Agent Skills › suboss87/FDEOps › evaluate

evaluate

GitHub

用于评估AI工作流、模型或检索系统，通过代表性案例测试生成结果、失败分析及发布证据。适用于模型验证和代理评估场景。

skills/evaluate/SKILL.md suboss87/FDEOps

触发场景

需要评估AI模型或Agent性能时进行工作流合规性或有效性检查时

安装

npx skills add suboss87/FDEOps --skill evaluate -g -y

更多选项

不安装直接使用

npx skills use suboss87/FDEOps@evaluate

指定 Agent (Claude Code)

npx skills add suboss87/FDEOps --skill evaluate -a claude-code -g -y

安装 repo 全部 skill

npx skills add suboss87/FDEOps --all -g -y

预览 repo 内 skill

npx skills add suboss87/FDEOps --list

SKILL.md

Frontmatter

{
    "name": "evaluate",
    "description": "Evaluate an AI workflow against representative cases and its permitted actions. Use for model, retrieval or agent evaluation; tests do not grant release authority."
}

evaluate

Purpose

Evaluation results, failure analysis and release evidence.

Before investigating or acting:

Read the task context contract.
Read the method.

Load further references only when the task needs them. Everything linked is included in this skill; no other skill pack is required.

Principles

Work directly from the supplied permitted context. Standalone work does not require an engagement folder or initialization. Record filenames in the method are optional persistence destinations when no engagement is bound.
If called by @fde, reuse its current sanitized packet and scope. Do not restart setup, discovery or questions already answered.
The task context contract controls persistence and authority in both modes. Preserve unknowns and distinguish implementation, verification, deployment and acceptance.
Use the customer's repository instructions and available tools. Report a missing capability or unrun check honestly; do not claim that installing a skill provisions infrastructure.