skill-creator
Guides creation, validation, and packaging of AI agent skills with token-efficient design, progressive disclosure patterns, and YAML frontmatter best practices. Use when building new skills, updating existing skills, validating skill structure against standards, or packaging for distribution—e.g., "create skill", "validate SKILL.md", "package skill for sharing", "check description format".
94
Does it follow best practices?
Validation for skill structure
Discovery
100%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 an excellent skill description that hits all the marks. It provides specific capabilities (creation, validation, packaging), includes methodological details (token-efficient design, progressive disclosure), and offers explicit trigger guidance with concrete example phrases. The description is well-scoped to a distinct domain that won't conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'creation, validation, and packaging of AI agent skills' along with specific techniques like 'token-efficient design, progressive disclosure patterns, and YAML frontmatter best practices'. | 3 / 3 |
Completeness | Clearly answers both what (guides creation, validation, packaging with specific methodologies) AND when with explicit 'Use when...' clause covering multiple scenarios and concrete example phrases. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'create skill', 'validate SKILL.md', 'package skill for sharing', 'check description format', plus domain terms like 'skills', 'YAML frontmatter'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused specifically on 'AI agent skills' and 'SKILL.md' files with unique triggers like 'validate SKILL.md' and 'package skill for sharing' that are unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with excellent progressive disclosure and clear workflows. The actionability is strong with concrete scripts and commands. Minor verbosity in explaining concepts (like persuasion principles inline) that could be more aggressively pushed to references, but overall this is a high-quality skill that practices what it preaches.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some content Claude likely knows (e.g., explaining what scripts/references/assets are). The persuasion principles section is detailed but arguably necessary for this specialized domain. Some sections could be tightened. | 2 / 3 |
Actionability | Provides concrete, executable commands (init_skill.py, package_skill.py, quick_validate.py), clear file structure templates, and specific YAML frontmatter examples. The workflow steps are copy-paste ready with actual script paths. | 3 / 3 |
Workflow Clarity | Clear 6-step creation workflow with explicit sequence (Understand → Plan → Initialize → Edit → Package → Iterate). Includes validation checkpoint before packaging and explicit instruction to run quick_validate.py after edits. Feedback loop present in step 6. | 3 / 3 |
Progressive Disclosure | Excellent structure with concise overview in SKILL.md and six clearly-signaled one-level-deep references. Each reference link includes guidance on when to load it (e.g., 'Load when designing sequential or conditional workflows'). Content appropriately split between main file and references. | 3 / 3 |
Total | 11 / 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.