure SDKs and Microsoft Foundry gives a clear niche 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 (980 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 4 missing	Warning
referenced_paths_exist	Referenced path issues: 14 missing	Warning

	Total	13 / 16 Passed

Repository: microsoft/agent-skills
Commit: 32cad4e

Reviewed: about 24 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.