agent-evaluator

Community

Deterministic subagent selection for auditable AI

Authorarisng
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides a deterministic evaluator to decide which subagents to activate for a given user query, ensuring reproducible and auditable agent activation and a JSON decision payload.

Core Features & Use Cases

  • Deterministic evaluation of a user query against available subagents and generation of a JSON payload containing activated, required, and suggested agents.
  • Context-aware scoring using keyword signals, intent patterns, and optional file-context to influence activation decisions.
  • Use Case: Orchestrating a multi-agent workflow, run the evaluator to determine which subagents to activate and how to report results to downstream systems.

Quick Start

Run the evaluator on a user query to determine activation: python scripts/agent_evaluator.py 'create a flowchart'

Dependency Matrix

Required Modules

None required

Components

scripts

💻 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: agent-evaluator
Download link: https://github.com/arisng/github-copilot-fc/archive/main.zip#agent-evaluator

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.