evaluation-building
OfficialBuild AI safety evaluations from designs.
AuthorEquiStamp
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Transforms a validated evaluation design into a concrete, reproducible Phase 4 build plan and implementation guide, bridging design to deployment.
Core Features & Use Cases
- Create a comprehensive Build Plan with architecture, item-set design, scoring pipeline, and validation steps for an Inspect-based evaluation.
- Provide phase-4 implementation guidance including docker configuration, code structure, and deployment considerations.
- Support end-to-end handoff with documentation and testable artifacts to enable a non-builder to reproduce results.
Quick Start
Provide a Phase 3 design and I will generate a complete Phase 4 build plan and guidance.
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: evaluation-building Download link: https://github.com/EquiStamp/evaluating-evaluations/archive/main.zip#evaluation-building 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 223,000+ vetted skills library on demand.