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.
75
70%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./examples/skills/skill-creator/SKILL.mdQuality
Discovery
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 well-crafted description that clearly communicates both what the skill does and when to use it. It has strong, distinctive trigger terms specific to Claude Code skill creation. The main area for improvement is adding more concrete actions to the 'what' portion—e.g., specifying that it generates YAML frontmatter, creates directory structure, or adds example content.
Suggestions
Expand the specificity by listing more concrete actions, e.g., 'Generates YAML frontmatter, creates directory structure, adds example instructions and bundled resource files.'
| 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., it doesn't specify what scaffolding entails beyond mentioning SKILL.md, frontmatter, and bundled resources. | 2 / 3 |
Completeness | Clearly answers both 'what' (scaffold a new Claude Code skill with SKILL.md, frontmatter, and bundled resources) and 'when' (explicit 'Use when' clause covering creating a custom skill, standardizing skill structure, or packaging 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—focuses specifically on scaffolding Claude Code skills with SKILL.md files, which is a narrow niche unlikely to conflict with other skills. The trigger terms like 'SKILL.md', 'frontmatter', and 'skill structure' are very specific. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
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 scaffold for creating new Claude Code skills with a clear structure and useful template. Its main weaknesses are the lack of executable validation/error-recovery steps, reliance on scripts that aren't shown to exist, and some content that could be more concise or split into reference files. The organizational patterns table and tips section add moderate value but contribute to verbosity.
Suggestions
Add explicit error recovery guidance in the validation step (e.g., 'If frontmatter validation fails: check that name matches /^[a-z0-9-]{1,64}$/ and fix accordingly')
Move the organizational patterns table and detailed example walkthrough into a references/ file, linking from the main SKILL.md
Make the distinction between Claude prompts and terminal commands clearer—use labeled code blocks (e.g., ```bash for commands, plain text or a different marker for Claude prompts)
Remove or condense the 'When to Use' section since it largely duplicates the frontmatter description
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably structured but includes some unnecessary content like the 'When to Use' section that largely repeats the description, and the organizational patterns table which is somewhat generic. The tips section contains some obvious advice. Could be tightened. | 2 / 3 |
Actionability | References scripts like `init_skill.py` and `package_skill.py` with concrete invocations, but the actual script content is not provided or shown to exist. The SKILL.md template is a useful concrete artifact, but the workflow steps mix natural language prompts with bash commands without clearly distinguishing which are Claude prompts vs terminal commands. The code blocks for 'Create a new skill' are plain text prompts, not executable. | 2 / 3 |
Workflow Clarity | The workflow has a clear 4-step sequence (Create → Template → Validate → Package) with a validation step that includes specific checks. However, there's no feedback loop for validation failures—it says what to verify but not what to do if checks fail. The validation step lists criteria but lacks executable validation commands or error recovery guidance. | 2 / 3 |
Progressive Disclosure | The content is reasonably organized with clear sections, but it's somewhat monolithic—the organizational patterns table and the full example walkthrough could be in separate reference files. It references scripts in subdirectories but doesn't link to any external documentation files for advanced topics like packaging or pattern details. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%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 | |
- Commit
746adc8
- Reviewed
Table of Contents
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.