eval-agent
OfficialEvaluate agent tools, patch gaps, delegate safely
Software Engineering#delegation#memory#risk-analysis#agent-evaluation#transparent-artifacts#tool-assessment
Authorm2ai-portfolio
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Score and compare agent tools or platforms against a structured framework to surface gaps, risks, and a concrete delegation spec.
Core Features & Use Cases
- Three-question scoring framework that quantifies persistent memory, inspectable artifacts, and compounding context for agent tools.
- Generates a concrete delegation spec that patches identified weaknesses and defines guardrails for safe operation.
- Provides an auditable risk assessment and a clear path to improvements across multiple evaluation scenarios.
Quick Start
Run an evaluation of a chosen agent tool against the three structural questions and generate a delegation spec.
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: eval-agent Download link: https://github.com/m2ai-portfolio/m2ai-skills-pack/archive/main.zip#eval-agent 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 510,000+ vetted skills library on demand.