evals-run
OfficialRun, debug, replay, and rescore evals.
Authorclawperator
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Coordinating and running Clawperator evals across local-dev and published runtimes to diagnose preflight failures, compare targets, and triage artifacts.
Core Features & Use Cases
- Orchestrates eval runs for android-version tasks across multiple runtimes (local-dev and published) on emulators and devices.
- Provides triage, replay, and rescore workflows with artifact outputs and run logs for debugging and validation.
- Includes a built-in runbook and helper scripts to install and configure the operator and APKs on connected devices.
Quick Start
Run an android-version eval with a chosen agent, model, and runtime to validate the end-to-end workflow.
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: evals-run Download link: https://github.com/clawperator/clawperator/archive/main.zip#evals-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.