create-skill
Guide for creating effective skills following best practices. Use when creating or updating skills that extend agent capabilities.
69
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
67%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 has good structure with an explicit 'Use when' clause that clearly separates what from when. However, it lacks specific concrete actions that would help Claude understand the full scope of the skill, and the trigger terms could be expanded to include more natural variations users might use when asking for help with skill creation.
Suggestions
Add specific concrete actions like 'write YAML frontmatter, define trigger conditions, structure skill content sections'
Expand trigger terms to include variations like 'SKILL.md', 'skill file', 'new skill', 'write a skill', 'skill template'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('creating effective skills') and mentions some actions ('creating or updating skills'), but lacks concrete specific actions like 'write YAML frontmatter', 'define trigger conditions', or 'structure skill content'. | 2 / 3 |
Completeness | Clearly answers both what ('Guide for creating effective skills following best practices') and when ('Use when creating or updating skills that extend agent capabilities') with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes relevant keywords like 'skills', 'creating', 'updating', and 'agent capabilities', but misses common variations users might say such as 'SKILL.md', 'skill file', 'new skill', 'write a skill', or 'skill template'. | 2 / 3 |
Distinctiveness Conflict Risk | Somewhat specific to skill creation, but 'agent capabilities' and 'best practices' are generic enough that it could potentially conflict with other documentation or guide-type skills. The term 'skills' helps distinguish it but could be clearer. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill demonstrates good structure and progressive disclosure but falls short on actionability. It explains concepts and principles well but doesn't provide concrete examples of skill content, templates, or a step-by-step creation workflow. The content would benefit from showing rather than telling - including a minimal working skill example inline.
Suggestions
Add a concrete, minimal skill example showing proper SKILL.md content (not just the file structure) that demonstrates the principles in action
Replace abstract guidance like 'Be concise' with specific before/after examples showing verbose vs. lean skill content
Add a numbered workflow for creating a skill with validation steps (e.g., '1. Draft SKILL.md 2. Check line count 3. Test with target models 4. Refine based on results')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary explanations that Claude would already know (e.g., 'Think of them as onboarding guides', explaining what skills provide at a conceptual level). The content could be tightened by removing meta-explanations and focusing on actionable guidance. | 2 / 3 |
Actionability | Provides structural guidance and principles but lacks concrete, executable examples. The 'Core Principles' section describes what to do abstractly ('Be concise', 'Set appropriate degrees of freedom') without showing specific before/after examples or copy-paste ready templates. | 2 / 3 |
Workflow Clarity | The three-level loading system is explained but lacks a clear step-by-step workflow for actually creating a skill. No validation checkpoints or feedback loops are provided for the skill creation process itself. | 2 / 3 |
Progressive Disclosure | Excellent use of progressive disclosure - the SKILL.md provides a clear overview under 200 lines with well-signaled one-level-deep references to detailed documentation in the references/ directory. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.