Create new Claude Code skills with proper structure, YAML frontmatter, and bundled resources. Generates skill templates following best practices for modular, self-contained capability packages.
Install with Tessl CLI
npx tessl i github:FlorianBruniaux/claude-code-ultimate-guide --skill skill-creator68
Quality
52%
Does it follow best practices?
Impact
99%
2.35xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./examples/skills/skill-creator/SKILL.mdQuality
Discovery
40%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 adequately identifies its domain (Claude Code skill creation) and has good distinctiveness, but suffers from missing explicit trigger guidance and somewhat vague capability language. The lack of a 'Use when...' clause is a significant gap that would make it harder for Claude to know when to select this skill.
Suggestions
Add a 'Use when...' clause with trigger terms like 'create skill', 'new skill', 'add capability', 'skill template', or 'teach Claude'
Replace vague phrases like 'proper structure' and 'best practices' with specific actions like 'creates frontmatter with filetype/description fields, generates instruction content, bundles resource files'
Include common user phrasings such as 'make a skill', 'skill.md', 'skill file', or 'custom instruction'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Claude Code skills) and some actions ('Create', 'Generates skill templates'), but lacks comprehensive concrete actions. 'Proper structure' and 'best practices' are somewhat vague. | 2 / 3 |
Completeness | Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance. Per rubric guidelines, missing explicit trigger guidance caps completeness at 2, and this has none at all. | 1 / 3 |
Trigger Term Quality | Includes relevant terms like 'skills', 'YAML frontmatter', 'skill templates', but missing common variations users might say like 'new skill', 'add skill', 'skill file', '.md skill', or 'teach Claude'. | 2 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on Claude Code skills with distinct terminology ('YAML frontmatter', 'bundled resources', 'capability packages'). Unlikely to conflict with other skills. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides solid actionable guidance with concrete commands and examples for creating new skills. However, it's moderately verbose with inline templates that could be externalized, and lacks validation steps in its workflows. The structure is reasonable but could benefit from tighter organization and explicit verification checkpoints.
Suggestions
Move the full SKILL.md template to assets/skill-template.md and reference it, reducing inline verbosity
Add validation steps after skill creation (e.g., 'Verify skill loads correctly: claude --list-skills | grep skill-name')
Remove explanatory text about what directories are for - Claude knows what scripts/ and assets/ folders contain
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary explanation (e.g., explaining what each folder is for when Claude already knows directory structures) and the SKILL.md template section is verbose. However, it's not egregiously padded and most content serves a purpose. | 2 / 3 |
Actionability | Provides concrete, executable commands for initialization and packaging scripts, clear directory structures, and specific examples of how to invoke the skill. The step-by-step example for creating a release notes skill is copy-paste actionable. | 3 / 3 |
Workflow Clarity | The 'Creating a Release Notes Skill' example shows a clear sequence, but lacks validation checkpoints. There's no guidance on verifying the skill works correctly before packaging, or what to do if initialization fails. | 2 / 3 |
Progressive Disclosure | The skill is self-contained but includes a lengthy SKILL.md template inline that could be in assets/. References to scripts are clear, but the document is somewhat monolithic with the full template embedded rather than referenced. | 2 / 3 |
Total | 9 / 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 | |
Table of Contents
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.