[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78ZDZXCX9PH5BCWKBFBYFY1":3,"skill-same:01M78ZDZXCX9PH5BCWKBFBYFY1":106},{"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":40,"commitSha":41,"skillDirectory":42,"forksCount":14,"repositoryHtmlUrl":43,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":45,"install":46,"resources":59},"01M78ZDZXCX9PH5BCWKBFBYFY1","crossframe-suite",null,"Use when the user explicitly invokes CrossFrame Suite for Chinese structural diagnosis workflows across relationships, organizations, public issues, philosophy, research, or essay output.","Elogic360\u002Fsoftware-factory","Elogic360","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F156535519?v=4","01M74NH3F0RB13PWB7JZDE2V80","elogic360","01M74NH3FPC65082MDZVMFHDM3",0,"MIT","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fcrossframe-suite\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: crossframe-suite\ndescription: \"Use when the user explicitly invokes CrossFrame Suite for Chinese structural diagnosis workflows across relationships, organizations, public issues, philosophy, research, or essay output.\"\ncategory: workflow\nrisk: safe\nsource: community\nsource_repo: xi-kari\u002Fcrossframe-skill\nsource_type: community\ndate_added: 2026-06-16\nauthor: xi-kari\nlicense: MIT\nlicense_source: https:\u002F\u002Fgithub.com\u002Fxi-kari\u002Fcrossframe-skill\u002Fblob\u002Fmain\u002FLICENSE\ntools:\n  - \"Agent Skills\"\n  - Codex\n  - Claude\ntags:\n  - crossframe\n  - chinese\n  - workflow\n  - multi-skill\n  - structural-diagnosis\n---\n# CrossFrame Suite\n\n\n## When to Use This Skill\n\n- Use only when the user explicitly names CrossFrame Suite, `crossframe-suite`, `\u002Fcrossframe-suite`, or `$crossframe-suite`.\n- Use as the umbrella router when a CrossFrame task may need multiple sibling skills, such as diagnosis plus public analysis, essay output, and review.\n- Do not load every sibling skill by default; follow the routed workflow and progressive-reading rules in the original body below.\n\n## Packaged Source Note\n\nThis AAS-ready copy preserves the original CrossFrame skill body below. Chinese remains the canonical semantic layer; English metadata is only for discovery, installation, and repository review.\n\n## Limitations\n\n- The skill body is intentionally Chinese-canonical; English metadata is for discovery and does not replace the original Chinese terms.\n- Use only after explicit CrossFrame invocation or `crossframe-suite` routing; do not apply it as a generic default reasoning layer.\n- It structures analysis, drafting, and review, but does not replace source verification, domain expertise, or legal, medical, or financial judgment.\n\n`crossframe-suite` 是总调度 skill，不替代任何专项 skill。它只做三件事：\n\n1. 判断用户任务属于哪条工作流。\n2. 安排连续读取顺序。\n3. 输出一个简短的调度提纲，然后进入相应 skill。\n\n它不复制 `crossframe`、`crossframe-essay` 或其它平行 skill 的正文。中文为权威语义；英文只作 skill id、文件名和对外传播名。\n\n当任务触发 CrossFrame 主体时，suite 还要把 `..\u002Fcrossframe\u002Freferences\u002Fruntime-read-policy.md` 与 `..\u002Fcrossframe\u002Freferences\u002Fcontinuity-closure-map.md` 纳入调度判断：本次是否需要按 v5.0 原文连续板块联读，而不是只读单个概念卡。需要包说明或源锚点时，再由下游定向读取 `continuity-bundles.md` 或具体包文件。v3.0 与 v2.0 文件只作为历史基线；默认以 v5.0 源结构为准。\n\nsuite 入口的交互选择只确认两项：输出模式与角色。文章类型不在 suite 开头选择；若最终进入 `crossframe-essay` 且文章层未关闭，先完成问题拆解与结构洞察底稿，再由 `crossframe-essay\u002Ftemplates\u002Farticle-type-selection-dialog.md` 在正文生成前单独确认。\n\n## 显式调用后的总入口\n\n只有用户显式调用 `crossframe-suite`、`$crossframe-suite`、`\u002Fcrossframe-suite` 或明确要求使用 CrossFrame Suite 时，才从本 skill 进入。进入之后，优先由本 skill 调度；只有任务非常单一且用户点名了专项 skill 时，才直接使用对应专项 skill。\n\n当用户通过本 skill 作为总入口提出任何 CrossFrame 内容任务时，默认最终都生成**5.0 混合长文**，输出档位为 `full-visible-v5-longform`：完整可见底稿 + 完整长文正文。专项产物可以先生成，但最后默认进入文章层。\n\n```text\ncrossframe -> [needed sibling skills] -> crossframe-essay(full-visible-v5-longform) -> crossframe-review\n```\n\n这条默认不是为了把所有回答写长，而是因为文章更适合把结构判断、专项产物和 v5.0 保真检查交给普通读者：先完成必要的诊断\u002F评审\u002F案例\u002F教学\u002F辩论\u002F备忘录，再形成底稿，再成文，最后过质量闸。\n\n完整交互顺序固定为：`\u002Fcrossframe-suite -> 模式\u002F角色选择器(4+6) -> suite 路由与专项拆解 -> 结构洞察底稿 -> 文章类型选择器 -> 写作技法读取 -> 文章正文 -> 质量闸收束`。文章类型选择器必须发生在结构洞察底稿之后、文章正文之前。\n\n这条默认不直接把固定声口传给 `crossframe-essay`。声口由 `references\u002Foutput-mode-selector.md` 中的角色、输出模式与 `topic_sensitivity` 共同决定：学术专家\u002F批判反思者默认中性分析体，大众传播\u002F未来探索者可启用编辑底色；用户显式要求“亲切\u002F编辑口吻\u002F答复体”时覆盖。中性分析体不是冷淡体，`vulnerable` 主题仍要先接住人。\n\n`full-visible-v5-longform` 的意思是：v5.0 连续联读包、源结构保真、概念风险和反向条件要在底稿中可见；但这些后台检查不能吞掉正文。正文仍必须写成完整文章，有标题、铺陈、概念上升、现实回落、边界和余味。\n\n`crossframe-review` 是质量闸，不是默认成文链路的最终写作者。只要文章层未关闭，最终可见交付必须仍然包含 `# 结构洞察底稿` 和 `# 文章正文`；质量闸通过时只追加极短结论或内部通过，不得只输出评审报告。只有用户明确要求“只要评审\u002F完整评审报告\u002F不要文章”，或质量闸发现硬失败且必须阻断发布时，才允许把评审报告作为主输出。\n\n只有在用户明确说“只要\u002F不要文章\u002F不要成文\u002F短答\u002F三句话\u002F表格\u002F清单\u002F原始评审\u002F原始案例库\u002F原始备忘录\u002F纯诊断\u002F仅行动方案”时，才关闭默认文章层。此时应保留用户指定的交付物。\n\n## 何时使用\n\n当任务不是单一诊断，而可能需要多个 CrossFrame skill 连续协作时，优先使用本 skill：\n\n- 用户希望使用 CrossFrame，但没有指定具体子 skill。\n- 用户只说“分析一下\u002F怎么看\u002F讲讲\u002F写一下”，且更像想看一段可读输出。\n- 写文章、评论、思想文章、公共评论、组织复盘文章。\n- 答读者问、编辑回信、咨询式回应，但问题背后有结构诊断。\n- 把材料整理成案例，再写分析或沉淀概念。\n- 读书、理论、文章研究笔记，需要比较与 CrossFrame 的关联和不同。\n- 命题辩论后需要成文、给结论或写反驳。\n- 先生成输出，再评审它是否真的推理。\n- 用户说“这些 skill 应该一起用”“连续触发”“总规则”“总入口”“怎么组合调用”。\n\n若任务非常单一，直接使用对应专项 skill，不要绕行：\n\n- 只要结构诊断：`..\u002Fcrossframe\u002FSKILL.md`\n- 只要文章：`..\u002Fcrossframe-essay\u002FSKILL.md`\n- 只要评审：`..\u002Fcrossframe-review\u002FSKILL.md`\n- 只要短答复：`..\u002Fcrossframe-dialogue\u002FSKILL.md`\n- 只要案例库：`..\u002Fcrossframe-casebook\u002FSKILL.md`\n- 只要公共议题证据边界：`..\u002Fcrossframe-public\u002FSKILL.md`\n- 只要组织修复备忘录：`..\u002Fcrossframe-org\u002FSKILL.md`\n- 只要概念教学：`..\u002Fcrossframe-teach\u002FSKILL.md`\n- 只要命题论证：`..\u002Fcrossframe-debate\u002FSKILL.md`\n- 只要读书研究笔记：`..\u002Fcrossframe-notebook\u002FSKILL.md`\n\n## 必须读取\n\n每次触发后读取：\n\n1. `references\u002Foutput-mode-selector.md`\n2. `references\u002Fworkflow-routing-map.md`\n3. `protocols\u002Fsuite-dispatch-protocol.md`\n4. `templates\u002Fsuite-reasoning-outline.md`\n\n然后按路由读取对应 sibling skill。基础结构判断通常先读 `..\u002Fcrossframe\u002FSKILL.md` 与 `..\u002Fcrossframe\u002Freferences\u002Fread-routing-map.md`。\n\n## 调度原则\n\n- 基础先行：多数复杂任务先由 `crossframe` 建立事实边界、尺度窗口、机制候选和判断档位。\n- 场景追加：只读取本次必要的专项 skill，不把全部 skill 一起触发。\n- 成文后置：写文章前先有结构洞察底稿；公共、组织、辩论、读书等专项判断先完成，再进入 `crossframe-essay`。\n- 默认成文：suite 被触发时，最终输出默认走 `crossframe-essay`，输出档位固定为 `full-visible-v5-longform`；专项产物先做，文章后置。\n- 模式\u002F角色先行：suite 开头只确认输出模式与角色；没有触发词时展示 `templates\u002Fmode-selection-dialog.md` 并等待回复，不直接开始。\n- 文章类型后置：文章类型只在进入 `crossframe-essay` 后、结构洞察底稿生成后确认；它决定文章表达形态和写作技法读取，不改变 suite 的主路由。\n- 胶囊归属：suite 只传入 `selection_state`、`workflow_state`、`voice_mode` 和文章层开关；不得读取 v5 源索引、不得展开连读包、不得生成 `v5-read-state-capsule`。胶囊由 `crossframe` 核心层在命中 source modules、入口包和必须同读闭包后生成。\n- 声口由角色决定：suite 默认成文时，根据 `output-mode-selector.md` 将 `voice_mode` 和 `topic_sensitivity` 传给 `crossframe-essay`。用户显式要求“亲切\u002F编辑口吻\u002F答复体”时覆盖。\n- 长文契约：任何从 suite 进入、且未显式关闭文章层的 CrossFrame 内容任务，默认不是短答，不得用项目符号诊断、摘要式回答或“如果只要一句话”替代完整正文。\n- 成文边界：默认对所有 CrossFrame 内容任务成文；只有用户用“只要\u002F不要文章\u002F短答\u002F表格\u002F清单\u002F纯诊断\u002F仅行动方案”等词明确关闭时，才关闭文章层。\n- 源连续性：高责任、公共制度、亲密关系、长期演化、深度分析、框架治理、AI 现实验证、弱信号\u002F不透明、无法退出和文章输出，要在调度中列出本次触发的 v5.0 连续联读包；不要只列概念卡。\n- 源锚点完整性：凡进入文章层、高责任、公共制度、AI\u002F过程性产物、生命周期、无法退出主体或框架治理时，调度提纲要要求下游复用 `v5-read-state-capsule` 并执行源锚点完整性检查。\n- 评审收束：重要输出默认最后用 `crossframe-review` 做质量闸；质量闸不得接管最终输出或吞掉底稿\u002F正文。轻量短答复可只做内部自检。\n- 查源克制：公共议题、真实机构、平台、政策、人物、公司和最新事实要查源；私人关系、哲学泛论、用户自给材料默认不查源。\n- 人话优先：最终输出先给普通人能读懂的结果，术语只做必要映射。\n\n## 默认连续链路\n\n```text\n结构诊断：\ncrossframe -> crossframe-essay(full-visible-v5-longform) -> crossframe-review\n\n开放式可读分析：\ncrossframe -> crossframe-essay(full-visible-v5-longform) -> crossframe-review\n\n普通洞察文章：\ncrossframe -> crossframe-essay(full-visible-v5-longform) -> crossframe-review\n\n公共评论文章：\ncrossframe -> crossframe-public -> crossframe-essay(full-visible-v5-longform) -> crossframe-review\n\n组织复盘\u002F修复文章：\ncrossframe -> crossframe-org -> crossframe-essay(full-visible-v5-longform) -> crossframe-review\n\n答读者问\u002F编辑回信：\ncrossframe -> crossframe-dialogue -> crossframe-essay(full-visible-v5-longform) -> crossframe-review\n\n案例沉淀：\ncrossframe -> crossframe-casebook -> crossframe-essay(full-visible-v5-longform) -> crossframe-review\n\n概念教学：\ncrossframe -> crossframe-teach -> crossframe-essay(full-visible-v5-longform) -> crossframe-review\n\n命题辩论：\ncrossframe -> crossframe-debate -> crossframe-essay(full-visible-v5-longform) -> crossframe-review\n\n辩论后成文：\ncrossframe -> crossframe-debate -> crossframe-essay -> crossframe-review\n\n读书\u002F理论研究：\ncrossframe -> crossframe-notebook -> crossframe-essay(full-visible-v5-longform) -> crossframe-review\n\n读书后成文：\ncrossframe -> crossframe-notebook -> crossframe-essay -> crossframe-review\n```\n\n进入 `crossframe-essay` 后先生成结构洞察底稿，再执行文章类型选择规则：用户已显式指定文章类型时在底稿中记录并直接采用；用户未指定且文章层开启时，基于底稿展示 `..\u002Fcrossframe-essay\u002Ftemplates\u002Farticle-type-selection-dialog.md`；用户回复“默认\u002F自动\u002F都行”时采用底稿推荐项；用户明确关闭文章层时不展示。\n\n`crossframe-review-lite` 表示不必输出完整评审报告，但必须检查：是否跳过事实边界、是否人格审判、是否概念堆砌、是否越过证据档位。\n\n## 输出方式\n\n除非用户只问“该用哪个 skill”，否则最终输出先给一个短调度提纲：\n\n```text\n调度提纲\n- 任务类型：\n- 输出模式与角色：\n- 工作流：\n- 必读 skill：\n- 按需读取：\n- 连续联读包：\n- 主题敏感度：\n- 正文声口：\n- 文章类型：\n- 输出档位：\n- 不读取：\n- 质量闸：\n```\n\n然后进入对应 skill 的正常输出。不要把调度提纲写得比任务本身还长。\n\n## 禁止\n\n- 禁止为了显得完整而触发全部 skill。\n- 禁止跳过 `crossframe` 的事实边界和判断档位直接写文章。\n- 禁止公共议题不查源却做强判断。\n- 禁止把 `crossframe-review` 当作形式收尾；它必须能否决坏输出。\n- 禁止在 suite 默认成文链路中只输出质量闸、评审结论或修复建议，而隐藏 `结构洞察底稿` 和 `文章正文`。\n- 禁止让调度规则取代专项 skill 的协议。\n","# CrossFrame Suite\n\n\n## When to Use This Skill\n\n- Use only when the user explicitly names CrossFrame Suite, `crossframe-suite`, `\u002Fcrossframe-suite`, or `$crossframe-suite`.\n- Use as the umbrella router when a CrossFrame task may need multiple sibling skills, such as diagnosis plus public analysis, essay output, and review.\n- Do not load every sibling skill by default; follow the routed workflow and progressive-reading rules in the original body below.\n\n## Packaged Source Note\n\nThis AAS-ready copy preserves the original CrossFrame skill body below. Chinese remains the canonical semantic layer; English metadata is only for discovery, installation, and repository review.\n\n## Limitations\n\n- The skill body is intentionally Chinese-canonical; English metadata is for discovery and does not replace the original Chinese terms.\n- Use only after explicit CrossFrame invocation or `crossframe-suite` routing; do not apply it as a generic default reasoning layer.\n- It structures analysis, drafting, and review, but does not replace source verification, domain expertise, or legal, medical, or financial judgment.\n\n`crossframe-suite` 是总调度 skill，不替代任何专项 skill。它只做三件事：\n\n1. 判断用户任务属于哪条工作流。\n2. 安排连续读取顺序。\n3. 输出一个简短的调度提纲，然后进入相应 skill。\n\n它不复制 `crossframe`、`crossframe-essay` 或其它平行 skill 的正文。中文为权威语义；英文只作 skill id、文件名和对外传播名。\n\n当任务触发 CrossFrame 主体时，suite 还要把 `..\u002Fcrossframe\u002Freferences\u002Fruntime-read-policy.md` 与 `..\u002Fcrossframe\u002Freferences\u002Fcontinuity-closure-map.md` 纳入调度判断：本次是否需要按 v5.0 原文连续板块联读，而不是只读单个概念卡。需要包说明或源锚点时，再由下游定向读取 `continuity-bundles.md` 或具体包文件。v3.0 与 v2.0 文件只作为历史基线；默认以 v5.0 源结构为准。\n\nsuite 入口的交互选择只确认两项：输出模式与角色。文章类型不在 suite 开头选择；若最终进入 `crossframe-essay` 且文章层未关闭，先完成问题拆解与结构洞察底稿，再由 `crossframe-essay\u002Ftemplates\u002Farticle-type-selection-dialog.md` 在正文生成前单独确认。\n\n## 显式调用后的总入口\n\n只有用户显式调用 `crossframe-suite`、`$crossframe-suite`、`\u002Fcrossframe-suite` 或明确要求使用 CrossFrame Suite 时，才从本 skill 进入。进入之后，优先由本 skill 调度；只有任务非常单一且用户点名了专项 skill 时，才直接使用对应专项 skill。\n\n当用户通过本 skill 作为总入口提出任何 CrossFrame 内容任务时，默认最终都生成**5.0 混合长文**，输出档位为 `full-visible-v5-longform`：完整可见底稿 + 完整长文正文。专项产物可以先生成，但最后默认进入文章层。\n\n```text\ncrossframe -> [needed sibling skills] -> crossframe-essay(full-visible-v5-longform) -> crossframe-review\n```\n\n这条默认不是为了把所有回答写长，而是因为文章更适合把结构判断、专项产物和 v5.0 保真检查交给普通读者：先完成必要的诊断\u002F评审\u002F案例\u002F教学\u002F辩论\u002F备忘录，再形成底稿，再成文，最后过质量闸。\n\n完整交互顺序固定为：`\u002Fcrossframe-suite -> 模式\u002F角色选择器(4+6) -> suite 路由与专项拆解 -> 结构洞察底稿 -> 文章类型选择器 -> 写作技法读取 -> 文章正文 -> 质量闸收束`。文章类型选择器必须发生在结构洞察底稿之后、文章正文之前。\n\n这条默认不直接把固定声口传给 `crossframe-essay`。声口由 `references\u002Foutput-mode-selector.md` 中的角色、输出模式与 `topic_sensitivity` 共同决定：学术专家\u002F批判反思者默认中性分析体，大众传播\u002F未来探索者可启用编辑底色；用户显式要求“亲切\u002F编辑口吻\u002F答复体”时覆盖。中性分析体不是冷淡体，`vulnerable` 主题仍要先接住人。\n\n`full-visible-v5-longform` 的意思是：v5.0 连续联读包、源结构保真、概念风险和反向条件要在底稿中可见；但这些后台检查不能吞掉正文。正文仍必须写成完整文章，有标题、铺陈、概念上升、现实回落、边界和余味。\n\n`crossframe-review` 是质量闸，不是默认成文链路的最终写作者。只要文章层未关闭，最终可见交付必须仍然包含 `# 结构洞察底稿` 和 `# 文章正文`；质量闸通过时只追加极短结论或内部通过，不得只输出评审报告。只有用户明确要求“只要评审\u002F完整评审报告\u002F不要文章”，或质量闸发现硬失败且必须阻断发布时，才允许把评审报告作为主输出。\n\n只有在用户明确说“只要\u002F不要文章\u002F不要成文\u002F短答\u002F三句话\u002F表格\u002F清单\u002F原始评审\u002F原始案例库\u002F原始备忘录\u002F纯诊断\u002F仅行动方案”时，才关闭默认文章层。此时应保留用户指定的交付物。\n\n## 何时使用\n\n当任务不是单一诊断，而可能需要多个 CrossFrame skill 连续协作时，优先使用本 skill：\n\n- 用户希望使用 CrossFrame，但没有指定具体子 skill。\n- 用户只说“分析一下\u002F怎么看\u002F讲讲\u002F写一下”，且更像想看一段可读输出。\n- 写文章、评论、思想文章、公共评论、组织复盘文章。\n- 答读者问、编辑回信、咨询式回应，但问题背后有结构诊断。\n- 把材料整理成案例，再写分析或沉淀概念。\n- 读书、理论、文章研究笔记，需要比较与 CrossFrame 的关联和不同。\n- 命题辩论后需要成文、给结论或写反驳。\n- 先生成输出，再评审它是否真的推理。\n- 用户说“这些 skill 应该一起用”“连续触发”“总规则”“总入口”“怎么组合调用”。\n\n若任务非常单一，直接使用对应专项 skill，不要绕行：\n\n- 只要结构诊断：`..\u002Fcrossframe\u002FSKILL.md`\n- 只要文章：`..\u002Fcrossframe-essay\u002FSKILL.md`\n- 只要评审：`..\u002Fcrossframe-review\u002FSKILL.md`\n- 只要短答复：`..\u002Fcrossframe-dialogue\u002FSKILL.md`\n- 只要案例库：`..\u002Fcrossframe-casebook\u002FSKILL.md`\n- 只要公共议题证据边界：`..\u002Fcrossframe-public\u002FSKILL.md`\n- 只要组织修复备忘录：`..\u002Fcrossframe-org\u002FSKILL.md`\n- 只要概念教学：`..\u002Fcrossframe-teach\u002FSKILL.md`\n- 只要命题论证：`..\u002Fcrossframe-debate\u002FSKILL.md`\n- 只要读书研究笔记：`..\u002Fcrossframe-notebook\u002FSKILL.md`\n\n## 必须读取\n\n每次触发后读取：\n\n1. `references\u002Foutput-mode-selector.md`\n2. `references\u002Fworkflow-routing-map.md`\n3. `protocols\u002Fsuite-dispatch-protocol.md`\n4. `templates\u002Fsuite-reasoning-outline.md`\n\n然后按路由读取对应 sibling skill。基础结构判断通常先读 `..\u002Fcrossframe\u002FSKILL.md` 与 `..\u002Fcrossframe\u002Freferences\u002Fread-routing-map.md`。\n\n## 调度原则\n\n- 基础先行：多数复杂任务先由 `crossframe` 建立事实边界、尺度窗口、机制候选和判断档位。\n- 场景追加：只读取本次必要的专项 skill，不把全部 skill 一起触发。\n- 成文后置：写文章前先有结构洞察底稿；公共、组织、辩论、读书等专项判断先完成，再进入 `crossframe-essay`。\n- 默认成文：suite 被触发时，最终输出默认走 `crossframe-essay`，输出档位固定为 `full-visible-v5-longform`；专项产物先做，文章后置。\n- 模式\u002F角色先行：suite 开头只确认输出模式与角色；没有触发词时展示 `templates\u002Fmode-selection-dialog.md` 并等待回复，不直接开始。\n- 文章类型后置：文章类型只在进入 `crossframe-essay` 后、结构洞察底稿生成后确认；它决定文章表达形态和写作技法读取，不改变 suite 的主路由。\n- 胶囊归属：suite 只传入 `selection_state`、`workflow_state`、`voice_mode` 和文章层开关；不得读取 v5 源索引、不得展开连读包、不得生成 `v5-read-state-capsule`。胶囊由 `crossframe` 核心层在命中 source modules、入口包和必须同读闭包后生成。\n- 声口由角色决定：suite 默认成文时，根据 `output-mode-selector.md` 将 `voice_mode` 和 `topic_sensitivity` 传给 `crossframe-essay`。用户显式要求“亲切\u002F编辑口吻\u002F答复体”时覆盖。\n- 长文契约：任何从 suite 进入、且未显式关闭文章层的 CrossFrame 内容任务，默认不是短答，不得用项目符号诊断、摘要式回答或“如果只要一句话”替代完整正文。\n- 成文边界：默认对所有 CrossFrame 内容任务成文；只有用户用“只要\u002F不要文章\u002F短答\u002F表格\u002F清单\u002F纯诊断\u002F仅行动方案”等词明确关闭时，才关闭文章层。\n- 源连续性：高责任、公共制度、亲密关系、长期演化、深度分析、框架治理、AI 现实验证、弱信号\u002F不透明、无法退出和文章输出，要在调度中列出本次触发的 v5.0 连续联读包；不要只列概念卡。\n- 源锚点完整性：凡进入文章层、高责任、公共制度、AI\u002F过程性产物、生命周期、无法退出主体或框架治理时，调度提纲要要求下游复用 `v5-read-state-capsule` 并执行源锚点完整性检查。\n- 评审收束：重要输出默认最后用 `crossframe-review` 做质量闸；质量闸不得接管最终输出或吞掉底稿\u002F正文。轻量短答复可只做内部自检。\n- 查源克制：公共议题、真实机构、平台、政策、人物、公司和最新事实要查源；私人关系、哲学泛论、用户自给材料默认不查源。\n- 人话优先：最终输出先给普通人能读懂的结果，术语只做必要映射。\n\n## 默认连续链路\n\n```text\n结构诊断：\ncrossframe -> crossframe-essay(full-visible-v5-longform) -> crossframe-review\n\n开放式可读分析：\ncrossframe -> crossframe-essay(full-visible-v5-longform) -> crossframe-review\n\n普通洞察文章：\ncrossframe -> crossframe-essay(full-visible-v5-longform) -> crossframe-review\n\n公共评论文章：\ncrossframe -> crossframe-public -> crossframe-essay(full-visible-v5-longform) -> crossframe-review\n\n组织复盘\u002F修复文章：\ncrossframe -> crossframe-org -> crossframe-essay(full-visible-v5-longform) -> crossframe-review\n\n答读者问\u002F编辑回信：\ncrossframe -> crossframe-dialogue -> crossframe-essay(full-visible-v5-longform) -> crossframe-review\n\n案例沉淀：\ncrossframe -> crossframe-casebook -> crossframe-essay(full-visible-v5-longform) -> crossframe-review\n\n概念教学：\ncrossframe -> crossframe-teach -> crossframe-essay(full-visible-v5-longform) -> crossframe-review\n\n命题辩论：\ncrossframe -> crossframe-debate -> crossframe-essay(full-visible-v5-longform) -> crossframe-review\n\n辩论后成文：\ncrossframe -> crossframe-debate -> crossframe-essay -> crossframe-review\n\n读书\u002F理论研究：\ncrossframe -> crossframe-notebook -> crossframe-essay(full-visible-v5-longform) -> crossframe-review\n\n读书后成文：\ncrossframe -> crossframe-notebook -> crossframe-essay -> crossframe-review\n```\n\n进入 `crossframe-essay` 后先生成结构洞察底稿，再执行文章类型选择规则：用户已显式指定文章类型时在底稿中记录并直接采用；用户未指定且文章层开启时，基于底稿展示 `..\u002Fcrossframe-essay\u002Ftemplates\u002Farticle-type-selection-dialog.md`；用户回复“默认\u002F自动\u002F都行”时采用底稿推荐项；用户明确关闭文章层时不展示。\n\n`crossframe-review-lite` 表示不必输出完整评审报告，但必须检查：是否跳过事实边界、是否人格审判、是否概念堆砌、是否越过证据档位。\n\n## 输出方式\n\n除非用户只问“该用哪个 skill”，否则最终输出先给一个短调度提纲：\n\n```text\n调度提纲\n- 任务类型：\n- 输出模式与角色：\n- 工作流：\n- 必读 skill：\n- 按需读取：\n- 连续联读包：\n- 主题敏感度：\n- 正文声口：\n- 文章类型：\n- 输出档位：\n- 不读取：\n- 质量闸：\n```\n\n然后进入对应 skill 的正常输出。不要把调度提纲写得比任务本身还长。\n\n## 禁止\n\n- 禁止为了显得完整而触发全部 skill。\n- 禁止跳过 `crossframe` 的事实边界和判断档位直接写文章。\n- 禁止公共议题不查源却做强判断。\n- 禁止把 `crossframe-review` 当作形式收尾；它必须能否决坏输出。\n- 禁止在 suite 默认成文链路中只输出质量闸、评审结论或修复建议，而隐藏 `结构洞察底稿` 和 `文章正文`。\n- 禁止让调度规则取代专项 skill 的协议。\n",{"name":5,"risk":24,"tags":25,"tools":31,"author":35,"source":36,"license":15,"category":28,"date_added":37,"description":7,"source_repo":38,"source_type":36,"license_source":39},"safe",[26,27,28,29,30],"crossframe","chinese","workflow","multi-skill","structural-diagnosis",[32,33,34],"Agent Skills","Codex","Claude","xi-kari","community",1781568000000,"xi-kari\u002Fcrossframe-skill","https:\u002F\u002Fgithub.com\u002Fxi-kari\u002Fcrossframe-skill\u002Fblob\u002Fmain\u002FLICENSE","main","c475fc64e94e803b50d14a791dfee8853fbb2c5c","integrations\u002Fantigravity-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fcrossframe-suite","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory","https:\u002F\u002Fgithub.com\u002FElogic360","2026-11-08 22:21:22",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add Elogic360\u002Fsoftware-factory --skill crossframe-suite",{"tool":52,"command":53},"bunx","bunx skills add Elogic360\u002Fsoftware-factory --skill crossframe-suite",{"tool":55,"command":56},"pnpm","pnpm dlx skills add Elogic360\u002Fsoftware-factory --skill crossframe-suite","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fcrossframe-suite\u002FSKILL.md",true,[60,66,70,74,78,82,86,90,94,98,102],{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"agents\u002Fopenai.yaml","REFERENCE","参考文档",656,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fcrossframe-suite\u002Fagents\u002Fopenai.yaml",{"path":67,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":68,"sourceHtmlUrl":69},"evals\u002Fcrossframe-suite-smoke-tests.md",6578,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fcrossframe-suite\u002Fevals\u002Fcrossframe-suite-smoke-tests.md",{"path":71,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":72,"sourceHtmlUrl":73},"examples\u002Fbad-overtrigger-case.md",844,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fcrossframe-suite\u002Fexamples\u002Fbad-overtrigger-case.md",{"path":75,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":76,"sourceHtmlUrl":77},"examples\u002Fessay-workflow-case.md",1057,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fcrossframe-suite\u002Fexamples\u002Fessay-workflow-case.md",{"path":79,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":80,"sourceHtmlUrl":81},"examples\u002Fpublic-comment-workflow-case.md",832,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fcrossframe-suite\u002Fexamples\u002Fpublic-comment-workflow-case.md",{"path":83,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":84,"sourceHtmlUrl":85},"examples\u002Freader-reply-workflow-case.md",1049,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fcrossframe-suite\u002Fexamples\u002Freader-reply-workflow-case.md",{"path":87,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":88,"sourceHtmlUrl":89},"protocols\u002Fsuite-dispatch-protocol.md",12154,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fcrossframe-suite\u002Fprotocols\u002Fsuite-dispatch-protocol.md",{"path":91,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Foutput-mode-selector.md",7170,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fcrossframe-suite\u002Freferences\u002Foutput-mode-selector.md",{"path":95,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Fworkflow-routing-map.md",11035,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fcrossframe-suite\u002Freferences\u002Fworkflow-routing-map.md",{"path":99,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":100,"sourceHtmlUrl":101},"templates\u002Fmode-selection-dialog.md",2762,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fcrossframe-suite\u002Ftemplates\u002Fmode-selection-dialog.md",{"path":103,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":104,"sourceHtmlUrl":105},"templates\u002Fsuite-reasoning-outline.md",3660,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fcrossframe-suite\u002Ftemplates\u002Fsuite-reasoning-outline.md",[107,115,122,129,136,143],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":111,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":19},"01M79G206MT3J6S0GY3C45P2KV","vss-summarize-video","Use to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for report generation or live RTSP captioning.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-summarize-video\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":111,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":19},"01M79G1WN63PGRE8CKD47WEBQ5","vss-setup-video-analytics-api","Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-setup-video-analytics-api\u002FSKILL.md",[],[],{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":111,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":19},"01M79G1S9F7VY3EF6H53PRP5AN","vss-setup-behavior-analytics","Use to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-setup-behavior-analytics\u002FSKILL.md",[],[],{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":111,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":19},"01M79G1N1S1Y27PFZPYMNK1MTQ","vss-search-archive","Use this skill to run top-level VSS fusion search on archived video, or to ingest video files \u002F RTSP streams for search. Do NOT use for ad-hoc visual Q&A (use vss-ask-video), live captioning (use vss-deploy-dense-captioning), or video summarization and reports (use vss-summarize-video).","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-search-archive\u002FSKILL.md",[],[],{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":111,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":19},"01M79G1H6WN0Q6C0VCAXCZX6B7","vss-query-analytics","Use this skill when reading video-analytics metrics, incidents, alerts, and sensor data via the VA-MCP server (port 9901). Not for live VLM or incident-range narrative reports.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-query-analytics\u002FSKILL.md",[],[],{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":111,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":149,"publishedAt":19},"01M79G1DYPNXQS7QHZ0AAF5FX5","vss-manage-video-io-storage","Use to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add\u002Fdelete sensors and streams). Not for VLM inference or search.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-manage-video-io-storage\u002FSKILL.md",[],[]]