skill-creator

Scaffold a new Claude Code skill with SKILL.md, frontmatter, and bundled resources. Use when creating a custom skill, standardizing skill structure across a team, or packaging a skill for distribution.

Quality

70%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./examples/skills/skill-creator/SKILL.md

Quality

Content

50%

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

This skill provides a reasonable overview of how to scaffold a new Claude Code skill, with a clear directory structure and validation checklist. However, it references scripts (init_skill.py, package_skill.py) that don't exist in the bundle, undermining actionability. The content could be tighter—the organizational patterns table and some sections add bulk without proportional value, and the validation workflow lacks explicit error recovery steps.

Suggestions

Either include the referenced scripts (init_skill.py, package_skill.py) in the bundle or remove references to them and provide inline executable alternatives

Add a feedback loop to the validation step: specify what to do when each check fails (e.g., 'If frontmatter name is invalid, rename to kebab-case and re-validate')

Move the organizational patterns table and detailed example walkthrough to a references/ file to keep SKILL.md leaner and improve progressive disclosure

Replace the natural language prompt examples ('Create a new skill called...') with a single clear approach—either script-based or prompt-based—to reduce ambiguity

Dimension	Reasoning	Score
Conciseness	The skill includes some unnecessary explanation (e.g., the 'When to Use' section repeats what the description already covers, the organizational patterns table adds bulk without strong actionability). However, it's mostly well-structured and not excessively verbose.	2 / 3
Actionability	Provides concrete commands (init_skill.py, package_skill.py) and a template structure, but the scripts referenced don't exist in the bundle, making them non-executable. The SKILL.md template is useful but is a template rather than fully copy-paste ready code. The workflow mixes natural language prompts with bash commands without clearly distinguishing which approach to use.	2 / 3
Workflow Clarity	The workflow has a clear 4-step sequence (Create → Template → Validate → Package) with a validation step that includes a checklist. However, there's no feedback loop for validation failures—it says what to check but not how to fix issues or retry. The validation step is a checklist rather than an executable command.	2 / 3
Progressive Disclosure	The content is reasonably well-organized with clear sections, but it's somewhat monolithic—the organizational patterns table, the full example walkthrough, and the tips section could be in separate reference files. No bundle files are provided despite references to scripts (init_skill.py, package_skill.py) and the content references paths that don't exist.	2 / 3
	Total	8 / 12 Passed

Description

89%

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

This is a solid description that clearly communicates both what the skill does and when to use it, with good trigger terms that are natural and distinctive. The main weakness is that the specificity of concrete actions could be improved—listing more granular steps like 'generates frontmatter YAML with name, description, and version fields' would strengthen it further.

Suggestions

Add more specific concrete actions, e.g., 'Generates SKILL.md with YAML frontmatter (name, description, version), creates resource directories, and produces a ready-to-use skill template.'

Dimension	Reasoning	Score
Specificity	Names the domain (Claude Code skill creation) and some actions ('scaffold', 'creating', 'standardizing', 'packaging'), but doesn't list multiple concrete actions in detail—e.g., what specific files are generated, what frontmatter fields are populated, or what bundled resources are included.	2 / 3
Completeness	Clearly answers both 'what' (scaffold a new Claude Code skill with SKILL.md, frontmatter, and bundled resources) and 'when' (Use when creating a custom skill, standardizing skill structure across a team, or packaging a skill for distribution).	3 / 3
Trigger Term Quality	Includes strong natural trigger terms: 'skill', 'SKILL.md', 'frontmatter', 'custom skill', 'skill structure', 'packaging a skill', 'scaffold'. These are terms a user would naturally use when wanting to create a new skill.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche—creating Claude Code skills with SKILL.md is a very specific task unlikely to conflict with other skills. The trigger terms like 'SKILL.md', 'frontmatter', and 'scaffold a skill' are unique to this domain.	3 / 3
	Total	11 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: FlorianBruniaux/claude-code-ultimate-guide
Commit: bbaa00d

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.