[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72ZXW42CA44NAKMX5M3F8FV":3,"skill-same:01M72ZXW42CA44NAKMX5M3F8FV":48},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M72ZXW42CA44NAKMX5M3F8FV","continuous-learning",null,"自动从Claude Code会话中提取可重复使用的模式，并将其保存为学习到的技能以供将来使用。","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\u002Fskills\u002Feverything-claude-code\u002Fdocs\u002Fzh-CN\u002Fskills\u002Fcontinuous-learning\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: continuous-learning\ndescription: 自动从Claude Code会话中提取可重复使用的模式，并将其保存为学习到的技能以供将来使用。\norigin: ECC\n---\n\n# 持续学习技能\n\n自动评估 Claude Code 会话的结尾，以提取可重用的模式，这些模式可以保存为学习到的技能。\n\n## 何时激活\n\n* 设置从 Claude Code 会话中自动提取模式\n* 为会话评估配置停止钩子\n* 在 `~\u002F.claude\u002Fskills\u002Flearned\u002F` 中审查或整理已学习的技能\n* 调整提取阈值或模式类别\n* 比较 v1（本方法）与 v2（基于本能的方法）\n\n## 工作原理\n\n此技能作为 **停止钩子** 在每个会话结束时运行：\n\n1. **会话评估**：检查会话是否包含足够多的消息（默认：10 条以上）\n2. **模式检测**：从会话中识别可提取的模式\n3. **技能提取**：将有用的模式保存到 `~\u002F.claude\u002Fskills\u002Flearned\u002F`\n\n## 配置\n\n编辑 `config.json` 以进行自定义：\n\n```json\n{\n  \"min_session_length\": 10,\n  \"extraction_threshold\": \"medium\",\n  \"auto_approve\": false,\n  \"learned_skills_path\": \"~\u002F.claude\u002Fskills\u002Flearned\u002F\",\n  \"patterns_to_detect\": [\n    \"error_resolution\",\n    \"user_corrections\",\n    \"workarounds\",\n    \"debugging_techniques\",\n    \"project_specific\"\n  ],\n  \"ignore_patterns\": [\n    \"simple_typos\",\n    \"one_time_fixes\",\n    \"external_api_issues\"\n  ]\n}\n```\n\n## 模式类型\n\n| 模式 | 描述 |\n|---------|-------------|\n| `error_resolution` | 特定错误是如何解决的 |\n| `user_corrections` | 来自用户纠正的模式 |\n| `workarounds` | 框架\u002F库特殊性的解决方案 |\n| `debugging_techniques` | 有效的调试方法 |\n| `project_specific` | 项目特定的约定 |\n\n## 钩子设置\n\n添加到你的 `~\u002F.claude\u002Fsettings.json` 中：\n\n```json\n{\n  \"hooks\": {\n    \"Stop\": [{\n      \"matcher\": \"*\",\n      \"hooks\": [{\n        \"type\": \"command\",\n        \"command\": \"~\u002F.claude\u002Fskills\u002Fcontinuous-learning\u002Fevaluate-session.sh\"\n      }]\n    }]\n  }\n}\n```\n\n## 为什么使用停止钩子？\n\n* **轻量级**：仅在会话结束时运行一次\n* **非阻塞**：不会给每条消息增加延迟\n* **完整上下文**：可以访问完整的会话记录\n\n## 相关\n\n* [长篇指南](https:\u002F\u002Fx.com\u002Faffaanmustafa\u002Fstatus\u002F2014040193557471352) - 关于持续学习的章节\n* `\u002Flearn` 命令 - 在会话中手动提取模式\n\n***\n\n## 对比说明（研究：2025年1月）\n\n### 与 Homunculus 的对比\n\nHomunculus v2 采用了更复杂的方法：\n\n| 功能 | 我们的方法 | Homunculus v2 |\n|---------|--------------|---------------|\n| 观察 | 停止钩子（会话结束时） | PreToolUse\u002FPostToolUse 钩子（100% 可靠） |\n| 分析 | 主上下文 | 后台代理 (Haiku) |\n| 粒度 | 完整技能 | 原子化的“本能” |\n| 置信度 | 无 | 0.3-0.9 加权 |\n| 演进 | 直接到技能 | 本能 → 集群 → 技能\u002F命令\u002F代理 |\n| 共享 | 无 | 导出\u002F导入本能 |\n\n**来自 homunculus 的关键见解：**\n\n> \"v1 依赖技能来观察。技能是概率性的——它们触发的概率约为 50-80%。v2 使用钩子进行观察（100% 可靠），并以本能作为学习行为的原子单元。\"\n\n### 潜在的 v2 增强功能\n\n1. **基于本能的学习** - 更小、原子化的行为，附带置信度评分\n2. **后台观察者** - Haiku 代理并行分析\n3. **置信度衰减** - 如果被反驳，本能会降低置信度\n4. **领域标记** - 代码风格、测试、git、调试等\n5. **演进路径** - 将相关本能聚类为技能\u002F命令\n\n参见：`docs\u002Fcontinuous-learning-v2-spec.md` 以获取完整规范。\n","# 持续学习技能\n\n自动评估 Claude Code 会话的结尾，以提取可重用的模式，这些模式可以保存为学习到的技能。\n\n## 何时激活\n\n* 设置从 Claude Code 会话中自动提取模式\n* 为会话评估配置停止钩子\n* 在 `~\u002F.claude\u002Fskills\u002Flearned\u002F` 中审查或整理已学习的技能\n* 调整提取阈值或模式类别\n* 比较 v1（本方法）与 v2（基于本能的方法）\n\n## 工作原理\n\n此技能作为 **停止钩子** 在每个会话结束时运行：\n\n1. **会话评估**：检查会话是否包含足够多的消息（默认：10 条以上）\n2. **模式检测**：从会话中识别可提取的模式\n3. **技能提取**：将有用的模式保存到 `~\u002F.claude\u002Fskills\u002Flearned\u002F`\n\n## 配置\n\n编辑 `config.json` 以进行自定义：\n\n```json\n{\n  \"min_session_length\": 10,\n  \"extraction_threshold\": \"medium\",\n  \"auto_approve\": false,\n  \"learned_skills_path\": \"~\u002F.claude\u002Fskills\u002Flearned\u002F\",\n  \"patterns_to_detect\": [\n    \"error_resolution\",\n    \"user_corrections\",\n    \"workarounds\",\n    \"debugging_techniques\",\n    \"project_specific\"\n  ],\n  \"ignore_patterns\": [\n    \"simple_typos\",\n    \"one_time_fixes\",\n    \"external_api_issues\"\n  ]\n}\n```\n\n## 模式类型\n\n| 模式 | 描述 |\n|---------|-------------|\n| `error_resolution` | 特定错误是如何解决的 |\n| `user_corrections` | 来自用户纠正的模式 |\n| `workarounds` | 框架\u002F库特殊性的解决方案 |\n| `debugging_techniques` | 有效的调试方法 |\n| `project_specific` | 项目特定的约定 |\n\n## 钩子设置\n\n添加到你的 `~\u002F.claude\u002Fsettings.json` 中：\n\n```json\n{\n  \"hooks\": {\n    \"Stop\": [{\n      \"matcher\": \"*\",\n      \"hooks\": [{\n        \"type\": \"command\",\n        \"command\": \"~\u002F.claude\u002Fskills\u002Fcontinuous-learning\u002Fevaluate-session.sh\"\n      }]\n    }]\n  }\n}\n```\n\n## 为什么使用停止钩子？\n\n* **轻量级**：仅在会话结束时运行一次\n* **非阻塞**：不会给每条消息增加延迟\n* **完整上下文**：可以访问完整的会话记录\n\n## 相关\n\n* [长篇指南](https:\u002F\u002Fx.com\u002Faffaanmustafa\u002Fstatus\u002F2014040193557471352) - 关于持续学习的章节\n* `\u002Flearn` 命令 - 在会话中手动提取模式\n\n***\n\n## 对比说明（研究：2025年1月）\n\n### 与 Homunculus 的对比\n\nHomunculus v2 采用了更复杂的方法：\n\n| 功能 | 我们的方法 | Homunculus v2 |\n|---------|--------------|---------------|\n| 观察 | 停止钩子（会话结束时） | PreToolUse\u002FPostToolUse 钩子（100% 可靠） |\n| 分析 | 主上下文 | 后台代理 (Haiku) |\n| 粒度 | 完整技能 | 原子化的“本能” |\n| 置信度 | 无 | 0.3-0.9 加权 |\n| 演进 | 直接到技能 | 本能 → 集群 → 技能\u002F命令\u002F代理 |\n| 共享 | 无 | 导出\u002F导入本能 |\n\n**来自 homunculus 的关键见解：**\n\n> \"v1 依赖技能来观察。技能是概率性的——它们触发的概率约为 50-80%。v2 使用钩子进行观察（100% 可靠），并以本能作为学习行为的原子单元。\"\n\n### 潜在的 v2 增强功能\n\n1. **基于本能的学习** - 更小、原子化的行为，附带置信度评分\n2. **后台观察者** - Haiku 代理并行分析\n3. **置信度衰减** - 如果被反驳，本能会降低置信度\n4. **领域标记** - 代码风格、测试、git、调试等\n5. **演进路径** - 将相关本能聚类为技能\u002F命令\n\n参见：`docs\u002Fcontinuous-learning-v2-spec.md` 以获取完整规范。\n",{"name":5,"origin":24,"description":7},"ECC","master","d6ca01da0f24a3b0e26e4a8b7b66cbd25d429f5d","skills\u002Feverything-claude-code\u002Fdocs\u002Fzh-CN\u002Fskills\u002Fcontinuous-learning",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":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add SriramGandhiS\u002FSkills --skill continuous-learning",{"tool":40,"command":41},"bunx","bunx skills add SriramGandhiS\u002FSkills --skill continuous-learning",{"tool":43,"command":44},"pnpm","pnpm dlx skills add SriramGandhiS\u002FSkills --skill continuous-learning","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fskills\u002Feverything-claude-code\u002Fdocs\u002Fzh-CN\u002Fskills\u002Fcontinuous-learning\u002FSKILL.md",true,[],[49,56,61,67,74,81],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"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":57,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7325XM47AGWB6K6C4VXKE6B","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fwebgpu-threejs-tsl\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"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":64,"categories":65,"keywords":66,"publishedAt":19},"01M7325WP6DES69JKC840VMFEP","verification-loop","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"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":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"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":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"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",[],[]]