modelNeedMeasured
OfficialConfigure and manage model templates for Stage5 evaluation.
AuthorEurecaMoment
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill streamlines the configuration and management of model templates for Stage5 evaluation, ensuring consistent and reliable model usage.
Core Features & Use Cases
- Model Configuration: Centralizes model configuration in a JSON template, eliminating hardcoded model rosters.
- Provider Management: Defines provider settings, model aliases, and test-group assignments in a structured format.
- Evaluation Flexibility: Supports grey and full evaluation model sets with configurable sampling and fail-fast options.
- Multimodal API Integration: Facilitates OpenAI-compatible chat completions API calls for image-based eval items.
- Use Case: When setting up for a full benchmark evaluation, use this Skill to load and verify the model configuration specified in
model_config.json.
Quick Start
Run the modelNeedMeasured skill to ensure the model configuration is correct for the upcoming evaluation.
Dependency Matrix
Required Modules
None requiredComponents
scriptsreferences
💻 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: modelNeedMeasured Download link: https://github.com/EurecaMoment/BenchClaw/archive/main.zip#modelneedmeasured 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 620,000+ vetted skills library on demand.