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 the agent's capabilities with specialized knowledge, workflows, or tool integrations.

Quality

77%

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 ./skill-creator/SKILL.md

Quality

Content

67%Weight 40%Scale 1-5

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 clear sequencing and properly signaled one-level references to real bundle files. The main drag is conceptual preamble that assumes too little of Claude's existing knowledge.

Suggestions

Trim the 'About Skills' and 'What Skills Provide' sections to a few lines, removing explanations of modularity and training-vs-skills that Claude already knows, to improve token efficiency.

Add explicit read-conditions for each reference file (e.g., 'Read references/workflows.md when the skill involves multi-step or conditional logic') so the agent knows exactly when to load them.

Add an explicit verification checklist in Step 4 (e.g., run quick_validate.py, confirm frontmatter, test a representative script) to strengthen feedback loops in the editing workflow.

Dimension	Reasoning	Score
Conciseness	Mostly procedural and efficient, but sections like 'About Skills' and 'What Skills Provide' explain concepts (modular plug-and-play packages, comparison to model training) that Claude already knows, adding token cost without proportional value.	3 / 5
Actionability	Provides concrete executable commands ('uv run scripts/init_skill.py <skill-name> --path <output-directory>', 'uv run scripts/package_skill.py') and concrete examples, with only minor gaps such as omitted example skill output.	4 / 5
Workflow Clarity	The 6-step creation process is clearly sequenced with ordering guidance and a validation checkpoint via the packaging script, though iteration/verification feedback loops are light rather than explicit checklists.	4 / 5
Progressive Disclosure	Body points one level deep to real bundled files ('See references/workflows.md', 'See references/output-patterns.md') with clear signals, and core workflow is kept inline; minor gaps in describing exact read-conditions for each reference keep it below 5.	4 / 5
	Total	15 / 20 Passed

Description

87%Weight 40%Scale 1-5

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 strong: it answers both what and when explicitly with natural trigger phrases and a clear niche. Minor specificity gains are available by naming more concrete authoring actions.

Dimension	Reasoning	Score
Specificity	Lists several specific actions ('create a new skill', 'update an existing skill', extend with 'specialized knowledge, workflows, or tool integrations') but stays slightly abstract rather than enumerating concrete capabilities, so it sits below the comprehensive 5 anchor.	4 / 5
Completeness	Clearly states what ('Guide for creating effective skills') and an explicit when ('This skill should be used when users want to create a new skill (or update an existing skill)'), satisfying both parts with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases users would say ('create a new skill', 'update an existing skill') are present with good coverage, though some synonyms or variations are missing, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (skill authoring) with distinct triggers unlikely to overlap with other skills, minimizing conflict risk.	5 / 5
	Total	18 / 20 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: 6 missing	Warning
referenced_paths_exist	Referenced path issues: 23 missing	Warning

	Total	14 / 16 Passed

Repository: ceshine/ceshine-agent-skills
Path: skill-creator/SKILL.md
Commit: a8d25c2

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.