Agent Skills
› openai/plugins
› metric-pack-designer
metric-pack-designer
GitHub用于设计自定义指标包，为plugin-eval扩展本地评估规范。通过定义检查项和指标载荷，生成兼容的JSON输出，支持团队添加本地评估标准及可视化需求。
触发场景
用户希望扩展plugin-eval的本地评估规则
需要创建自定义的评估标准和指标可视化
安装
npx skills add openai/plugins --skill metric-pack-designer -g -y
SKILL.md
Frontmatter
{
"name": "metric-pack-designer",
"description": "Design custom metric packs for plugin-eval so teams can add local evaluation rubrics that emit schema-compatible checks and metrics. Use when the user wants their own evaluation criteria or visualizations."
}
Metric Pack Designer
Use this skill when the user wants to extend plugin-eval with a local rubric.
Workflow
- Clarify the custom rubric categories and target kinds.
- Define the smallest useful
checks[]andmetrics[]payload. - Create a metric-pack manifest plus a script that prints JSON to stdout.
- Run the pack through
plugin-eval analyze <path> --metric-pack <manifest.json>.
Design Rules
- Keep IDs stable across runs so comparisons stay meaningful.
- Emit only
checks[],metrics[], and optionalartifacts[]. - Do not try to overwrite the core score or summary.
- Prefer deterministic local signals over subjective text generation.
Reference
../../references/metric-pack-manifest.md
版本历史
- 11c74d6 当前 2026-07-19 09:43
