[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77SZP84A1KXNES55PXMA636":3,"skill-same:01M77SZP84A1KXNES55PXMA636":62},{"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":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":44,"ownerHtmlUrl":45,"ownerBlogUrl":6,"ownerDescription":46,"updatedAt":47,"install":48,"resources":61},"01M77SZP84A1KXNES55PXMA636","requirement-comprehension-engine",null,"Advanced requirement comprehension and skill orchestration engine. Analyzes complex\u002Fmulti-step user requests, determines which skills to invoke and in what order, builds task decomposition trees. Delegates memory management to complex-memory-manager and self-iteration to self-iteration-engine for cross-skill consistency. Triggers: multi-intent requests, ambiguous instructions, requests spanning multiple skill domains, structured requirement analysis.","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\u002Fr\u002Frequirement-comprehension-engine\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: requirement-comprehension-engine\ndescription: >\n  Advanced requirement comprehension and skill orchestration engine.\n  Analyzes complex\u002Fmulti-step user requests, determines which skills to invoke\n  and in what order, builds task decomposition trees.\n  Delegates memory management to complex-memory-manager and self-iteration to\n  self-iteration-engine for cross-skill consistency.\n  Triggers: multi-intent requests, ambiguous instructions, requests spanning\n  multiple skill domains, structured requirement analysis.\nversion: 1.2.0\nmetadata:\n  openclaw:\n    emoji: \"🧠\"\n    homepage: https:\u002F\u002Fclawhub.ai\u002FBusTes01\u002Frequirement-comprehension-engine\n    models:\n      - gpt-4\n      - deepseek-v4-flash\n      - gemini-2.0-flash\n      - claude-4-opus\n    requires:\n      skills:\n        - complex-memory-manager\n        - self-iteration-engine\n---\n\n# 🧠 Requirement Comprehension Engine\n\nA metacognitive skill that equips agents with structured requirement analysis, skill selection & orchestration. Delegates memory management to **complex-memory-manager** and self-iteration to **self-iteration-engine** for cross-skill consistency.\n\n## Core Capabilities\n\n### 1. Requirement Analysis & Decomposition\n\nWhen the agent receives a complex or ambiguous request:\n\n**Step 1: Intent Classification**\n- Parse incoming message for explicit intent signals (verbs, domain keywords, output expectations)\n- Classify into: Direct Action \u002F Information Request \u002F Creative Generation \u002F Analysis & Insight \u002F Meta-Request \u002F Multi-Step Workflow\n- If ambiguous, flag as **Under-Specified** and use elicitation templates\n\n**Step 2: Structured Decomposition**\nBreak the request into a tree:\n```\nOriginal Request\n├── Intent A (primary)\n│   ├── Sub-goal A1 → skill\u002Faction candidate\n│   ├── Sub-goal A2 → skill\u002Faction candidate\n│   └── Dependency check\n├── Intent B (secondary)\n│   └── ...\n└── Cross-cutting concerns (privacy, cost, performance)\n```\n\n**Step 3: Skill Mapping**\nFor each sub-goal, select the best matching skill:\n- Check `name` + `description` of all available skills (always in context as metadata)\n- Rank matching skills by semantic relevance\n- If no match → fallback to general knowledge\n- If multiple → pick the most specific or orchestrate\n\n### 2. Skill Orchestration Logic\n\n| Situation | Action |\n|-----------|--------|\n| Single clear intent, single skill | Direct invocation |\n| Multiple independent intents | Parallel execution |\n| Multi-step pipeline (output A → input B) | Sequential orchestration with handoff |\n| Full autonomy requested | Analyze, decide, execute, explain |\n| Conflicting skill capabilities | Prefer skill with more specific description |\n\n**Handoff Protocol:**\n```\n[ComprehensionEngine] Handoff: Skill-A → Skill-B\n  Context: {user's original intent excerpt}\n  Skill-A result: {summary}\n  Skill-B requirement: {what Skill-B needs to continue}\n```\n\n### 3. Requirement Elicitation Templates\n\nWhen a request is **under-specified**:\n\n**Pattern A: Missing Output Format**\n> \"I need to confirm the output format — do you want a daily report, summary, table, chart, code, or something else?\"\n\n**Pattern B: Missing Scope**\n> \"This request seems broad. Could you narrow down the focus? For example: Option A, Option B, or Option C?\"\n\n**Pattern C: Ambiguous Intent**\n> \"I see two possible directions: do you want me to analyze existing data, or go out and collect new data?\"\n\n**Pattern D: Multi-Step Confirmation**\n> \"I plan to do this in three steps: ① collect latest market data ② analyze trends ③ generate a visualization. Does that work?\"\n\n### 4. Delegation to Shared Components\n\n| Function | Delegated To | How |\n|----------|-------------|-----|\n| Persistent memory (T1\u002FT2\u002FT3) | `complex-memory-manager` | Use its encrypt\u002Fdecrypt, storage conventions, and cleanup protocols |\n| Usage logging & performance tracking | `self-iteration-engine` | Use its log format, review cycles, and update matrix |\n| Self-iteration decisions | `self-iteration-engine` | Check triggers, run update decision matrix |\n| New skill creation proposals | `self-iteration-engine` | Use its proposal template |\n\n## Quick Reference: Skill Selection Flow\n\n```\nUser speaks\n  ↓\nParse & Classify Intent\n  ↓\nIs it clear? ──No──→ Use Elicitation Templates\n  │                     ↓\n  Yes←── User clarifies\n  ↓\nDecompose into sub-goals\n  ↓\nFor each sub-goal:\n  ├── Match skill by name+description\n  ├── If match: check last-review-date; if >30d → quick scan SKILL.md\n  ├── If no match: fallback to general knowledge\n  └── If multi-skill: orchestrate (parallel or sequential)\n  ↓\nExecute & Deliver\n  ↓\nLog outcome → Delegate to self-iteration-engine\n  ↓\n[Periodic] Delegate review to self-iteration-engine + memory cleanup to complex-memory-manager\n```\n\n## Dependency Check\n\nBefore each orchestration run:\n1. Verify `complex-memory-manager` metadata description is in context\n2. Verify `self-iteration-engine` metadata description is in context\n3. If either is missing, they may not be installed — fallback to built-in behavior\n\n---\n\n# 🧠 需求理解引擎\n\n一个元认知技能，赋予Agent结构化的需求分析、技能选择与编排能力。将持久化记忆委托给 **complex-memory-manager**，将自迭代委托给 **self-iteration-engine**，实现跨技能一致性。\n\n## 核心能力\n\n### 1. 需求分析与分解\n\n当Agent收到复杂或模糊请求时：\n\n**第一步：意图分类**\n- 解析输入信息的意图信号\n- 分类：直接操作 \u002F 信息查询 \u002F 创意生成 \u002F 分析洞察 \u002F 元请求 \u002F 多步工作流\n- 若模棱两可，标记为\"信息不足\"并使用澄清模板\n\n**第二步：结构化分解**\n将请求拆解为树状结构\n\n**第三步：Skill映射**\n为每个子目标选择最佳匹配skill\n\n### 2. 技能编排逻辑\n\n| 场景 | 行动 |\n|------|------|\n| 单一明确意图 | 直接调用 |\n| 多个独立意图 | 并行执行 |\n| 多步流水线 | 顺序编排+交接记录 |\n| 用户要求自主 | 分析→决策→执行→解释 |\n| 技能冲突 | 选择描述更具体的 |\n\n### 3. 需求澄清模板\n\n在请求信息不足时使用四种追问模式（详见英文版）。\n\n### 4. 委托给共享组件\n\n| 功能 | 委托给 | 方式 |\n|------|--------|------|\n| 持久化记忆(T1\u002FT2\u002FT3) | `complex-memory-manager` | 使用其加密\u002F解密、存储规范、清理协议 |\n| 使用日志与性能追踪 | `self-iteration-engine` | 使用其日志格式、审查周期、更新矩阵 |\n| 自迭代决策 | `self-iteration-engine` | 检查触发条件、运行更新决策矩阵 |\n| 新技能创建建议 | `self-iteration-engine` | 使用其提案模板 |\n\n## 依赖检查\n\n每次编排运行前：\n1. 检查 `complex-memory-manager` 的 metadata 是否在上下文中\n2. 检查 `self-iteration-engine` 的 metadata 是否在上下文中\n3. 若缺失，可能未安装——回退到内置基础行为\n\n## 参考文件\n\n- `references\u002Forchestration-patterns.md` — 高级多skill编排示例\n","# 🧠 Requirement Comprehension Engine\n\nA metacognitive skill that equips agents with structured requirement analysis, skill selection & orchestration. Delegates memory management to **complex-memory-manager** and self-iteration to **self-iteration-engine** for cross-skill consistency.\n\n## Core Capabilities\n\n### 1. Requirement Analysis & Decomposition\n\nWhen the agent receives a complex or ambiguous request:\n\n**Step 1: Intent Classification**\n- Parse incoming message for explicit intent signals (verbs, domain keywords, output expectations)\n- Classify into: Direct Action \u002F Information Request \u002F Creative Generation \u002F Analysis & Insight \u002F Meta-Request \u002F Multi-Step Workflow\n- If ambiguous, flag as **Under-Specified** and use elicitation templates\n\n**Step 2: Structured Decomposition**\nBreak the request into a tree:\n```\nOriginal Request\n├── Intent A (primary)\n│   ├── Sub-goal A1 → skill\u002Faction candidate\n│   ├── Sub-goal A2 → skill\u002Faction candidate\n│   └── Dependency check\n├── Intent B (secondary)\n│   └── ...\n└── Cross-cutting concerns (privacy, cost, performance)\n```\n\n**Step 3: Skill Mapping**\nFor each sub-goal, select the best matching skill:\n- Check `name` + `description` of all available skills (always in context as metadata)\n- Rank matching skills by semantic relevance\n- If no match → fallback to general knowledge\n- If multiple → pick the most specific or orchestrate\n\n### 2. Skill Orchestration Logic\n\n| Situation | Action |\n|-----------|--------|\n| Single clear intent, single skill | Direct invocation |\n| Multiple independent intents | Parallel execution |\n| Multi-step pipeline (output A → input B) | Sequential orchestration with handoff |\n| Full autonomy requested | Analyze, decide, execute, explain |\n| Conflicting skill capabilities | Prefer skill with more specific description |\n\n**Handoff Protocol:**\n```\n[ComprehensionEngine] Handoff: Skill-A → Skill-B\n  Context: {user's original intent excerpt}\n  Skill-A result: {summary}\n  Skill-B requirement: {what Skill-B needs to continue}\n```\n\n### 3. Requirement Elicitation Templates\n\nWhen a request is **under-specified**:\n\n**Pattern A: Missing Output Format**\n> \"I need to confirm the output format — do you want a daily report, summary, table, chart, code, or something else?\"\n\n**Pattern B: Missing Scope**\n> \"This request seems broad. Could you narrow down the focus? For example: Option A, Option B, or Option C?\"\n\n**Pattern C: Ambiguous Intent**\n> \"I see two possible directions: do you want me to analyze existing data, or go out and collect new data?\"\n\n**Pattern D: Multi-Step Confirmation**\n> \"I plan to do this in three steps: ① collect latest market data ② analyze trends ③ generate a visualization. Does that work?\"\n\n### 4. Delegation to Shared Components\n\n| Function | Delegated To | How |\n|----------|-------------|-----|\n| Persistent memory (T1\u002FT2\u002FT3) | `complex-memory-manager` | Use its encrypt\u002Fdecrypt, storage conventions, and cleanup protocols |\n| Usage logging & performance tracking | `self-iteration-engine` | Use its log format, review cycles, and update matrix |\n| Self-iteration decisions | `self-iteration-engine` | Check triggers, run update decision matrix |\n| New skill creation proposals | `self-iteration-engine` | Use its proposal template |\n\n## Quick Reference: Skill Selection Flow\n\n```\nUser speaks\n  ↓\nParse & Classify Intent\n  ↓\nIs it clear? ──No──→ Use Elicitation Templates\n  │                     ↓\n  Yes←── User clarifies\n  ↓\nDecompose into sub-goals\n  ↓\nFor each sub-goal:\n  ├── Match skill by name+description\n  ├── If match: check last-review-date; if >30d → quick scan SKILL.md\n  ├── If no match: fallback to general knowledge\n  └── If multi-skill: orchestrate (parallel or sequential)\n  ↓\nExecute & Deliver\n  ↓\nLog outcome → Delegate to self-iteration-engine\n  ↓\n[Periodic] Delegate review to self-iteration-engine + memory cleanup to complex-memory-manager\n```\n\n## Dependency Check\n\nBefore each orchestration run:\n1. Verify `complex-memory-manager` metadata description is in context\n2. Verify `self-iteration-engine` metadata description is in context\n3. If either is missing, they may not be installed — fallback to built-in behavior\n\n---\n\n# 🧠 需求理解引擎\n\n一个元认知技能，赋予Agent结构化的需求分析、技能选择与编排能力。将持久化记忆委托给 **complex-memory-manager**，将自迭代委托给 **self-iteration-engine**，实现跨技能一致性。\n\n## 核心能力\n\n### 1. 需求分析与分解\n\n当Agent收到复杂或模糊请求时：\n\n**第一步：意图分类**\n- 解析输入信息的意图信号\n- 分类：直接操作 \u002F 信息查询 \u002F 创意生成 \u002F 分析洞察 \u002F 元请求 \u002F 多步工作流\n- 若模棱两可，标记为\"信息不足\"并使用澄清模板\n\n**第二步：结构化分解**\n将请求拆解为树状结构\n\n**第三步：Skill映射**\n为每个子目标选择最佳匹配skill\n\n### 2. 技能编排逻辑\n\n| 场景 | 行动 |\n|------|------|\n| 单一明确意图 | 直接调用 |\n| 多个独立意图 | 并行执行 |\n| 多步流水线 | 顺序编排+交接记录 |\n| 用户要求自主 | 分析→决策→执行→解释 |\n| 技能冲突 | 选择描述更具体的 |\n\n### 3. 需求澄清模板\n\n在请求信息不足时使用四种追问模式（详见英文版）。\n\n### 4. 委托给共享组件\n\n| 功能 | 委托给 | 方式 |\n|------|--------|------|\n| 持久化记忆(T1\u002FT2\u002FT3) | `complex-memory-manager` | 使用其加密\u002F解密、存储规范、清理协议 |\n| 使用日志与性能追踪 | `self-iteration-engine` | 使用其日志格式、审查周期、更新矩阵 |\n| 自迭代决策 | `self-iteration-engine` | 检查触发条件、运行更新决策矩阵 |\n| 新技能创建建议 | `self-iteration-engine` | 使用其提案模板 |\n\n## 依赖检查\n\n每次编排运行前：\n1. 检查 `complex-memory-manager` 的 metadata 是否在上下文中\n2. 检查 `self-iteration-engine` 的 metadata 是否在上下文中\n3. 若缺失，可能未安装——回退到内置基础行为\n\n## 参考文件\n\n- `references\u002Forchestration-patterns.md` — 高级多skill编排示例\n",{"name":5,"version":24,"metadata":25,"description":38},"1.2.0",{"openclaw":26},{"emoji":27,"models":28,"homepage":33,"requires":34},"🧠",[29,30,31,32],"gpt-4","deepseek-v4-flash","gemini-2.0-flash","claude-4-opus","https:\u002F\u002Fclawhub.ai\u002FBusTes01\u002Frequirement-comprehension-engine",{"skills":35},[36,37],"complex-memory-manager","self-iteration-engine","Advanced requirement comprehension and skill orchestration engine. Analyzes complex\u002Fmulti-step user requests, determines which skills to invoke and in what order, builds task decomposition trees. Delegates memory management to complex-memory-manager and self-iteration to self-iteration-engine for cross-skill consistency. Triggers: multi-intent requests, ambiguous instructions, requests spanning multiple skill domains, structured requirement analysis.\n","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fr\u002Frequirement-comprehension-engine",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":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill requirement-comprehension-engine",{"tool":54,"command":55},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill requirement-comprehension-engine",{"tool":57,"command":58},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill requirement-comprehension-engine","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fr\u002Frequirement-comprehension-engine\u002FSKILL.md",true,[],[63,70,77,84,91,98],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"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":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"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":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"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":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"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":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"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":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"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",[],[]]