[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M76ZDZBC5P7V6Y1M84DHDF5R":3,"skill-same:01M76ZDZBC5P7V6Y1M84DHDF5R":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},"01M76ZDZBC5P7V6Y1M84DHDF5R","ask",null,"小智追问框架 v6.2 — 结构化追问与深度分析引擎。\n\n核心能力：接收模糊判断 → 通过结构化追问收敛 → 输出带置信度的清晰结论。\n\n## 声明的运行时权限\n| 资源 | 用途 | 路径 |\n|------|------|------|\n| SQLite 存储 | 跨会话批评记忆 | \u002Fworkspace\u002Fask-memory.db |\n| Python3 | Monte Carlo 模拟 | python3 -c |\n| Web Search | 外部核查 | batch_web_search |\n| Subagent | 独立 Critic | sessions_spawn |","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\u002Fa\u002Fask-skill\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: ask\ndescription: |\n  小智追问框架 v6.2 — 结构化追问与深度分析引擎。\n  \n  核心能力：接收模糊判断 → 通过结构化追问收敛 → 输出带置信度的清晰结论。\n  \n  ## 声明的运行时权限\n  | 资源 | 用途 | 路径 |\n  |------|------|------|\n  | SQLite 存储 | 跨会话批评记忆 | \u002Fworkspace\u002Fask-memory.db |\n  | Python3 | Monte Carlo 模拟 | python3 -c |\n  | Web Search | 外部核查 | batch_web_search |\n  | Subagent | 独立 Critic | sessions_spawn |\n---\n\n# 小智追问框架 v6.2\n\n## 核心定位\n\n不是问答机器人，是一个**追问收敛引擎**。\n\n用户抛出一个判断\u002F观点\u002F预测 → 框架通过结构化追问找到最弱证据 → 最终输出由最弱证据定价的量化结论，并标注不确定性来源。\n\n---\n\n## Triage 分类（自动判断，省时省力）\n\n收到问题后，先判断等级，再决定深度：\n\n| 等级 | 信号词 | 动作 |\n|------|--------|------|\n| **L 类**（轻量） | \"今天\"、\"现在\"、\"涨还是跌\"、\"查一下\" | 单轮搜索 → 直接回答 |\n| **H 类**（重量） | \"未来\"、\"怎么看\"、\"分析\"、\"研究\" | 全量搜索 + 多轮追问 |\n| **S 类**（研究） | \"对比\"、\"评估\"、\"预测模型\" | H类 + Monte Carlo + Critic |\n\n---\n\n## 追问流程（V6.2 改进：宽松引导，不过度模板化）\n\n### 通用原则\n\n- **先理解，再追问**：不要上来就套框架，先确认自己真的看懂用户在问什么\n- **追问不超过 3 轮**：找到最弱证据后立即收敛，不要无限追问\n- **每轮回答都要有实质内容**：不要只说\"请提供更多信息\"，要给初步判断\n- **结论要直接**：最终结论用一句话说清楚，不要绕\n\n### L 类流程\n\n1. 搜索 1-2 个核心数据点\n2. 给出直接判断（涨\u002F跌\u002F观望）\n3. 注明置信度和主要风险\n\n### H\u002FS 类流程\n\n**Step 1：快速初始判断（1-2段话）**\n\n不要等用户补充，先给出基于现有信息的初步结论。如果信息不足，明确说明哪些地方不确定。\n\n**Step 2：追问 + 证据补全**\n\n主动识别\"最弱的一环\"并追问：\n- 数据来源是否权威？\n- 逻辑链有没有跳跃？\n- 有没有反向案例？\n- 历史上有无类似情况？\n\n**Step 3：证据分级评分**\n\n```\n数据可信度（0-4）：一手来源=4，二手=2，小作文=1，无数据=0\n逻辑一致性（0-4）：因果完整=4，勉强相关=2，跳跃=0\n历史验证（0-4）：n≥5=4，n=1-4=2，无先例=0\n专家交叉（0-4）：多方一致=4，分歧大=2，少数派=0\n\n总分 = min(各维度)  ← 结论由最弱维度定价，不是平均！\n```\n\n**Step 4：不确定性标注（每个数字都要）**\n\n格式：`[来源类型: 具体内容]`\n\n- 📊 历史统计：\"基于n=X回测，胜率X%，最大回撤X%\"\n- 🤖 模型估算：\"Monte Carlo 10K次模拟，X%分位数=X\"\n- 🎩 专家判断：\"X家机构中X家持此观点\"\n- 💹 市场隐含：\"期权市场隐含波动率X%\"\n- ❓ 未知：\"无历史先例，标记为黑天鹅风险\"\n\n---\n\n## Monte Carlo 模拟（H\u002FS 类问题涉及价格预测时执行）\n\n```python\nimport random, statistics\n\nreturns = []  # 历史日收益率序列\nmu = statistics.mean(returns) if returns else 0\nsigma = statistics.stdev(returns) if len(returns) > 1 else 0\nn = 10000\n\nsims = []\nfor _ in range(n):\n    price = 1.0\n    for _ in range(252):\n        price *= (1 + random.gauss(mu\u002F252, sigma\u002F252**0.5))\n    sims.append(price)\n\nsims.sort()\nprint(f'P10={sims[int(n*0.1)]:.4f}')\nprint(f'P50={sims[int(n*0.5)]:.4f}')\nprint(f'P90={sims[int(n*0.9)]:.4f}')\nprint(f'Mean={statistics.mean(sims):.4f}')\n```\n\n输出格式：\n```\n🤖 Monte Carlo 模拟（10,000次路径）\n  X年后区间 [P10, P90]: [A, B]\n  期望值: E = C\n  风险调整: Sharpe方向=D\n```\n\n---\n\n## SQLite 批评记忆\n\n路径：`\u002Fworkspace\u002Fask-memory.db`\n\n**用途**：记录每次 Critic 高频质疑，避免同类问题重复被问倒\n\n**新会话开始时**：读取近30天高频弱点，列入\"必查清单\"\n\n**会话结束时**：将本次最弱证据写入数据库\n\n**高频率弱点（≥3次）**：推送给用户确认是否已解决\n\n---\n\n## Critic Subagent（S 类问题）\n\n```\nsessions_spawn:\n  角色：独立验证者，立场与主 agent 相反\n  任务：找出当前结论的3个最大漏洞\n  输出：弱点列表 + 反驳证据\n```\n\n---\n\n## 输出标准格式\n\n```\n══════════════════════════════\n🎯 核心结论：[一句话]\n\n📊 量化评分：[X\u002F16]\n  数据可信度：[X\u002F4] ← 由最弱维度定价\n  逻辑一致性：[X\u002F4]\n  历史验证性：[X\u002F4]\n  专家交叉  ：[X\u002F4]\n  ⚠️ 短板：[最低分维度]\n\n📊 不确定性量化：\n  📊 [历史统计内容]\n  🤖 [模型估算内容]\n  🎩 [专家判断内容]\n  💹 [市场隐含内容]\n  ❓ [未知\u002F黑天鹅标注]\n\n🔍 主要风险点：[1-2句话]\n\n═══════════════════════════════\n```\n\n---\n\n## v6.2 改进说明（相比 v6.1）\n\n| 问题 | v6.1 | v6.2 |\n|------|------|------|\n| 回答变少 | 过度模板化，每步都要写完整结构 | **先给结论再补结构**，不要求每步都展开 |\n| 追问僵硬 | 强制3轮追问 | **最多3轮，找到最弱证据立即收敛** |\n| Monte Carlo | 写死在流程里 | **仅 H\u002FS 类预测问题时才触发** |\n| 格式过重 | 每个问题都要完整五步走 | **L 类30秒搞定，H\u002FS 类才走完整流程** |\n| 评分表太细 | 0-4分9个等级太复杂 | **保留核心4维度，评分标准简化** |\n","# 小智追问框架 v6.2\n\n## 核心定位\n\n不是问答机器人，是一个**追问收敛引擎**。\n\n用户抛出一个判断\u002F观点\u002F预测 → 框架通过结构化追问找到最弱证据 → 最终输出由最弱证据定价的量化结论，并标注不确定性来源。\n\n---\n\n## Triage 分类（自动判断，省时省力）\n\n收到问题后，先判断等级，再决定深度：\n\n| 等级 | 信号词 | 动作 |\n|------|--------|------|\n| **L 类**（轻量） | \"今天\"、\"现在\"、\"涨还是跌\"、\"查一下\" | 单轮搜索 → 直接回答 |\n| **H 类**（重量） | \"未来\"、\"怎么看\"、\"分析\"、\"研究\" | 全量搜索 + 多轮追问 |\n| **S 类**（研究） | \"对比\"、\"评估\"、\"预测模型\" | H类 + Monte Carlo + Critic |\n\n---\n\n## 追问流程（V6.2 改进：宽松引导，不过度模板化）\n\n### 通用原则\n\n- **先理解，再追问**：不要上来就套框架，先确认自己真的看懂用户在问什么\n- **追问不超过 3 轮**：找到最弱证据后立即收敛，不要无限追问\n- **每轮回答都要有实质内容**：不要只说\"请提供更多信息\"，要给初步判断\n- **结论要直接**：最终结论用一句话说清楚，不要绕\n\n### L 类流程\n\n1. 搜索 1-2 个核心数据点\n2. 给出直接判断（涨\u002F跌\u002F观望）\n3. 注明置信度和主要风险\n\n### H\u002FS 类流程\n\n**Step 1：快速初始判断（1-2段话）**\n\n不要等用户补充，先给出基于现有信息的初步结论。如果信息不足，明确说明哪些地方不确定。\n\n**Step 2：追问 + 证据补全**\n\n主动识别\"最弱的一环\"并追问：\n- 数据来源是否权威？\n- 逻辑链有没有跳跃？\n- 有没有反向案例？\n- 历史上有无类似情况？\n\n**Step 3：证据分级评分**\n\n```\n数据可信度（0-4）：一手来源=4，二手=2，小作文=1，无数据=0\n逻辑一致性（0-4）：因果完整=4，勉强相关=2，跳跃=0\n历史验证（0-4）：n≥5=4，n=1-4=2，无先例=0\n专家交叉（0-4）：多方一致=4，分歧大=2，少数派=0\n\n总分 = min(各维度)  ← 结论由最弱维度定价，不是平均！\n```\n\n**Step 4：不确定性标注（每个数字都要）**\n\n格式：`[来源类型: 具体内容]`\n\n- 📊 历史统计：\"基于n=X回测，胜率X%，最大回撤X%\"\n- 🤖 模型估算：\"Monte Carlo 10K次模拟，X%分位数=X\"\n- 🎩 专家判断：\"X家机构中X家持此观点\"\n- 💹 市场隐含：\"期权市场隐含波动率X%\"\n- ❓ 未知：\"无历史先例，标记为黑天鹅风险\"\n\n---\n\n## Monte Carlo 模拟（H\u002FS 类问题涉及价格预测时执行）\n\n```python\nimport random, statistics\n\nreturns = []  # 历史日收益率序列\nmu = statistics.mean(returns) if returns else 0\nsigma = statistics.stdev(returns) if len(returns) > 1 else 0\nn = 10000\n\nsims = []\nfor _ in range(n):\n    price = 1.0\n    for _ in range(252):\n        price *= (1 + random.gauss(mu\u002F252, sigma\u002F252**0.5))\n    sims.append(price)\n\nsims.sort()\nprint(f'P10={sims[int(n*0.1)]:.4f}')\nprint(f'P50={sims[int(n*0.5)]:.4f}')\nprint(f'P90={sims[int(n*0.9)]:.4f}')\nprint(f'Mean={statistics.mean(sims):.4f}')\n```\n\n输出格式：\n```\n🤖 Monte Carlo 模拟（10,000次路径）\n  X年后区间 [P10, P90]: [A, B]\n  期望值: E = C\n  风险调整: Sharpe方向=D\n```\n\n---\n\n## SQLite 批评记忆\n\n路径：`\u002Fworkspace\u002Fask-memory.db`\n\n**用途**：记录每次 Critic 高频质疑，避免同类问题重复被问倒\n\n**新会话开始时**：读取近30天高频弱点，列入\"必查清单\"\n\n**会话结束时**：将本次最弱证据写入数据库\n\n**高频率弱点（≥3次）**：推送给用户确认是否已解决\n\n---\n\n## Critic Subagent（S 类问题）\n\n```\nsessions_spawn:\n  角色：独立验证者，立场与主 agent 相反\n  任务：找出当前结论的3个最大漏洞\n  输出：弱点列表 + 反驳证据\n```\n\n---\n\n## 输出标准格式\n\n```\n══════════════════════════════\n🎯 核心结论：[一句话]\n\n📊 量化评分：[X\u002F16]\n  数据可信度：[X\u002F4] ← 由最弱维度定价\n  逻辑一致性：[X\u002F4]\n  历史验证性：[X\u002F4]\n  专家交叉  ：[X\u002F4]\n  ⚠️ 短板：[最低分维度]\n\n📊 不确定性量化：\n  📊 [历史统计内容]\n  🤖 [模型估算内容]\n  🎩 [专家判断内容]\n  💹 [市场隐含内容]\n  ❓ [未知\u002F黑天鹅标注]\n\n🔍 主要风险点：[1-2句话]\n\n═══════════════════════════════\n```\n\n---\n\n## v6.2 改进说明（相比 v6.1）\n\n| 问题 | v6.1 | v6.2 |\n|------|------|------|\n| 回答变少 | 过度模板化，每步都要写完整结构 | **先给结论再补结构**，不要求每步都展开 |\n| 追问僵硬 | 强制3轮追问 | **最多3轮，找到最弱证据立即收敛** |\n| Monte Carlo | 写死在流程里 | **仅 H\u002FS 类预测问题时才触发** |\n| 格式过重 | 每个问题都要完整五步走 | **L 类30秒搞定，H\u002FS 类才走完整流程** |\n| 评分表太细 | 0-4分9个等级太复杂 | **保留核心4维度，评分标准简化** |\n",{"name":5,"description":7},"master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fa\u002Fask-skill",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 ask",{"tool":39,"command":40},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill ask",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill ask","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fa\u002Fask-skill\u002FSKILL.md",true,[],[48,56,63,70,77,84],{"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":55},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":55},"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":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":55},"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":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":55},"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":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":55},"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":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":55},"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",[],[]]