Loading...
Loading...
Found 2 Skills
Evaluate Agent Skill design quality against official specifications and best practices. Use when reviewing, auditing, or improving SKILL.md files and skill packages. Provides multi-dimensional scoring and actionable improvement suggestions.
Run a 5-dimensional quality assessment (Clarity/Conciseness/Actionability/Consistency/Minimal-slop) on any LLM prompt / document (markdown, YAML, JSON, TOML) and iteratively refine it until the target score is reached. The default target score is 90, which can be overridden using the target_score parameter (e.g., target_score=95). This is used when users want to validate and improve the quality of LLM-facing prompts, instructions, or skills.