skills.rest
mandubian
mandubianCOMMUNITY
Explore all skills by this author →
Website𝕏@mandubianGitHub

evaluator.default

Automate validation and testing of autonomous agents with runtime sandboxing.

1|Updated Mar 23, 2026
Search Tags:#testing#validation#agent#promotion#autonomous#evaluate
One-click install
npx skills add https://github.com/mandubian/autonoetic --skill evaluator-default
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: evaluator.default
Source: https://github.com/mandubian/autonoetic/tree/main/agents/specialists/evaluator.default
Command: npx skills add https://github.com/mandubian/autonoetic --skill evaluator-default

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates validation and testing of autonomous agents to ensure safe, reliable behavior.

Core Features & Use Cases

  • Validates agent behavior across scenarios
  • Generates evidence for promotion gates and governance
  • Supports soft validation with runtime sandboxing

Quick Start

Run the evaluator against an agent bundle to start validation and evidence generation.

Frequently Asked Questions about evaluator.default

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I validate and test autonomous agents safely?▼

Yes, you can generate evidence for promotion gates by running an evaluator against your agent bundle. It automates validation and behavior testing across agent lifecycles to provide the required governance proof for promotions.

What is soft validation for autonomous agents?▼

You can test autonomous agent behavior across scenarios by running an evaluator against an agent bundle. It automates validation and applies soft validation with runtime sandboxing to ensure safe, reliable behavior across the agent lifecycle.

Does autonomous agent testing work with sandbox access and code execution permissions?▼

You should use autonomous agent evaluation when you need to validate behavior across scenarios, generate evidence for promotion gates, or ensure safety boundaries are met. It automates testing across agent lifecycles within runtime sandboxing constraints.

What are the limitations of automated agent validation?▼

Before validating autonomous agents, you need an agent bundle to run the evaluator against. The evaluator then applies soft validation and generates evidence while respecting sandbox access and code execution permissions defined in the frontmatter.

Related Skills

Explore More Software Engineering Skills→
ax-llmax-llm
2.9k

ax-java-agent-rlm

Build Java Ax agent runtime code for the dev.axllm:ax package.

Official
Intermediate
ScientiaCapitalScientiaCapital
1

adaptive-workflows

Track experiment results and generate reusable workflow templates.

Community
Advanced
matteocervellimatteocervelli
25

permission-test-skill

Verify permission handling and access control in Claude Code workflows.

Community
Basic
mattjeffersonmattjefferson
4

he-video

Capture paired browser evidence videos for UI bug fixes using agent-browser.

Community
Intermediate