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.

1.25x

Quality

80%

Does it follow best practices?

Impact

79%

1.25x

Average score across 7 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/skill-creator/SKILL.md

The canonical home for this skill is skill-creator in anthropics/skills

Quality

Content

85%

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

The body is well-structured with executable commands, a clear multi-step workflow including a validation feedback loop, and clean progressive disclosure to real bundled references. Its main weakness is length and some redundancy that could be tightened for token efficiency.

Suggestions

Consolidate the repeated directory-tree examples in the Progressive Disclosure section; one canonical tree plus brief pattern notes would reduce length without losing the idea.

Trim conceptual restatement of 'Claude is already smart / context window is a public good' which appears in multiple phrasings.

Dimension	Reasoning	Score
Conciseness	At 356 lines the body is thorough and mostly lean, but it restates principles (e.g., progressive disclosure described both conceptually and via multiple near-duplicate tree examples) that could be tightened without losing clarity.	2 / 3
Actionability	It gives concrete, copy-paste-ready commands such as 'scripts/init_skill.py <skill-name> --path <output-directory>' and 'scripts/package_skill.py <path/to/skill-folder> ./dist' with explicit options.	3 / 3
Workflow Clarity	The six-step creation process is clearly sequenced, with the packaging step embedding an explicit validate-then-package feedback loop ('If validation fails... fix any validation errors and run the packaging command again').	3 / 3
Progressive Disclosure	The body is an overview that points one level deep to real, well-signaled reference files (references/workflows.md, references/output-patterns.md) and bundled scripts, with clear guidance on when to read them; referenced paths exist in the bundle.	3 / 3
	Total	11 / 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 clearly states both what the skill does and when to use it with an explicit trigger clause, occupying a distinct niche. It is slightly light on concrete capability enumeration and natural keyword variety.

Suggestions

Enumerate concrete actions the skill performs (e.g., scaffold, validate, package, iterate) to raise specificity from domain-level to action-level.

Add a few more natural user-side trigger phrases (e.g., 'scaffold a skill', 'package a skill') for broader keyword coverage.

Dimension	Reasoning	Score
Specificity	It names the domain and actions ('create a new skill (or update an existing skill)', 'specialized knowledge, workflows, or tool integrations') but does not enumerate a comprehensive list of concrete capabilities the skill performs.	2 / 3
Completeness	It explicitly answers 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.	3 / 3
Trigger Term Quality	It includes natural phrases ('create a new skill', 'update an existing skill') a user would say, but the keyword coverage is narrow with limited common variations.	2 / 3
Distinctiveness Conflict Risk	It occupies a clear niche (skill authoring) with distinct triggers unlikely to conflict with other skills.	3 / 3
	Total	10 / 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: 6 missing	Warning
referenced_paths_exist	Referenced path issues: 12 missing	Warning

	Total	14 / 16 Passed

Repository: vercel-labs/json-render
Path: skills/skill-creator/SKILL.md
Commit: 9d3dfc8

Reviewed: about 13 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.