Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
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
Run tests multiple times and analyze result distributions
Define and test agent behavioral invariants
Actively try to break agent behavior
| 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 |
Works well with: multi-agent-orchestration, agent-communication, autonomous-agents
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
[00] TnR ABSOLUTE RIGOR — Systemic Verification Doctrine. Forced cognitive exertion for high-stakes investigations. Mandates absolute deconstruction, mathematical proof chains, and ≥95% derived certainty. Zero-tolerance for heuristics or sentiment-based reasoning. Shortcuts are defined as intentional hallucinations.
The English summary is being prepared. Showing the original description.
Configures 2-Agent workflow between PM and implementation roles. Use when user mentions 2-Agent, 2エージェント, PM連携設定, Cursor設定, Cursor連携, 2-agent運用. Do NOT load for: 単独運用, ワークフロー実行, ハンドオフ処理.
The English summary is being prepared. Showing the original description.
Appends relevant hashtags to journal entries based on content analysis. Intended for LLM execution.
The English summary is being prepared. Showing the original description.
Add a new AI coding agent to Agent Sandbox. Creates all required files (Dockerfile, templates, CI, docs) and wires the agent into the CLI, proxy, and build system.
The English summary is being prepared. Showing the original description.
Add a new property to the AI agents database. Use when the user wants to add, create, or introduce a new column, property, field, or feature to track across all agents in the comparison matrix. Handles all four required steps - database updates, groups.json, table display, and GitHub issue templates.
The English summary is being prepared. Showing the original description.
Add new Agent templates to the meta-agent-skills framework.
The English summary is being prepared. Showing the original description.