← 返回 Skills 市场
luiciferyi

Agent Evaluation Report

作者 LuiciferYi · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
90
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install agent-evaluation-report
功能描述
根据测试数据自动生成标准化的智能体系统评测报告。 Use when: 用户说"生成智能体评测报告"、"创建测试报告"、"项目测试报告"。
使用说明 (SKILL.md)

Agent Evaluation Report - 智能体评测报告生成器

飞书文档写入位置

知识库: 7616288931050507220
节点: 效果评测/测试报告

根据测试数据自动生成标准化的智能体系统评测报告。

触发条件

当用户需要以下报告时触发：

  • "生成智能体评测报告"
  • "创建测试报告"
  • "项目测试报告"
  • "AI系统测试报告"
  • "智能体测试报告"

功能

基于用户提供的测试数据，自动生成包含以下章节的标准化报告：

  1. 报告概述（基本信息、执行摘要）
  2. 测试范围与目标
  3. 测试环境（硬件、软件、测试数据）
  4. 测试执行详情（功能测试、性能测试、安全测试、兼容性测试）
  5. 缺陷分析
  6. 业务场景验证
  7. 风险评估
  8. 测试结论与建议
  9. 附录

使用方法

提供以下信息即可生成报告：

项目名称: [项目名称]
测试周期: [开始日期] - [结束日期]
报告日期: [日期]
测试版本: [版本号]

执行摘要: [测试总结]

测试模块:
- 模块1: [描述] - [优先级]
- 模块2: [描述] - [优先级]

功能测试结果:
- [模块名]: 用例数X, 通过Y, 失败Z, 通过率P%

性能测试结果:
- [并发数]: 首字平均响应时间Xs

缺陷列表:
1. [模块] - [描述] - [严重程度] - [状态]

风险评估:
- [风险项] - [影响程度] - [发生概率] - [应对措施]

关键指标:
- 功能测试通过率: X% (目标: Y%)
- 性能响应时间: Xms (目标: Yms)

报告模板结构

1. 报告概述

  • 报告基本信息（项目名称、测试周期、报告日期、测试版本）
  • 执行摘要

2. 测试范围与目标

  • 测试范围（测试模块、测试内容、测试优先级）
  • 测试目标

3. 测试环境

  • 硬件环境（组件、配置、数量）
  • 软件环境（序号、是否携带、名称、部署版本、端口）
  • 测试数据

4. 测试执行详情

  • 功能测试结果（各模块测试项统计）
  • 性能测试结果（负载测试数据表格）
  • 安全测试结果（Web安全、业务逻辑安全、服务器安全、中间件安全）
  • 兼容性测试结果

5. 缺陷分析

  • 关键缺陷列表（编号、模块、描述、严重程度、状态、修复方案）

6. 业务场景验证

  • 核心业务流测试
  • 用户体验评估

7. 风险评估

  • 技术风险（风险项、影响程度、发生概率、应对措施）

8. 测试结论与建议

  • 总体评价
  • 关键指标达成情况
  • 上线建议（立即行动项、短期优化项、长期规划项）
  • 发布建议

9. 附录

  • 测试用例清单
  • 性能测试详细数据
  • 缺陷跟踪记录

输出格式

  • 格式：Markdown / Word文档
  • 保存位置：output/effect-reports/
  • 文件名格式：{项目名称}_效果评测报告_{日期}.md

示例

参考模板：北银金租AI中台建设项目测试报告

  • 测试模块：智能问答Agent、智能问数Agent、智能审单Agent、智能写作Agent
  • 测试维度：功能、性能、安全、兼容性
  • 关键指标：功能测试通过率≥95%、性能响应时间≤500ms、系统可用性≥99.5%
安全使用建议
This skill appears to do what it says: generate standardized agent test reports and save them as Markdown/Word and to Feishu. Before installing, confirm: (1) you trust the skill source (owner unknown) and are comfortable with the agent writing to the hard-coded Feishu knowledge base/node listed in SKILL.md; (2) the platform's Feishu credentials granted to the agent have the intended scope (so it can't write to unexpected org resources); (3) any sensitive test data you provide will be written to output/effect-reports/ and to Feishu — review outputs before sharing. No environment variables or external installers are required by the skill itself.
功能分析
Type: OpenClaw Skill Name: agent-evaluation-report Version: 1.0.0 The skill bundle is a template and instruction set for generating standardized AI agent evaluation reports. It utilizes standard tools for file operations and Feishu (Lark) document management (feishu_create_doc, etc.) to save reports to a specified knowledge base. No malicious code, unauthorized data exfiltration, or harmful prompt injection attempts were identified in SKILL.md or the metadata files.
能力评估
✓ Purpose & Capability
Name/description match the SKILL.md: it generates evaluation reports from test data. Declared capabilities (Feishu doc operations, read/write, message) are consistent with producing and saving reports.
ℹ Instruction Scope
Instructions stay within report generation (template, required inputs, save locations). One minor note: SKILL.md includes a hard-coded Feishu knowledge-base ID and node (7616288931050507220 / 效果评测/测试报告), which means the skill will attempt to write to a specific target if Feishu access is available — this is consistent with a doc-writing skill but worth confirming you want that target.
✓ Install Mechanism
No install spec and no code files beyond SKILL.md/package.json. Instruction-only skills carry low install risk because nothing is downloaded or executed on install.
ℹ Credentials
Skill declares no required environment variables or credentials, which is reasonable. It uses Feishu tools (feishu_create_doc etc.); platform-level Feishu credentials/permissions (not declared in the skill) will be needed at runtime — confirm that Feishu access granted to the agent is appropriate for writing to the specified knowledge base.
✓ Persistence & Privilege
always is false and the skill does not request elevated persistence. It writes output to a local folder (output/effect-reports/) and to Feishu docs per its instructions — this is expected behavior for a report generator.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install agent-evaluation-report
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /agent-evaluation-report 触发
  4. 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
- Initial release of agent-evaluation-report skill. - Generates standardized evaluation reports for intelligent agent systems based on user-provided test data. - Supports Markdown and Word output, auto-saves to a designated location. - Covers all key sections: project info, test scope, environment, execution details, defect analysis, business validation, risk assessment, conclusions, and appendix. - Triggered by user requests such as "生成智能体评测报告", "创建测试报告", or related phrases.
元数据
Slug agent-evaluation-report
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Agent Evaluation Report 是什么？

根据测试数据自动生成标准化的智能体系统评测报告。 Use when: 用户说"生成智能体评测报告"、"创建测试报告"、"项目测试报告"。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 90 次。

如何安装 Agent Evaluation Report？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install agent-evaluation-report」即可一键安装，无需额外配置。

Agent Evaluation Report 是免费的吗？

是的，Agent Evaluation Report 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Agent Evaluation Report 支持哪些平台？

Agent Evaluation Report 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Agent Evaluation Report？

由 LuiciferYi（@luiciferyi）开发并维护，当前版本 v1.0.0。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191113 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论