[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7E1VJ47PWPRWA7AAQJFAE3Z":3,"skill-same:01M7E1VJ47PWPRWA7AAQJFAE3Z":75},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7E1VJ47PWPRWA7AAQJFAE3Z","viral-article-generator",null,"爆款长文生成（风格路由）：按选题六维匹配气质、生成公众号级母稿与渠道建议。 当前可写 T1-1 风控老炮解构气质、T1-2 深度调查讽刺气质（参数级）；另 12 种仅推荐预告。 用户提到爆款文章、公众号长文、风格路由、半佛气质、兽爷气质、渠道分发时使用。","rufeng0411\u002FNova-Ai-Studio","rufeng0411","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F125196267?v=4","01M7C7KFAM66TF6CD0GFGF8JQW","01M7C7KFB6XYDM1Z0M26N1Z9Z1",1,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002Frufeng0411\u002FNova-Ai-Studio\u002Fblob\u002Fmain\u002Fskills\u002Fviral-article-generator\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: viral-article-generator\ndescription: >\n  爆款长文生成（风格路由）：按选题六维匹配气质、生成公众号级母稿与渠道建议。\n  当前可写 T1-1 风控老炮解构气质、T1-2 深度调查讽刺气质（参数级）；另 12 种仅推荐预告。\n  用户提到爆款文章、公众号长文、风格路由、半佛气质、兽爷气质、渠道分发时使用。\n---\n\n\u003C!-- NOVA-EXEC-BEGIN -->\n## Nova Ai-Studio 集成（优先于下文）\n\n- 所有成果写入 **`\u003Ctask-artifact-dir>\u002F`**；勿写工作区根、`output\u002F` 或其它 `artifacts\u002Ftask-*`。\n- **禁止**首 turn `ask_user_question`；**禁止**正文末「请选择一个风格」——推荐模式直接开写最高分 full。\n- **禁止** Task\u002Fsubagent；禁止以 `skills\u002Fvendor\u002Fviral-article-generator\u002F` 为风格权威。\n- **须交付四文件（同 turn 写完即停，basename 固定）**：\n  1. `article-brief.md` — 六维 + TOP3（标 full\u002Fstub）+ 主风格\u002F理由 + 结构说明要点 + **2 条变体方向**（各 1 句）\n  2. `article.md` — 3–5 标题候选 + 正文（主槽；可选副写「爆款母稿.md」）\n  3. `quotes.md` — 可截图金句（5–12 条）\n  4. `channel-plan.md` — 按 `channel-matrix` 短模板，**≤800 字**\n- `data-sources.md` 由引擎同步时勿抢权威槽；未要求配图时禁 `generate_image`。\n- 研究：`web_search` 1–3 次；选定风格后最多再读 **1** 份 `style-t1-1.md` 或 `style-t1-2.md`（勿连环读 3–5 份）。\n- **停写铁律**：四文件落盘并通过自检后停止；禁止为润色 channel-plan \u002F 补运营手册 \u002F 再搜图空转至 max_turns。\n\n### 选风铁律\n\n1. 打分可含 stub；brief TOP3 必须标 `full` \u002F `stub`；冲突对勿并列推送。\n2. **自动主风格** = 得分最高的 **full**（仅 T1-1 \u002F T1-2）；stub 永不自动主写。\n3. 点名 stub：**软拒绝**——改用最近 full 仍交四文件，brief 首段说明。\n4. 点名 full 但总分＜30 或落入禁区维=0：**软切换**最高分 full，brief 说明（本批不硬中断）。\n5. 两种及以上风格同篇：**硬拒绝混搭**——不写伪混搭正文；brief 解释框架撕裂并建议拆两篇。\n6. 系列模式本批不做：brief 一句说明可拆多 turn。\n\n### brief 必含骨架（推荐模式）\n\n```\n选题分析：领域|性质|证据|情绪|深度|时效\nTOP3：1..3（风格名 + full\u002Fstub + 分\u002F60 + 2–3 句理由）\n选中主风格：… + 叠加公式 F?\n结构说明：钩子→…→收尾（各 1 句设计意图）\n变体方向：①… ②…\n（若软切换：首段说明点名风格未入库\u002F低配原因）\n```\n\n### T1-1 \u002F T1-2 迷你红线\n\n**T1-1**：短段 1–3 句；≥5 出格类比；硬数据≤2；必算一笔账；情绪「哈哈哈说得对」；**禁**「这意味着什么」\u002F行动清单\u002F框架命名\u002F报告腔。  \n**T1-2**：第三人称；**蓝字=Markdown 加粗**（每 400–600 字）；禁感叹号\u002F模糊信源\u002F结尾道德升华；公开信息拼图。  \n虚构数据标【示例数据】。用户提供数据必须作核心论据。\n\u003C!-- NOVA-EXEC-END -->\n\n# 爆款长文生成（风格路由 · 参数级）\n\n为正确的选题匹配可写气质，在合适渠道交付母稿。当前 **full** 仅 T1-1、T1-2；其余见 `references\u002Fstub-styles.md`。  \n索引见 `references\u002Fstyle-registry.md`（可选读）。\n\n## 适用 \u002F 不适用\n\n**适用**：公众号\u002F垂类长文、热点解构、调查讽刺向商业稿；需风格路由 + 渠道建议。  \n**不适用**：短视频口播主交付；只要选题清单（内容飞轮）；深度蒸馏写作 OS；未要求时的批量配图。\n\n## 工作流（推荐模式默认）\n\n1. 推断选题\u002F渠道\u002F字数（缺省：公众号 + 该风格标准字数）。\n2. 六维特征 + 打分（`routing-matrix.md` 刻度）。\n3. 写 `article-brief.md`（含 TOP3、结构说明、2 变体）；**不询问用户选风**。\n4. 按迷你红线生成 `article.md`；可选再读 1 份 `style-t1-*.md`；可叠 F1–F8。\n5. 抽 `quotes.md`；写短 `channel-plan.md`。\n6. 自检通过 → **停止**。\n\n### 硬拒绝混搭（示例口径）\n\n用户「半佛+刘润」：说明二者认知框架\u002F节奏\u002F情绪出口不同，混搭导致风格撕裂；建议各写一篇；本 turn 只交 brief（或单一风格正文）。\n\n## 全流程质检（强制）\n\n**通用**：风格唯一；公式模块可辨；数据来源\u002F【示例数据】；用户数据已用；移动端短段；值得转发；去 AI 套话。  \n**专项**：对照该风格红线；标题适配首选平台。  \n**交付**：四 basename 齐全且未膨胀为第七八个运营附件。\n\n## 绝对禁止\n\n- 一篇混搭多风格  \n- 禁区硬写却不说明软切换  \n- 编造数据不标【示例数据】  \n- 忽略用户原始资料  \n- 跳过自检直接收口  \n- 推荐生态位冲突风格对并列第一  \n- stub 自动主写，或点名 stub 后硬中断不交稿  \n- 未验证宣称「已发布」  \n- 连环读盘 \u002F channel-plan 运营长文空转  \n\n## 参考（按需最多 +1 细则）\n\n- `references\u002Fstyle-registry.md`（索引）\n- `references\u002Fstyle-t1-1.md` \u002F `style-t1-2.md`\n- `references\u002Fstub-styles.md`\n- `references\u002Frouting-matrix.md`\n- `references\u002Fchannel-matrix.md`\n- `references\u002Ftopic-formulas.md`\n","\u003C!-- NOVA-EXEC-BEGIN -->\n## Nova Ai-Studio 集成（优先于下文）\n\n- 所有成果写入 **`\u003Ctask-artifact-dir>\u002F`**；勿写工作区根、`output\u002F` 或其它 `artifacts\u002Ftask-*`。\n- **禁止**首 turn `ask_user_question`；**禁止**正文末「请选择一个风格」——推荐模式直接开写最高分 full。\n- **禁止** Task\u002Fsubagent；禁止以 `skills\u002Fvendor\u002Fviral-article-generator\u002F` 为风格权威。\n- **须交付四文件（同 turn 写完即停，basename 固定）**：\n  1. `article-brief.md` — 六维 + TOP3（标 full\u002Fstub）+ 主风格\u002F理由 + 结构说明要点 + **2 条变体方向**（各 1 句）\n  2. `article.md` — 3–5 标题候选 + 正文（主槽；可选副写「爆款母稿.md」）\n  3. `quotes.md` — 可截图金句（5–12 条）\n  4. `channel-plan.md` — 按 `channel-matrix` 短模板，**≤800 字**\n- `data-sources.md` 由引擎同步时勿抢权威槽；未要求配图时禁 `generate_image`。\n- 研究：`web_search` 1–3 次；选定风格后最多再读 **1** 份 `style-t1-1.md` 或 `style-t1-2.md`（勿连环读 3–5 份）。\n- **停写铁律**：四文件落盘并通过自检后停止；禁止为润色 channel-plan \u002F 补运营手册 \u002F 再搜图空转至 max_turns。\n\n### 选风铁律\n\n1. 打分可含 stub；brief TOP3 必须标 `full` \u002F `stub`；冲突对勿并列推送。\n2. **自动主风格** = 得分最高的 **full**（仅 T1-1 \u002F T1-2）；stub 永不自动主写。\n3. 点名 stub：**软拒绝**——改用最近 full 仍交四文件，brief 首段说明。\n4. 点名 full 但总分＜30 或落入禁区维=0：**软切换**最高分 full，brief 说明（本批不硬中断）。\n5. 两种及以上风格同篇：**硬拒绝混搭**——不写伪混搭正文；brief 解释框架撕裂并建议拆两篇。\n6. 系列模式本批不做：brief 一句说明可拆多 turn。\n\n### brief 必含骨架（推荐模式）\n\n```\n选题分析：领域|性质|证据|情绪|深度|时效\nTOP3：1..3（风格名 + full\u002Fstub + 分\u002F60 + 2–3 句理由）\n选中主风格：… + 叠加公式 F?\n结构说明：钩子→…→收尾（各 1 句设计意图）\n变体方向：①… ②…\n（若软切换：首段说明点名风格未入库\u002F低配原因）\n```\n\n### T1-1 \u002F T1-2 迷你红线\n\n**T1-1**：短段 1–3 句；≥5 出格类比；硬数据≤2；必算一笔账；情绪「哈哈哈说得对」；**禁**「这意味着什么」\u002F行动清单\u002F框架命名\u002F报告腔。  \n**T1-2**：第三人称；**蓝字=Markdown 加粗**（每 400–600 字）；禁感叹号\u002F模糊信源\u002F结尾道德升华；公开信息拼图。  \n虚构数据标【示例数据】。用户提供数据必须作核心论据。\n\u003C!-- NOVA-EXEC-END -->\n\n# 爆款长文生成（风格路由 · 参数级）\n\n为正确的选题匹配可写气质，在合适渠道交付母稿。当前 **full** 仅 T1-1、T1-2；其余见 `references\u002Fstub-styles.md`。  \n索引见 `references\u002Fstyle-registry.md`（可选读）。\n\n## 适用 \u002F 不适用\n\n**适用**：公众号\u002F垂类长文、热点解构、调查讽刺向商业稿；需风格路由 + 渠道建议。  \n**不适用**：短视频口播主交付；只要选题清单（内容飞轮）；深度蒸馏写作 OS；未要求时的批量配图。\n\n## 工作流（推荐模式默认）\n\n1. 推断选题\u002F渠道\u002F字数（缺省：公众号 + 该风格标准字数）。\n2. 六维特征 + 打分（`routing-matrix.md` 刻度）。\n3. 写 `article-brief.md`（含 TOP3、结构说明、2 变体）；**不询问用户选风**。\n4. 按迷你红线生成 `article.md`；可选再读 1 份 `style-t1-*.md`；可叠 F1–F8。\n5. 抽 `quotes.md`；写短 `channel-plan.md`。\n6. 自检通过 → **停止**。\n\n### 硬拒绝混搭（示例口径）\n\n用户「半佛+刘润」：说明二者认知框架\u002F节奏\u002F情绪出口不同，混搭导致风格撕裂；建议各写一篇；本 turn 只交 brief（或单一风格正文）。\n\n## 全流程质检（强制）\n\n**通用**：风格唯一；公式模块可辨；数据来源\u002F【示例数据】；用户数据已用；移动端短段；值得转发；去 AI 套话。  \n**专项**：对照该风格红线；标题适配首选平台。  \n**交付**：四 basename 齐全且未膨胀为第七八个运营附件。\n\n## 绝对禁止\n\n- 一篇混搭多风格  \n- 禁区硬写却不说明软切换  \n- 编造数据不标【示例数据】  \n- 忽略用户原始资料  \n- 跳过自检直接收口  \n- 推荐生态位冲突风格对并列第一  \n- stub 自动主写，或点名 stub 后硬中断不交稿  \n- 未验证宣称「已发布」  \n- 连环读盘 \u002F channel-plan 运营长文空转  \n\n## 参考（按需最多 +1 细则）\n\n- `references\u002Fstyle-registry.md`（索引）\n- `references\u002Fstyle-t1-1.md` \u002F `style-t1-2.md`\n- `references\u002Fstub-styles.md`\n- `references\u002Frouting-matrix.md`\n- `references\u002Fchannel-matrix.md`\n- `references\u002Ftopic-formulas.md`\n",{"name":5,"description":7},"main","4f23625805df8f10defe3b1e93812cdb04d07e27","skills\u002Fviral-article-generator",0,"https:\u002F\u002Fgithub.com\u002Frufeng0411\u002FNova-Ai-Studio","https:\u002F\u002Fwww.novapage.online\u002F","https:\u002F\u002Fgithub.com\u002Frufeng0411","2026-09-07 07:19:49",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add rufeng0411\u002FNova-Ai-Studio --skill viral-article-generator",{"tool":37,"command":38},"bunx","bunx skills add rufeng0411\u002FNova-Ai-Studio --skill viral-article-generator",{"tool":40,"command":41},"pnpm","pnpm dlx skills add rufeng0411\u002FNova-Ai-Studio --skill viral-article-generator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frufeng0411\u002FNova-Ai-Studio\u002Fblob\u002Fmain\u002Fskills\u002Fviral-article-generator\u002FSKILL.md",true,[45,51,55,59,63,67,71],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"references\u002Fchannel-matrix.md","REFERENCE","参考文档",2959,"https:\u002F\u002Fgithub.com\u002Frufeng0411\u002FNova-Ai-Studio\u002Fblob\u002Fmain\u002Fskills\u002Fviral-article-generator\u002Freferences\u002Fchannel-matrix.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Frouting-matrix.md",3176,"https:\u002F\u002Fgithub.com\u002Frufeng0411\u002FNova-Ai-Studio\u002Fblob\u002Fmain\u002Fskills\u002Fviral-article-generator\u002Freferences\u002Frouting-matrix.md",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fstub-styles.md",1840,"https:\u002F\u002Fgithub.com\u002Frufeng0411\u002FNova-Ai-Studio\u002Fblob\u002Fmain\u002Fskills\u002Fviral-article-generator\u002Freferences\u002Fstub-styles.md",{"path":60,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fstyle-registry.md",1087,"https:\u002F\u002Fgithub.com\u002Frufeng0411\u002FNova-Ai-Studio\u002Fblob\u002Fmain\u002Fskills\u002Fviral-article-generator\u002Freferences\u002Fstyle-registry.md",{"path":64,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Fstyle-t1-1.md",4398,"https:\u002F\u002Fgithub.com\u002Frufeng0411\u002FNova-Ai-Studio\u002Fblob\u002Fmain\u002Fskills\u002Fviral-article-generator\u002Freferences\u002Fstyle-t1-1.md",{"path":68,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fstyle-t1-2.md",3432,"https:\u002F\u002Fgithub.com\u002Frufeng0411\u002FNova-Ai-Studio\u002Fblob\u002Fmain\u002Fskills\u002Fviral-article-generator\u002Freferences\u002Fstyle-t1-2.md",{"path":72,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Ftopic-formulas.md",1688,"https:\u002F\u002Fgithub.com\u002Frufeng0411\u002FNova-Ai-Studio\u002Fblob\u002Fmain\u002Fskills\u002Fviral-article-generator\u002Freferences\u002Ftopic-formulas.md",[76,83,90,97,104,111],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M7E1Y07R2NYVGM2PJRBZRRHB","wireframe-mobile-flow","A lo-fi multi-screen MOBILE flow wireframe — three or four phone frames\nlaid out in a row on a board, showing a connected user flow (Onboarding →\nHome feed → Item detail → Confirm). Grey-box content inside each device,\ndashed connector arrows + numbered step labels between screens, and a\ncouple of annotation callouts. Reads like an app flow pinned to a\nwhiteboard before any pixels are committed. Use when the brief asks for\n\"mobile wireframe\", \"app flow\", \"user flow wireframe\", \"lo-fi mobile\",\n\"low fidelity\", \"线框图\", \"移动端线框\", or \"App 流程\".","https:\u002F\u002Fgithub.com\u002Frufeng0411\u002FNova-Ai-Studio\u002Fblob\u002Fmain\u002Ftmp\u002Fod-templates\u002Fwireframe-mobile-flow\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M7E1XTWE18MRVFRGEGY20YEG","web-prototype","General-purpose desktop web prototype. Single self-contained HTML file built\nby copying the seed `assets\u002Ftemplate.html` and pasting section layouts from\n`references\u002Flayouts.md`. Default for any landing \u002F marketing \u002F docs \u002F SaaS\npage when no more specific skill matches.","https:\u002F\u002Fgithub.com\u002Frufeng0411\u002FNova-Ai-Studio\u002Fblob\u002Fmain\u002Ftmp\u002Fod-templates\u002Fweb-prototype\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":18},"01M7E1X8WXJBC7AMQP0VZWQZZ4","waitlist-page","Minimal pre-launch landing with email capture, brand logo, and optional decorative layer.\nReads DESIGN.md for colors, typography, and layout rules.\nBest for: product launches, beta signups, early access programs, indie projects.","https:\u002F\u002Fgithub.com\u002Frufeng0411\u002FNova-Ai-Studio\u002Fblob\u002Fmain\u002Ftmp\u002Fod-templates\u002Fwaitlist-page\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":18},"01M7E1X4MG06QDPHHXQBS4THHB","team-okrs","OKR tracker page — quarter banner, three objectives with their key\nresults as progress bars, owner avatars, status pills, and a \"this\nquarter at a glance\" sidebar. Use when the brief mentions \"OKRs\",\n\"key results\", \"objectives\", or \"目标\".","https:\u002F\u002Fgithub.com\u002Frufeng0411\u002FNova-Ai-Studio\u002Fblob\u002Fmain\u002Ftmp\u002Fod-templates\u002Fteam-okrs\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":18},"01M7E1X1D63032XDA1R5YGCVXX","pricing-page","A standalone pricing page — header, plan tiers, feature comparison table,\nand an FAQ. Use when the brief asks for \"pricing\", \"plans\",\n\"subscription tiers\", or a \"compare plans\" page.","https:\u002F\u002Fgithub.com\u002Frufeng0411\u002FNova-Ai-Studio\u002Fblob\u002Fmain\u002Ftmp\u002Fod-templates\u002Fpricing-page\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":18},"01M7E1WWV4V6C5WZ9E2CCFYFSB","pm-spec","Product spec \u002F PRD as a single page — problem, success metrics, scope,\nuser stories, design notes, rollout plan, open questions. Use when the\nbrief mentions \"PRD\", \"spec\", \"product spec\", \"feature brief\", or \"需求文档\".","https:\u002F\u002Fgithub.com\u002Frufeng0411\u002FNova-Ai-Studio\u002Fblob\u002Fmain\u002Ftmp\u002Fod-templates\u002Fpm-spec\u002FSKILL.md",[],[]]