name	agent-evaluation
description	ALWAYS use this when the request matches Agent Evaluation: 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

Agent Evaluation

Start with:

Then load only the inherited docs, scripts, assets, examples, or detailed instructions that match the user's actual task.

Read references/full-skill-instructions.md only when the task needs the full original upstream guidance.
Prefer bundled scripts for deterministic or repetitive operations when they exist.
Reuse bundled assets instead of inventing substitutes when assets are present.
Keep final answers aligned with this skill's frontmatter trigger, Senior Master standard, and Codex strict review gate.

name	agent-evaluation
description	ALWAYS use this when the request matches Agent Evaluation: 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

Start with:

Then load only the inherited docs, scripts, assets, examples, or detailed instructions that match the user's actual task.

Read references/full-skill-instructions.md only when the task needs the full original upstream guidance.
Prefer bundled scripts for deterministic or repetitive operations when they exist.
Reuse bundled assets instead of inventing substitutes when assets are present.
Keep final answers aligned with this skill's frontmatter trigger, Senior Master standard, and Codex strict review gate.

agent-evaluation