mayubench-en
@clawhub_wanyview1/mayubench-en
By wanyview1
About this Skill
AI-Native Behavior Benchmark — 48 scenarios × 3 difficulty levels = 144 questions, 8-dimension scoring, measuring whether AI should do things, not whether it...
工作流编排提示词优化上下文管理
Skill files and instructions
Read SKILL.md and the other instructions or configuration files published with this Skill.
Loading file list
Details
- Category
- AI Agent
- Source
- clawhub
- Version
- 1.0.0
- Updated
- Sep 23, 2026