Multi-tier framework for evaluating AI agent skills and plugins with quality gates, security scanning, harness compatibility checks, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior. Ships reusable CI templates that bring every check to any repository.
Python agent-evaluationagent-pluginsagent-securityagent-skillsagentic-aibenchmarkci-templatesclaude-codecodexevaluateevaluationharnesspluginplugin-evaluationsecurity-scannerskill-evalskill-evaluationskill-evaluatorskill-gap-analysisskills
# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
"""Utility functions for SkillEvaluator."""
from skillevaluator.utils.helpers import find_skills_in_directory, get_skill_name_from_path
from skillevaluator.utils.tool_runner import (
CVSS_THRESHOLDS,
ExternalTool,
Severity,
ToolResult,
Tools,
create_temp_config,
cvss_to_severity,
parse_json_output,
)
__all__ = [
"CVSS_THRESHOLDS",
"ExternalTool",
"Severity",
"ToolResult",
"Tools",
"create_temp_config",
"cvss_to_severity",
"find_skills_in_directory",
"get_skill_name_from_path",
"parse_json_output",
]