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 solid description that clearly communicates both what the skill does and when to use it, with good trigger terms that users would naturally employ. The main weakness is that the 'what' portion could be slightly more specific about the concrete actions performed during scaffolding (e.g., generating template files, setting up directory structure, populating default frontmatter fields).
Suggestions
Expand the capability list slightly to clarify what 'scaffold' entails—e.g., 'Generates SKILL.md template with frontmatter, creates directory structure, and bundles resource files for a new Claude Code skill.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Claude Code skill creation) and some actions ('scaffold', 'SKILL.md', 'frontmatter', 'bundled resources'), but doesn't list multiple concrete actions in detail—e.g., it doesn't specify what scaffolding entails beyond naming the artifacts. | 2 / 3 |
Completeness | Clearly answers both 'what' (scaffold a new Claude Code skill with SKILL.md, frontmatter, and bundled resources) and 'when' (creating a custom skill, standardizing skill structure across a team, or packaging a skill for distribution) with explicit trigger guidance. | 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 | Very specific niche—scaffolding Claude Code skills with SKILL.md files. Unlikely to conflict with other skills since it targets a narrow, well-defined use case around skill creation and packaging. | 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 directory structure and validation checklist. Its main weaknesses are reliance on scripts that may not exist (reducing actionability), lack of explicit error recovery in the workflow, and some content that could be more concise or better organized across files. The template example is helpful but the overall content sits in a middle ground between abstract guidance and fully executable instructions.
Suggestions
Add explicit error recovery steps to the validation workflow (e.g., 'If frontmatter validation fails: check that name matches /^[a-z0-9-]{1,64}$/, fix and re-validate')
Either include the init_skill.py script content inline or clearly mark it as something the user must create first, to avoid referencing non-existent resources
Move the organizational patterns table and the detailed release notes example into a references/ file, keeping SKILL.md focused on the core workflow
Replace the natural language prompt examples ('Create a new skill called...') with clearer indication of whether these are prompts to Claude or commands to run
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably structured but includes some unnecessary content like the 'When to Use' section that largely restates 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, and provides a SKILL.md template structure. However, the scripts are referenced but not shown or guaranteed to exist, the template is illustrative rather than executable, and the workflow steps mix natural language prompts with bash commands without clear distinction of what's automated vs manual. | 2 / 3 |
Workflow Clarity | The workflow has a clear 4-step sequence (Create → Template → Validate → Package) with a validation step that includes specific checks (frontmatter format, word count, testing). However, there's no explicit feedback loop for validation failures—it says what to verify but not what to do if checks fail. The validation step is a checklist rather than an automated command with error recovery. | 2 / 3 |
Progressive Disclosure | Content is organized into logical sections with headers and a table, but everything is inline in one file. The references to scripts in `scripts/` directory suggest external resources exist, but there are no explicit links to separate documentation files. The organizational patterns table and full example could potentially be split into reference files for cleaner navigation. | 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
4ef3dec
- 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.