skill-creator

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

1.42x

Quality

—

Does it follow best practices?

Impact

98%

1.42x

Average score across 3 eval scenarios

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 a well-structured, actionable guide with a clear validated workflow, but it carries some conceptual redundancy that could be tightened, and its progressive-disclosure design is undermined by references to bundle files that are not actually present.

Suggestions

Tighten conciseness by trimming the 'About Skills' intro and the bridge/field analogy, and merge the duplicate progressive-disclosure treatment (Core Principle vs. the full 'Progressive Disclosure Design Principle' section) into one.

Fix progressive disclosure by either adding the missing bundle files (references/workflows.md, references/output-patterns.md, scripts/init_skill.py, scripts/package_skill.py) or removing the references, so the signaled navigation does not break.

Dimension	Reasoning	Score
Conciseness	The body is mostly useful procedural guidance, but it includes conceptual padding such as the 'About Skills' intro (which repeats the description), the bridge/field analogy, and a progressive-disclosure explanation that appears both as a Core Principle and again as a full section.	2 / 3
Actionability	It provides concrete, copy-paste-ready commands ('scripts/init_skill.py <skill-name> --path <output-directory>', 'scripts/package_skill.py <path/to/skill-folder>') and specific examples (rotate_pdf.py, references/schema.md, a frontmatter example).	3 / 3
Workflow Clarity	A clearly sequenced 6-step creation process with explicit validation checkpoints, including the packaging auto-validation fix-and-retry feedback loop and the directive to test added scripts by running them.	3 / 3
Progressive Disclosure	The body is well organized and clearly signals one-level-deep references (references/workflows.md, references/output-patterns.md, scripts/init_skill.py, scripts/package_skill.py), but none of those files exist in the bundle, so the signaled navigation breaks in practice.	2 / 3
	Total	10 / 12 Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that pairs a clear statement of what the skill does with an explicit 'should be used when' trigger clause and natural user-facing keywords. Its only weakness is limited breadth of concrete actions, with the rest of the text describing skill categories rather than actions.

Dimension	Reasoning	Score
Specificity	Names the domain ('creating effective skills') and concrete actions ('create a new skill (or update an existing skill)'), but the action list is limited to two verbs and the remainder ('specialized knowledge, workflows, or tool integrations') describes skill categories rather than additional concrete actions, so it is not comprehensive.	2 / 3
Completeness	It explicitly answers both what ('Guide for creating effective skills') and when ('This skill should be used when users want to create a new skill (or update an existing skill)'), with an explicit trigger clause equivalent to 'Use when...'.	3 / 3
Trigger Term Quality	'create a new skill', 'update an existing skill', and 'extends Claude's capabilities' are natural terms users would actually say, giving good coverage of the domain's trigger vocabulary.	3 / 3
Distinctiveness Conflict Risk	The skill-creation niche with its specific 'create/update a skill' trigger is clearly distinct and unlikely to cause conflicts with other skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 8 missing	Warning
referenced_paths_exist	Referenced path issues: 19 missing	Warning

	Total	14 / 16 Passed

Repository: NeverSight/skills_feed
Commit: 26d37ce

Reviewed: 4 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.