make-skill

Create new Agent Skills for GitHub Copilot. Use when asked to create, scaffold, or add a skill. Generates SKILL.md with frontmatter, directory structure, and optional resources.

Quality

92%

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

Quality

Content

85%

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

A well-structured orchestrating skill: actionable templates, a clearly sequenced 8-step workflow with checkpoints, and clean progressive disclosure into two real reference files. The only weakness is minor redundancy that could be tightened for token efficiency.

Suggestions

Consolidate the Step 1 and Step 7 checklists or clearly differentiate them (investigation readiness vs. final validation) to remove overlap and save tokens.

Move the per-field frontmatter descriptions in Step 3 into a short reference table, keeping only the required name/description fields inline in SKILL.md.

Consider an explicit 'Validation' section with observable success criteria as the body recommends for new skills, rather than folding it entirely into the Step 7 checklist.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence, but the Step 1 and Step 7 checklists overlap and the inline frontmatter field list could be tightened or moved to a reference.	2 / 3
Actionability	Provides copy-paste-ready artifacts: a full frontmatter template, directory tree, concrete name-validation rules (1-64 chars, no consecutive hyphens), and specific script conventions — fully executable guidance.	3 / 3
Workflow Clarity	Eight numbered steps with explicit checkbox checkpoints at Step 1 and Step 7, plus feedback loops (retrospective, A/B test, writer-critic convergence) — a clear sequence with validation.	3 / 3
Progressive Disclosure	Overview body points to one-level-deep references (testing-patterns.md, anti-patterns.md) via clearly signaled markdown links; both referenced files exist and content is appropriately split.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 exemplary: concise, third-person, concrete actions, and an explicit 'Use when' trigger clause covering natural user phrasings. It cleanly satisfies every dimension.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Create new Agent Skills', 'Generates SKILL.md with frontmatter, directory structure, and optional resources' — matching the multi-action anchor rather than the single-action level 2.	3 / 3
Completeness	Explicitly answers both what (generates SKILL.md with frontmatter, directory structure, optional resources) and when ('Use when asked to create, scaffold, or add a skill'), satisfying the level-3 anchor.	3 / 3
Trigger Term Quality	'create, scaffold, or add a skill' are natural phrasings a user would actually say, giving good coverage of trigger variations.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche — skill scaffolding for GitHub Copilot — with distinct triggers unlikely to overlap with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: dotnet/efcore
Path: .agents/skills/make-skill/SKILL.md
Commit: 61317c9

Reviewed: 5 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.