Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/luohaothu-eval-harness
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/eval-harness
What's inside
- Skill name
eval-harness- Description
- 克劳德代码会话的正式评估框架,实施评估驱动开发(EDD)原则
- License
- MIT
- Instructions
- 256 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Eval Harness 技能 一个用于 Claude Code 会话的正式评估框架,实现了评估驱动开发 (EDD) 原则。 ## 理念 评估驱动开发将评估视为 "AI 开发的单元测试": * 在实现 **之前** 定义预期行为 * 在开发过程中持续运行评估 * 跟踪每次更改的回归情况 * 使用 pass@k 指标来衡量可靠性 ## 评估类型 ### 能力评估 测试 Claude 是否能完成之前无法完成的事情: ```markdown [能力评估:功能名称] 任务:描述 Claude 应完成的工作 成功标准: - [ ] 标准 1 - [ ] 标准 2 - [ ] 标准 标准 3 预期输出:对预期结果的描述 ``` ### 回归评估 确保更改不会破坏现有功能: ```markdown [回归评估:功能名称] 基线:SHA 或检查点名称 测试: - 现有测试-1:通过/失败 - 现有测试-2:通过/失败 - 现有测试-3:通过/失败 结果:X/Y 通过(之前为 Y/Y) ``` ## 评分器类型 ### 1. 基于代码的评分器 使用代码进行确定性检查: ```bash # Check if file contains expected pattern grep -q "export function handleAuth" src/auth.ts && echo "PASS" || echo "FAIL" # Check if tests pass npm test -- --testPathPattern="auth" && echo "PASS" || echo "FAIL" # Check if build succeeds npm run build && echo "PASS" || echo "FAIL" ``` ### 2. 基于模型的评分器 使用 Claude 来评估开放式输出: ```markdown [MODEL GRADER PROMPT] 评估以下代码变更: 1. 它是否解决了所述问题? 2. 它的结构是否良好? 3. 是否处理了边界情况? 4. 错误处理是否恰当? 评分:1-5 (1=差,5=优秀) 推理:[解释] ``` ### 3. 人工评分器 标记为需要手动审查: ```markdown [HUMAN REVIEW REQUIRED] 变更:对更改内容的描述 原因:为何需要人工审核 风险等级:低/中/高 ``` ## 指标 ### pass@k "k 次尝试中至少成功一次" * pass@1:首次尝试成功率 * pass@3:3 次尝试内成功率 * 典型目标:pass@3 > 90% ### pass^k "所有 k 次试验都成功" * 更高的可靠性门槛 * pass^3:连续 3 次成功 * 用于关键路径 ## 评估工作流程 ### 1. 定义(编码前) ```markdown ## 评估定义:功能-xyz ### 能力评估 1. 可以创建新用户账户 2. 可以验证电子邮件格式
From Luohaothu/everything-codex, MIT.
More from Luohaothu/everything-codex
- 0.493score
build-fix
Luohaothu
Build and compilation error resolution specialist.
SkillDFreshness: D★ 26Claude Code +9 - 0.493score
architect
Luohaothu
Software architecture specialist for system design, scalability, and technical decision-making.
SkillDFreshness: D★ 26Claude Code +9 - 0.490score
code-review
Luohaothu
Expert code review for quality, security, and maintainability.
SkillDFreshness: D★ 26Claude Code +9 - 0.490score
checkpoint
Luohaothu
Create or verify workflow checkpoints using git commits and state tracking.
SkillDFreshness: D★ 26Claude Code +9 - 0.487score
springboot-tdd
Luohaothu
使用JUnit 5、Mockito、MockMvc、Testcontainers和JaCoCo进行Spring Boot的测试驱动开发。适用于添加功能、修复错误或重构时。
SkillDFreshness: D★ 26Claude Code +9 - 0.487score
tdd-workflow
Luohaothu
在编写新功能、修复错误或重构代码时使用此技能。强制执行测试驱动开发,包含单元测试、集成测试和端到端测试,覆盖率超过80%。
SkillDFreshness: D★ 26Claude Code +9 - 0.487score
springboot-patterns
Luohaothu
Spring Boot 架构模式、REST API 设计、分层服务、数据访问、缓存、异步处理和日志记录。适用于 Java Spring Boot 后端工作。
SkillDFreshness: D★ 26Claude Code +9 - 0.487score
springboot-security
Luohaothu
Java Spring Boot 服务中关于身份验证/授权、验证、CSRF、密钥、标头、速率限制和依赖安全的 Spring Security 最佳实践。
SkillDFreshness: D★ 26Claude Code +9 - 0.484score
jpa-patterns
Luohaothu
Spring Boot中的JPA/Hibernate实体设计、关系、查询优化、事务、审计、索引、分页和连接池模式。
SkillDFreshness: D★ 26Claude Code +9 - 0.484score
postgres-patterns
Luohaothu
基于Supabase最佳实践的PostgreSQL数据库模式,用于查询优化、架构设计、索引和安全。
SkillDFreshness: D★ 26Claude Code +9 - 0.484score
strategic-compact
Luohaothu
建议在逻辑间隔处进行手动上下文压缩,以在任务阶段中保留上下文,而非任意的自动压缩。
SkillDFreshness: D★ 26Claude Code +9 - 0.484score
continuous-learning-v2
Luohaothu
基于本能的学习系统,通过钩子观察会话,创建具有置信度评分的原子本能,并将其演化为技能/命令/代理。
SkillDFreshness: D★ 26Claude Code +9
Signals
- Stars
- 26
- Forks
- 5
- Open issues
- 0
- Last commit (this folder)
- Feb 5, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Luohaothu/everything-codex
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Luohaothu
- 0.493score
build-fix
Luohaothu
Build and compilation error resolution specialist.
SkillDFreshness: D★ 26Claude Code +9 - 0.493score
architect
Luohaothu
Software architecture specialist for system design, scalability, and technical decision-making.
SkillDFreshness: D★ 26Claude Code +9 - 0.490score
code-review
Luohaothu
Expert code review for quality, security, and maintainability.
SkillDFreshness: D★ 26Claude Code +9 - 0.490score
checkpoint
Luohaothu
Create or verify workflow checkpoints using git commits and state tracking.
SkillDFreshness: D★ 26Claude Code +9 - 0.487score
springboot-security
Luohaothu
Java Spring Boot 服务中关于身份验证/授权、验证、CSRF、密钥、标头、速率限制和依赖安全的 Spring Security 最佳实践。
SkillDFreshness: D★ 26Claude Code +9 - 0.487score
springboot-tdd
Luohaothu
使用JUnit 5、Mockito、MockMvc、Testcontainers和JaCoCo进行Spring Boot的测试驱动开发。适用于添加功能、修复错误或重构时。
SkillDFreshness: D★ 26Claude Code +9
Cite this page
eval-harness skill. Agent Mart. https://agentmart.dev/skills/luohaothu-eval-harness (last updated 2026-10-24)