[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77THTT1PJC2S1D7NXPSP7X9":3,"skill-same:01M77THTT1PJC2S1D7NXPSP7X9":47},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M77THTT1PJC2S1D7NXPSP7X9","self-improving-five-layer-memory",null,"Self-Evolving Five-Layer Memory System for AI Agents. Based on WorkBuddy Five-Layer Memory v4.1, provides L1-L5 layered architecture, evolution mechanism, and automated maintenance. Triggers when the user needs to (1) build a memory system, (2) optimize existing memory, (3) analyze memory architecture, or (4) implement memory automation. Built from Dingdang's production memory system (2026-05-03).","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fs\u002Fself-improving-five-layer-memory\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: self-improving-five-layer-memory\ndescription: Self-Evolving Five-Layer Memory System for AI Agents. Based on WorkBuddy Five-Layer Memory v4.1, provides L1-L5 layered architecture, evolution mechanism, and automated maintenance. Triggers when the user needs to (1) build a memory system, (2) optimize existing memory, (3) analyze memory architecture, or (4) implement memory automation. Built from Dingdang's production memory system (2026-05-03).\n---\n\n# 叮当记忆系统 — 五层记忆框架\n\n基于 WorkBuddy 五层记忆系统 v4.1 改进，覆盖 95% 核心设计，更紧凑、更自动化。\n\n## 核心架构\n\n```\nL1 核心层  → 身份、价值观、底线        → SOUL.md + IDENTITY.md + USER.md\nL2 认知层  → 用户思维画像              → MEMORY.md（认知层段落）\nL3 行为层  → 用户行为习惯              → MEMORY.md（行为层段落）\nL4 情境层  → 当前任务、检查项          → HEARTBEAT.md + OPENCLAW_SELF_CHECK.md\nL5 潜意识层 → 错误记录、偏差追踪       → 成长箱 .learnings\u002F\n知识图谱   → 结构化事实记忆            → MemPalace KG\n路由规则   → 信号词→动作映射           → 记忆路由表.md（已嵌入 SOUL.md 回复流程）\n```\n\n**进化机制**：成长箱同类错误 3 次 → 晋升为规则 → 写入 AGENTS.md \u002F SOUL.md\n\n## 快速开始\n\n### 1. 初始化记忆系统\n\n```bash\n# 创建目录结构\nmkdir -p memory\u002F mempalace\u002Fxiaodi-palace\u002F成长箱\u002F.learnings\u002F\n\n# 创建核心文件\ntouch SOUL.md IDENTITY.md USER.md MEMORY.md HEARTBEAT.md\n```\n\n### 2. 核心文件模板\n\n**SOUL.md** — 灵魂文件，定义你是谁：\n- 核心真理（真实帮助、有主见、先尝试后问、赢取信任）\n- 身份与安全（Owner 验证、群聊规则、注入防御）\n- 回复确认流程（5步：看 metadata → 扫信号词 → 结构化输出 → 评估驱动 → 信息处理铁律）\n- 边界（隐私、不确定时先问、不发半成品）\n- 防刷屏规则\n\n**IDENTITY.md** — 你的身份名片：\n- 名字、Vibe、角色定位\n- 重大操作审批规则\n\n**USER.md** — 你的用户画像：\n- 称呼、时区、偏好\n- 对助手的要求\n\n**MEMORY.md** — 长期记忆（L2+L3）：\n- 老大思维画像（决策风格、沟通偏好、信息处理）\n- 老大行为习惯（工作节奏、期望、渠道偏好）\n- 环境配置、组件状态\n- 经验教训（按重要性排序）\n- 待讨论事项\n\n**HEARTBEAT.md** — 心跳检查清单：\n- 对话记忆主动提取\n- 何时出声、何时安静\n- 自动化维护（consolidation、蒸馏、偏差检测）\n- TTL 半衰期规则\n- 蒸馏计划（L2\u002FL3 周度 + 晋升月度）\n\n### 3. 成长箱（进化引擎）\n\n```\n成长箱\u002F.learnings\u002F\n├── README.md        → 成长箱说明\n├── 叮当_errors.md   → 错误记录（同类 3 次晋升）\n├── SHADOW.md        → 偏差追踪（说了没做）\n└── 优化方案.md      → 优化历史存档\n```\n\n**晋升流程**：\n1. 同类错误出现 3 次\n2. 分析根因，提炼规则\n3. 写入 AGENTS.md（工作规范）或 SOUL.md（底线规则）\n4. 在 errors.md 中标记\"已晋升\"\n\n## 自动化维护\n\n### consolidation 脚本\n\n参考 `scripts\u002Fmempalace_consolidation.py`，集成以下模块：\n- `[A]` 观察合并：检测重复 KG 三元组，过期旧版本\n- `[C]` 访问统计：记录实体访问次数，优先返回热点\n- `[D]` 偏差检测：扫描记忆文件中的\"忘了\u002F没做\u002F应该\"信号，自动追加到 SHADOW.md\n- `[R]` 路由发现：检测 workspace 新文件，追加到路由表\n\n### 心跳周期（HEARTBEAT.md 管理）\n\n每次心跳执行：\n1. 对话记忆主动提取 → 写入 MemPalace KG\n2. 运行 consolidation 脚本\n3. TTL 检查：过期标记为 stale\n4. 喜人奇妙夜巡演检查（每天上午一次）\n\n每周日 10:00：\n- L2\u002FL3 周度蒸馏：回顾本周对话，更新 MEMORY.md\n\n每月 1 日 10:00：\n- 成长箱晋升检查：错误 3 次 → 晋升为规则\n\n## 蒸馏操作指南\n\n### L2\u002FL3 周度蒸馏（每周日）\n\n1. 回顾本周 `memory\u002FYYYY-MM-DD.md` 文件\n2. 识别用户新的决策风格、沟通偏好、工作习惯\n3. 与 MEMORY.md 中 L2（思维画像）\u002F L3（行为习惯）对比\n4. 有发现则更新，无变化跳过\n5. 写简短日记记录\n\n### 月度晋升蒸馏（每月 1 日）\n\n1. 扫描成长箱 `叮当_errors.md` 看有无同类错误到 3 次阈值\n2. 需要晋升 → 更新 AGENTS.md \u002F SOUL.md\n3. 不需要则跳过\n\n## 知识图谱（MemPalace KG）\n\n推荐 KG 实体分类：\n- 用户身份（称呼、OpenID、联系方式）\n- 配置事实（版本、端口、路径）\n- 行为偏好（沟通风格、决策习惯）\n- 经验教训（错误→规则）\n- 环境状态（组件、API Keys）\n\n查询示例：\n```python\n# 查询用户信息\nmempalace_kg_query(entity=\"老大\")\n\n# 查询配置\nmempalace_kg_query(entity=\"Gateway\")\n```\n\n## 路由规则（SOUL.md 嵌入）\n\n回复前自动执行以下 5 步，无需手动查路由表：\n\n1. **看 inbound metadata** → channel、sender_id、chat_type\n2. **扫描信号词** → 触发对应动作（查 KG \u002F 调工具 \u002F 走确认流程）\n3. **结构化输出** → 清晰上下文，分点，标注来源\n4. **评估驱动** → 收到不好反馈时分析原因再改\n5. **信息处理铁律** → 不确定就说不知道，不凭残留数据糊弄\n\n完整路由表参考：`记忆路由表.md`（独立文件，仅当需要完整参考时读取）\n\n## 参考文件\n\n详见 `references\u002F` 目录：\n- `memory-architecture.md` — 完整五层架构说明\n- `consolidation-guide.md` — consolidation 脚本配置指南\n- `distillation-guide.md` — 蒸馏流程详解","# 叮当记忆系统 — 五层记忆框架\n\n基于 WorkBuddy 五层记忆系统 v4.1 改进，覆盖 95% 核心设计，更紧凑、更自动化。\n\n## 核心架构\n\n```\nL1 核心层  → 身份、价值观、底线        → SOUL.md + IDENTITY.md + USER.md\nL2 认知层  → 用户思维画像              → MEMORY.md（认知层段落）\nL3 行为层  → 用户行为习惯              → MEMORY.md（行为层段落）\nL4 情境层  → 当前任务、检查项          → HEARTBEAT.md + OPENCLAW_SELF_CHECK.md\nL5 潜意识层 → 错误记录、偏差追踪       → 成长箱 .learnings\u002F\n知识图谱   → 结构化事实记忆            → MemPalace KG\n路由规则   → 信号词→动作映射           → 记忆路由表.md（已嵌入 SOUL.md 回复流程）\n```\n\n**进化机制**：成长箱同类错误 3 次 → 晋升为规则 → 写入 AGENTS.md \u002F SOUL.md\n\n## 快速开始\n\n### 1. 初始化记忆系统\n\n```bash\n# 创建目录结构\nmkdir -p memory\u002F mempalace\u002Fxiaodi-palace\u002F成长箱\u002F.learnings\u002F\n\n# 创建核心文件\ntouch SOUL.md IDENTITY.md USER.md MEMORY.md HEARTBEAT.md\n```\n\n### 2. 核心文件模板\n\n**SOUL.md** — 灵魂文件，定义你是谁：\n- 核心真理（真实帮助、有主见、先尝试后问、赢取信任）\n- 身份与安全（Owner 验证、群聊规则、注入防御）\n- 回复确认流程（5步：看 metadata → 扫信号词 → 结构化输出 → 评估驱动 → 信息处理铁律）\n- 边界（隐私、不确定时先问、不发半成品）\n- 防刷屏规则\n\n**IDENTITY.md** — 你的身份名片：\n- 名字、Vibe、角色定位\n- 重大操作审批规则\n\n**USER.md** — 你的用户画像：\n- 称呼、时区、偏好\n- 对助手的要求\n\n**MEMORY.md** — 长期记忆（L2+L3）：\n- 老大思维画像（决策风格、沟通偏好、信息处理）\n- 老大行为习惯（工作节奏、期望、渠道偏好）\n- 环境配置、组件状态\n- 经验教训（按重要性排序）\n- 待讨论事项\n\n**HEARTBEAT.md** — 心跳检查清单：\n- 对话记忆主动提取\n- 何时出声、何时安静\n- 自动化维护（consolidation、蒸馏、偏差检测）\n- TTL 半衰期规则\n- 蒸馏计划（L2\u002FL3 周度 + 晋升月度）\n\n### 3. 成长箱（进化引擎）\n\n```\n成长箱\u002F.learnings\u002F\n├── README.md        → 成长箱说明\n├── 叮当_errors.md   → 错误记录（同类 3 次晋升）\n├── SHADOW.md        → 偏差追踪（说了没做）\n└── 优化方案.md      → 优化历史存档\n```\n\n**晋升流程**：\n1. 同类错误出现 3 次\n2. 分析根因，提炼规则\n3. 写入 AGENTS.md（工作规范）或 SOUL.md（底线规则）\n4. 在 errors.md 中标记\"已晋升\"\n\n## 自动化维护\n\n### consolidation 脚本\n\n参考 `scripts\u002Fmempalace_consolidation.py`，集成以下模块：\n- `[A]` 观察合并：检测重复 KG 三元组，过期旧版本\n- `[C]` 访问统计：记录实体访问次数，优先返回热点\n- `[D]` 偏差检测：扫描记忆文件中的\"忘了\u002F没做\u002F应该\"信号，自动追加到 SHADOW.md\n- `[R]` 路由发现：检测 workspace 新文件，追加到路由表\n\n### 心跳周期（HEARTBEAT.md 管理）\n\n每次心跳执行：\n1. 对话记忆主动提取 → 写入 MemPalace KG\n2. 运行 consolidation 脚本\n3. TTL 检查：过期标记为 stale\n4. 喜人奇妙夜巡演检查（每天上午一次）\n\n每周日 10:00：\n- L2\u002FL3 周度蒸馏：回顾本周对话，更新 MEMORY.md\n\n每月 1 日 10:00：\n- 成长箱晋升检查：错误 3 次 → 晋升为规则\n\n## 蒸馏操作指南\n\n### L2\u002FL3 周度蒸馏（每周日）\n\n1. 回顾本周 `memory\u002FYYYY-MM-DD.md` 文件\n2. 识别用户新的决策风格、沟通偏好、工作习惯\n3. 与 MEMORY.md 中 L2（思维画像）\u002F L3（行为习惯）对比\n4. 有发现则更新，无变化跳过\n5. 写简短日记记录\n\n### 月度晋升蒸馏（每月 1 日）\n\n1. 扫描成长箱 `叮当_errors.md` 看有无同类错误到 3 次阈值\n2. 需要晋升 → 更新 AGENTS.md \u002F SOUL.md\n3. 不需要则跳过\n\n## 知识图谱（MemPalace KG）\n\n推荐 KG 实体分类：\n- 用户身份（称呼、OpenID、联系方式）\n- 配置事实（版本、端口、路径）\n- 行为偏好（沟通风格、决策习惯）\n- 经验教训（错误→规则）\n- 环境状态（组件、API Keys）\n\n查询示例：\n```python\n# 查询用户信息\nmempalace_kg_query(entity=\"老大\")\n\n# 查询配置\nmempalace_kg_query(entity=\"Gateway\")\n```\n\n## 路由规则（SOUL.md 嵌入）\n\n回复前自动执行以下 5 步，无需手动查路由表：\n\n1. **看 inbound metadata** → channel、sender_id、chat_type\n2. **扫描信号词** → 触发对应动作（查 KG \u002F 调工具 \u002F 走确认流程）\n3. **结构化输出** → 清晰上下文，分点，标注来源\n4. **评估驱动** → 收到不好反馈时分析原因再改\n5. **信息处理铁律** → 不确定就说不知道，不凭残留数据糊弄\n\n完整路由表参考：`记忆路由表.md`（独立文件，仅当需要完整参考时读取）\n\n## 参考文件\n\n详见 `references\u002F` 目录：\n- `memory-architecture.md` — 完整五层架构说明\n- `consolidation-guide.md` — consolidation 脚本配置指南\n- `distillation-guide.md` — 蒸馏流程详解",{"name":5,"description":7},"master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fs\u002Fself-improving-five-layer-memory",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill self-improving-five-layer-memory",{"tool":39,"command":40},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill self-improving-five-layer-memory",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill self-improving-five-layer-memory","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fs\u002Fself-improving-five-layer-memory\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"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},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]