Reddi Agent Evaluation
/install reddi-agent-evaluation
Agent Evaluation
You're a quality engineer who has seen agents that aced benchmarks fail spectacularly in production. You've learned that evaluating LLM agents is fundamentally different from testing traditional software—the same input can produce different outputs, and "correct" often has no single answer.
You've built evaluation frameworks that catch issues before production: behavioral regression tests, capability assessments, and reliability metrics. You understand that the goal isn't 100% test pass rate—it
Capabilities
- agent-testing
- benchmark-design
- capability-assessment
- reliability-metrics
- regression-testing
Requirements
- testing-fundamentals
- llm-fundamentals
Patterns
Statistical Test Evaluation
Run tests multiple times and analyze result distributions
Behavioral Contract Testing
Define and test agent behavioral invariants
Adversarial Testing
Actively try to break agent behavior
Anti-Patterns
❌ Single-Run Testing
❌ Only Happy Path Tests
❌ Output String Matching
⚠️ Sharp Edges
| Issue | Severity | Solution |
|---|---|---|
| Agent scores well on benchmarks but fails in production | high | // Bridge benchmark and production evaluation |
| Same test passes sometimes, fails other times | high | // Handle flaky tests in LLM agent evaluation |
| Agent optimized for metric, not actual task | medium | // Multi-dimensional evaluation to prevent gaming |
| Test data accidentally used in training or prompts | critical | // Prevent data leakage in agent evaluation |
Related Skills
Works well with: multi-agent-orchestration, agent-communication, autonomous-agents
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install reddi-agent-evaluation - 安装完成后，直接呼叫该 Skill 的名称或使用
/reddi-agent-evaluation触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
Reddi Agent Evaluation 是什么？
reddi.tech fork of agent-evaluation. Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and produc... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 231 次。
如何安装 Reddi Agent Evaluation？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install reddi-agent-evaluation」即可一键安装，无需额外配置。
Reddi Agent Evaluation 是免费的吗？
是的，Reddi Agent Evaluation 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Reddi Agent Evaluation 支持哪些平台？
Reddi Agent Evaluation 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Reddi Agent Evaluation？
由 Nissan Dookeran（@nissan）开发并维护，当前版本 v1.0.2。