ellmos-ai

Ellmos Tests — AI skill for Claude Code

AI community

B/O/E evaluation framework for SKILL.md-based LLM operating systems and agent hubs.

How to install Ellmos Tests

This entry records only its repository, not the path inside it, so there is no exact command to give. Open ellmos-ai/ellmos-tests and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Ellmos Tests does

B/O/E evaluation framework for SKILL.md-based LLM operating systems and agent hubs.

Alternatives in AI

Welcome — AI Research Skills — You now have access to 86 production-ready skills covering the entire AI research lifecycle: literature survey 5.4k ★
StereOS — A Linux based operating system hardened and purpose built for AI agents 489 ★
SkillEvaluator — Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic 327 ★

README

ellmos-tests

Structured B/O/E testing framework for LLM operating systems, agent hubs, and SKILL.md architectures

[English](README.md) | [Deutsch](README_de.md)

[![Python](https://img.shields.io/badge/Python-3.10+-blue?logo=python&logoColor=white)](https://python.org) [![Version](https://img.shields.io/badge/Version-0.2.1-blue)](pyproject.toml) [![License: MIT](https://img.shields.io/badge/License-MIT-green)](LICENSE) [![Test definitions](https://img.shields.io/badge/Test_definitions-26_B%2FO%2FE-orange)](system_diff_tests/) [![Automated suite](https://img.shields.io/badge/Automated_suite-23%2B_unittest-brightgreen)](tests/) [![LLM-Ready](https://img.shields.io/badge/LLM--Ready-llms.txt-blueviolet)](llms.txt) [![Security: RunAsInvoker](https://img.shields.io/badge/Security-RunAsInvoker-blue)](SECURITY.md) [![Privacy: Zero Egress](https://img.shields.io/badge/Privacy-Zero_Egress-blue)](THIRD_PARTY_LICENSES.md) [![SLA: 48h Response](https://img.shields.io/badge/SLA-48h_Response-blue)](SECURITY.md) [![Organization: ellmos-ai](https://img.shields.io/badge/Org-ellmos--ai-blue)](https://github.com/ellmos-ai) [![Umbrella: open-bricks](https://img.shields.io/badge/Umbrella-open--bricks-blue)](https://github.com/open-bricks)

Quick Navigation

Index	Section	Description
01	Overview & Core Philosophy	Tri-modal B/O/E evaluation framework
02	Target Personas & Use Cases	High-intent use cases for architects and evaluators
03	Comparative Matrix	10 dimensions vs. 4 industry alternatives
04	System Architecture Topology	5-layer topology diagram (Mermaid)
05	Evaluation Lifecycle	Complete execution workflow (Mermaid)
06	B-Tests: Observation Battery	8 automated static audits (B001–B008)
07	O-Tests: Output Battery	8 functional c