skill-creator
Design and create Agent Skills using progressive disclosure principles. Use when building new skills, planning skill architecture, or writing skill content.
Overall
score
75%
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.
This description has good structure with explicit 'Use when' guidance, making it complete. However, it lacks concrete specific actions beyond generic verbs and could benefit from more natural trigger terms that users would actually say when needing this skill. The domain is reasonably distinct but could be more precisely scoped.
Suggestions
Add more specific concrete actions like 'define YAML frontmatter fields', 'structure skill sections', 'write trigger conditions', or 'create skill templates'
Include additional natural trigger terms users might say: 'SKILL.md', 'skill file', 'teach Claude', 'new capability', 'skill template'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('Agent Skills') and mentions some actions ('Design and create', 'building', 'planning', 'writing'), but lacks concrete specific actions like 'define YAML frontmatter', 'structure markdown sections', or 'implement trigger conditions'. | 2 / 3 |
Completeness | Clearly answers both what ('Design and create Agent Skills using progressive disclosure principles') and when ('Use when building new skills, planning skill architecture, or writing skill content') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms ('skills', 'skill architecture', 'skill content') but misses common variations users might say like 'SKILL.md', 'skill file', 'skill template', 'new capability', or 'teach Claude'. | 2 / 3 |
Distinctiveness Conflict Risk | The term 'skills' is somewhat specific to this context, but 'planning architecture' and 'writing content' could overlap with general documentation or software design skills. The 'progressive disclosure principles' adds some distinctiveness. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill exemplifies excellent progressive disclosure and token efficiency - it's a lean overview that appropriately delegates details to reference files. However, it sacrifices actionability by providing no concrete examples or executable guidance in the main file itself. The skill tells you what to do conceptually but relies entirely on references for the 'how'.
Suggestions
Add a minimal concrete example showing a complete SKILL.md with YAML frontmatter and body content (even 10-15 lines would significantly improve actionability)
Include a brief numbered workflow (3-5 steps) for creating a skill, with validation checkpoints, before pointing to the detailed development-process.md reference
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. Every section serves a purpose with no unnecessary explanation. Assumes Claude understands concepts like YAML frontmatter, token budgets, and file structures without elaboration. | 3 / 3 |
Actionability | Provides clear conceptual guidance and structure, but lacks concrete executable examples. The 'When to Create a Skill' section describes rather than instructs, and there's no actual code or copy-paste ready content for creating a skill. | 2 / 3 |
Workflow Clarity | The 3-level progressive disclosure is clearly explained, and the structure is well-defined. However, there's no step-by-step workflow for actually creating a skill - the process is delegated entirely to references without even a brief numbered sequence. | 2 / 3 |
Progressive Disclosure | Excellent structure with a concise overview and well-signaled one-level-deep references. Six clearly labeled reference files cover different aspects, and the content appropriately keeps the main file lean while pointing to detailed resources. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
body_output_format | No obvious output/return/format terms detected; consider specifying expected outputs | Warning |
Total | 13 / 16 Passed | |
- 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.