[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M731T1KFSFWXGE7ZP0WXY6YP":3,"skill-same:01M731T1KFSFWXGE7ZP0WXY6YP":49},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M731T1KFSFWXGE7ZP0WXY6YP","agent-eval",null,"编码代理（Claude Code、Aider、Codex等）在自定义任务上的直接比较，包含通过率、成本、时间和一致性指标","SriramGandhiS\u002FSkills","SriramGandhiS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F211849986?v=4","01M72WQCW12BYX71C6WN584TTA","Sriram S","01M72WQCWTJ2RD0ET1X31AF1RC",1,"MIT","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-CN\u002Fskills\u002Fagent-eval\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: agent-eval\ndescription: 编码代理（Claude Code、Aider、Codex等）在自定义任务上的直接比较，包含通过率、成本、时间和一致性指标\norigin: ECC\ntools: Read, Write, Edit, Bash, Grep, Glob\n---\n\n# Agent Eval 技能\n\n一个轻量级 CLI 工具，用于在可复现的任务上对编码代理进行头对头比较。每个“哪个编码代理最好？”的比较都基于感觉——本工具将其系统化。\n\n## 何时使用\n\n* 在你自己的代码库上比较编码代理（Claude Code、Aider、Codex 等）\n* 在采用新工具或模型之前衡量代理性能\n* 当代理更新其模型或工具时运行回归检查\n* 为团队做出数据支持的代理选择决策\n\n## 安装\n\n```bash\n## pinned to v0.1.0 — latest stable commit\npip install git+https:\u002F\u002Fgithub.com\u002Fjoaquinhuigomez\u002Fagent-eval.git@6d062a2f5cda6ea443bf5d458d361892c04e749b\n```\n\n## 核心概念\n\n### YAML 任务定义\n\n以声明方式定义任务。每个任务指定要做什么、要修改哪些文件以及如何判断成功：\n\n```yaml\nname: add-retry-logic\ndescription: Add exponential backoff retry to the HTTP client\nrepo: .\u002Fmy-project\nfiles:\n  - src\u002Fhttp_client.py\nprompt: |\n  Add retry logic with exponential backoff to all HTTP requests.\n  Max 3 retries. Initial delay 1s, max delay 30s.\njudge:\n  - type: pytest\n    command: pytest tests\u002Ftest_http_client.py -v\n  - type: grep\n    pattern: \"exponential_backoff|retry\"\n    files: src\u002Fhttp_client.py\ncommit: \"abc1234\"  # pin to specific commit for reproducibility\n```\n\n### Git 工作树隔离\n\n每个代理运行都获得自己的 git 工作树——无需 Docker。这提供了可复现的隔离，使得代理之间不会相互干扰或损坏基础仓库。\n\n### 收集的指标\n\n| 指标 | 衡量内容 |\n|--------|-----------------|\n| 通过率 | 代理生成的代码是否通过了判断？ |\n| 成本 | 每个任务的 API 花费（如果可用） |\n| 时间 | 完成所需的挂钟秒数 |\n| 一致性 | 跨重复运行的通过率（例如，3\u002F3 = 100%） |\n\n## 工作流程\n\n### 1. 定义任务\n\n创建一个 `tasks\u002F` 目录，其中包含 YAML 文件，每个任务一个文件：\n\n```bash\nmkdir tasks\n## Write task definitions (see template above)\n```\n\n### 2. 运行代理\n\n针对你的任务执行代理：\n\n```bash\nagent-eval run --task tasks\u002Fadd-retry-logic.yaml --agent claude-code --agent aider --runs 3\n```\n\n每次运行：\n\n1. 从指定的提交创建一个新的 git 工作树\n2. 将提示交给代理\n3. 运行判断标准\n4. 记录通过\u002F失败、成本和时间\n\n### 3. 比较结果\n\n生成比较报告：\n\n```bash\nagent-eval report --format table\n```\n\n```\nTask: add-retry-logic (3 runs each)\n┌──────────────┬───────────┬────────┬────────┬─────────────┐\n│ Agent        │ Pass Rate │ Cost   │ Time   │ Consistency │\n├──────────────┼───────────┼────────┼────────┼─────────────┤\n│ claude-code  │ 3\u002F3       │ $0.12  │ 45s    │ 100%        │\n│ aider        │ 2\u002F3       │ $0.08  │ 38s    │  67%        │\n└──────────────┴───────────┴────────┴────────┴─────────────┘\n```\n\n## 判断类型\n\n### 基于代码（确定性）\n\n```yaml\njudge:\n  - type: pytest\n    command: pytest tests\u002F -v\n  - type: command\n    command: npm run build\n```\n\n### 基于模式\n\n```yaml\njudge:\n  - type: grep\n    pattern: \"class.*Retry\"\n    files: src\u002F**\u002F*.py\n```\n\n### 基于模型（LLM 作为判断器）\n\n```yaml\njudge:\n  - type: llm\n    prompt: |\n      Does this implementation correctly handle exponential backoff?\n      Check for: max retries, increasing delays, jitter.\n```\n\n## 最佳实践\n\n* **从 3-5 个任务开始**，这些任务代表你的真实工作负载，而非玩具示例\n* **每个代理至少运行 3 次试验**以捕捉方差——代理是非确定性的\n* **在你的任务 YAML 中固定提交**，以便结果在数天\u002F数周内可复现\n* **每个任务至少包含一个确定性判断器**（测试、构建）——LLM 判断器会增加噪音\n* **跟踪成本与通过率**——一个通过率 95% 但成本高出 10 倍的代理可能不是正确的选择\n* **对你的任务定义进行版本控制**——它们是测试夹具，应将其视为代码\n\n## 链接\n\n* 仓库：[github.com\u002Fjoaquinhuigomez\u002Fagent-eval](https:\u002F\u002Fgithub.com\u002Fjoaquinhuigomez\u002Fagent-eval)\n","# Agent Eval 技能\n\n一个轻量级 CLI 工具，用于在可复现的任务上对编码代理进行头对头比较。每个“哪个编码代理最好？”的比较都基于感觉——本工具将其系统化。\n\n## 何时使用\n\n* 在你自己的代码库上比较编码代理（Claude Code、Aider、Codex 等）\n* 在采用新工具或模型之前衡量代理性能\n* 当代理更新其模型或工具时运行回归检查\n* 为团队做出数据支持的代理选择决策\n\n## 安装\n\n```bash\n## pinned to v0.1.0 — latest stable commit\npip install git+https:\u002F\u002Fgithub.com\u002Fjoaquinhuigomez\u002Fagent-eval.git@6d062a2f5cda6ea443bf5d458d361892c04e749b\n```\n\n## 核心概念\n\n### YAML 任务定义\n\n以声明方式定义任务。每个任务指定要做什么、要修改哪些文件以及如何判断成功：\n\n```yaml\nname: add-retry-logic\ndescription: Add exponential backoff retry to the HTTP client\nrepo: .\u002Fmy-project\nfiles:\n  - src\u002Fhttp_client.py\nprompt: |\n  Add retry logic with exponential backoff to all HTTP requests.\n  Max 3 retries. Initial delay 1s, max delay 30s.\njudge:\n  - type: pytest\n    command: pytest tests\u002Ftest_http_client.py -v\n  - type: grep\n    pattern: \"exponential_backoff|retry\"\n    files: src\u002Fhttp_client.py\ncommit: \"abc1234\"  # pin to specific commit for reproducibility\n```\n\n### Git 工作树隔离\n\n每个代理运行都获得自己的 git 工作树——无需 Docker。这提供了可复现的隔离，使得代理之间不会相互干扰或损坏基础仓库。\n\n### 收集的指标\n\n| 指标 | 衡量内容 |\n|--------|-----------------|\n| 通过率 | 代理生成的代码是否通过了判断？ |\n| 成本 | 每个任务的 API 花费（如果可用） |\n| 时间 | 完成所需的挂钟秒数 |\n| 一致性 | 跨重复运行的通过率（例如，3\u002F3 = 100%） |\n\n## 工作流程\n\n### 1. 定义任务\n\n创建一个 `tasks\u002F` 目录，其中包含 YAML 文件，每个任务一个文件：\n\n```bash\nmkdir tasks\n## Write task definitions (see template above)\n```\n\n### 2. 运行代理\n\n针对你的任务执行代理：\n\n```bash\nagent-eval run --task tasks\u002Fadd-retry-logic.yaml --agent claude-code --agent aider --runs 3\n```\n\n每次运行：\n\n1. 从指定的提交创建一个新的 git 工作树\n2. 将提示交给代理\n3. 运行判断标准\n4. 记录通过\u002F失败、成本和时间\n\n### 3. 比较结果\n\n生成比较报告：\n\n```bash\nagent-eval report --format table\n```\n\n```\nTask: add-retry-logic (3 runs each)\n┌──────────────┬───────────┬────────┬────────┬─────────────┐\n│ Agent        │ Pass Rate │ Cost   │ Time   │ Consistency │\n├──────────────┼───────────┼────────┼────────┼─────────────┤\n│ claude-code  │ 3\u002F3       │ $0.12  │ 45s    │ 100%        │\n│ aider        │ 2\u002F3       │ $0.08  │ 38s    │  67%        │\n└──────────────┴───────────┴────────┴────────┴─────────────┘\n```\n\n## 判断类型\n\n### 基于代码（确定性）\n\n```yaml\njudge:\n  - type: pytest\n    command: pytest tests\u002F -v\n  - type: command\n    command: npm run build\n```\n\n### 基于模式\n\n```yaml\njudge:\n  - type: grep\n    pattern: \"class.*Retry\"\n    files: src\u002F**\u002F*.py\n```\n\n### 基于模型（LLM 作为判断器）\n\n```yaml\njudge:\n  - type: llm\n    prompt: |\n      Does this implementation correctly handle exponential backoff?\n      Check for: max retries, increasing delays, jitter.\n```\n\n## 最佳实践\n\n* **从 3-5 个任务开始**，这些任务代表你的真实工作负载，而非玩具示例\n* **每个代理至少运行 3 次试验**以捕捉方差——代理是非确定性的\n* **在你的任务 YAML 中固定提交**，以便结果在数天\u002F数周内可复现\n* **每个任务至少包含一个确定性判断器**（测试、构建）——LLM 判断器会增加噪音\n* **跟踪成本与通过率**——一个通过率 95% 但成本高出 10 倍的代理可能不是正确的选择\n* **对你的任务定义进行版本控制**——它们是测试夹具，应将其视为代码\n\n## 链接\n\n* 仓库：[github.com\u002Fjoaquinhuigomez\u002Fagent-eval](https:\u002F\u002Fgithub.com\u002Fjoaquinhuigomez\u002Fagent-eval)\n",{"name":5,"tools":24,"origin":25,"description":7},"Read, Write, Edit, Bash, Grep, Glob","ECC","master","d6ca01da0f24a3b0e26e4a8b7b66cbd25d429f5d","web-assets\u002Fdocs\u002Fzh-CN\u002Fskills\u002Fagent-eval",0,"https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills","https:\u002F\u002Fgithub.com\u002FSriramGandhiS","https:\u002F\u002Fsriram.website\u002F","Curious guy who keeps tinkering until something works","2026-05-20 16:21:34",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add SriramGandhiS\u002FSkills --skill agent-eval",{"tool":41,"command":42},"bunx","bunx skills add SriramGandhiS\u002FSkills --skill agent-eval",{"tool":44,"command":45},"pnpm","pnpm dlx skills add SriramGandhiS\u002FSkills --skill agent-eval","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-CN\u002Fskills\u002Fagent-eval\u002FSKILL.md",true,[],[50,57,62,68,75,82],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M732609EPJWV13PVTX3GT4TM","webgpu-threejs-tsl","Comprehensive guide for developing WebGPU-enabled Three.js applications using TSL (Three.js Shading Language). Covers WebGPU renderer setup, TSL syntax and node materials, compute shaders, post-processing effects, and WGSL integration. Use this skill when working with Three.js WebGPU, TSL shaders, node materials, or GPU compute in Three.js.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fwebgpu-threejs-tsl\u002Fskills\u002Fwebgpu-threejs-tsl\u002FSKILL.md",[],[],{"skillNo":58,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7325XM47AGWB6K6C4VXKE6B","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fwebgpu-threejs-tsl\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7325WP6DES69JKC840VMFEP","verification-loop","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7325TFQF1DZTQ6J3WGQQ1VR","tdd-workflow","Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Ftdd-workflow\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7325RGV9AY9PK92D2V8KKPW","strategic-compact","Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Fstrategic-compact\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7325MZC28SE86E7NMCNEFS4","security-review","Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment\u002Fsensitive features. Provides comprehensive security checklist and patterns.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Fsecurity-review\u002FSKILL.md",[],[]]