dw-skill-eval-run
CommunityAutomate end-to-end Skill evaluation.
Authorxurik
Version1.0.0
Installs0
System Documentation
What problem does it solve?
自动化端到端的 Skill 评测流程，通过统一的 testset、跨模型执行、 transcripts 收集、评分与报告生成，帮助团队快速验证新技能的质量与对比不同实现。
Core Features & Use Cases
- 跨模型执行测试并收集 transcripts（包括 Claude 类模型和非 Claude 模型）
- 执行隔离：Subagent 隔离执行，确保测试的可重复性与安全性
- 生成执行计划、汇总结果并输出 execution_summary.yaml
- 使用场景包括：新技能验证、回归测试、模型对比评估
Quick Start
运行 /dw-skill-eval-run 来对当前技能执行完整的测试评估流程。
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: dw-skill-eval-run Download link: https://github.com/xurik/dataworks-skill-evaluator/archive/main.zip#dw-skill-eval-run Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.