llm-eval-designer
OfficialDesign robust evaluation for LLM workflows.
AuthorCAPHTECH
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Guides evaluation design for LLM-based workflows, covering failure modes and test case generation.
Core Features & Use Cases
- Failure mode analysis (hallucination, overfitting, partial processing)
- Generalization pattern guidance
- Test-case templates and scorer design
Quick Start
Create test cases and a scorer outline for an LLM task like a text replacement workflow.
Dependency Matrix
Required Modules
None requiredComponents
referencesassets
💻 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: llm-eval-designer Download link: https://github.com/CAPHTECH/claude-marketplace/archive/main.zip#llm-eval-designer Please download this .zip file, extract it, and install it in the .claude/skills/ directory.