← Back to Skills Marketplace
Agent Evaluation Report
by
LuiciferYi
· GitHub ↗
· v1.0.0
· MIT-0
90
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install agent-evaluation-report
Description
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"。
README (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:
- 报告概述(基本信息、执行摘要)
- 测试范围与目标
- 测试环境(硬件、软件、测试数据)
- 测试执行详情(功能测试、性能测试、安全测试、兼容性测试)
- 缺陷分析
- 业务场景验证
- 风险评估
- 测试结论与建议
- 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%
Usage Guidance
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.
Capability Analysis
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.
Capability Assessment
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.
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.
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.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install agent-evaluation-report - After installation, invoke the skill by name or use
/agent-evaluation-report - Provide required inputs per the skill's parameter spec and get structured output
Version History
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.
Metadata
Frequently Asked Questions
What is Agent Evaluation Report?
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"。 It is an AI Agent Skill for Claude Code / OpenClaw, with 90 downloads so far.
How do I install Agent Evaluation Report?
Run "/install agent-evaluation-report" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Agent Evaluation Report free?
Yes, Agent Evaluation Report is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Agent Evaluation Report support?
Agent Evaluation Report is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Agent Evaluation Report?
It is built and maintained by LuiciferYi (@luiciferyi); the current version is v1.0.0.
More Skills