[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M795P6VMYHN6F8RR7FSNEZRE":3,"skill-same:01M795P6VMYHN6F8RR7FSNEZRE":135},{"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":41,"commitSha":42,"skillDirectory":43,"forksCount":14,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":46,"install":47,"resources":60},"01M795P6VMYHN6F8RR7FSNEZRE","crossframe-public",null,"Use when CrossFrame Suite routes explicit Chinese analysis of public issues, platform governance, policy, institutional responsibility, appeals, or compliance evidence.","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\u002Fskills\u002Fcrossframe-public\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: crossframe-public\ndescription: \"Use when CrossFrame Suite routes explicit Chinese analysis of public issues, platform governance, policy, institutional responsibility, appeals, or compliance evidence.\"\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  - public-policy\n  - governance\n  - evidence\n---\n# CrossFrame Public\n\n\n\n## When to Use This Skill\n\n- Use when `crossframe-suite` routes an explicit CrossFrame task about public issues, platform governance, policy, institutional responsibility, public commitments, appeals, or compliance materials.\n- Use when source ledgers, evidence downgrades, public responsibility boundaries, and low-power subject protection matter.\n- Do not use independently unless the user explicitly names this sibling skill.\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> **本 skill 不独立触发。** 所有 CrossFrame 任务统一从 `crossframe-suite` 入口调度。用户无需直接调用本 skill；suite 根据路由规则在需要时自动加载。\n\n如果公共议题分析之后要写评论文章、组织建议、辩论论证或质量评审，先读取 `..\u002Fcrossframe-suite\u002FSKILL.md` 做总调度；本 skill 只负责公共事实、证据边界、程序与制度专项判断。\n\nCrossFrame Public 是 `crossframe` 的公共议题\u002F制度评论专项轻入口，不复制 canonical CrossFrame 全文。中文是权威语义；英文只作为 skill id、文件名或对外简介。\n\n## 必须读取\n\n每次触发后先读取：\n\n1. `..\u002Fcrossframe\u002FSKILL.md`\n2. `..\u002Fcrossframe\u002Freferences\u002Fread-routing-map.md`\n3. 若公共判断触发高责任、公共制度、长期演化、框架治理、AI 现实验证、弱信号\u002F不透明、无法退出、工具化、隐喻\u002F来源透明或文章输出，追加读取 `..\u002Fcrossframe\u002Freferences\u002Fcontinuity-bundles.md`，并按需使用 `..\u002Fcrossframe\u002Fworksheets\u002Fsource-continuity-check.md`；未完成联读时只能降档。\n4. 复用 `..\u002Fcrossframe\u002Ftemplates\u002Fread-state-capsule.md` 规定的 `v5-read-state-capsule`，并在高责任、公共、AI\u002F过程性产物、生命周期、无法退出主体或文章输出场景执行 `..\u002Fcrossframe\u002Fworksheets\u002Fsource-anchor-integrity-check.md`。如果胶囊缺失，回到 `..\u002Fcrossframe\u002FSKILL.md` 补齐；本 skill 不重新发明源路由。\n5. `protocols\u002Fpublic-issue-protocol.md`\n6. `references\u002Fsource-and-evidence-rules.md`\n7. `..\u002Fcrossframe\u002Freferences\u002Fsource-ledger-workflow.md`，用于统一记录来源、时间、来源类型、支持命题、不能证明什么、证据档位、使用位置、降档理由和仍需补证处。\n\n公共评论、平台治理、机构合规、公共强判断默认触发 `v5-public-power-institution-pack`、`v5-low-power-protection-pack`、`v5-evidence-downgrade-action-ceiling-pack`；AI 报告或合规材料追加 `v5-ai-process-artifact-boundary-pack`。\n\n按任务类型追加：\n\n- 平台处罚、封禁、限流、删帖、账号申诉：读 `protocols\u002Fplatform-appeal-protocol.md` 和 `templates\u002Faction-boundary.md`。\n- 公共政策、制度评论、公共承诺兑现：读 `protocols\u002Fpublic-policy-protocol.md` 和 `templates\u002Fpublic-comment-draft.md`。\n- 机构自查、整改报告、AI 合规材料、伦理\u002F安全声明：读 `protocols\u002Finstitutional-compliance-protocol.md` 和 `references\u002Fai-compliance-performance.md`。\n- 需要写成公共评论文章：再读 `..\u002Fcrossframe-essay\u002FSKILL.md`，但事实边界和证据档位仍以本 skill 为入口。\n- 只要求边界、不要求评论：使用 `templates\u002Fevidence-boundary-summary.md` 或 `templates\u002Faction-boundary.md`。\n\n## 默认查源\n\n真实公共议题默认需要查源，并按 `..\u002Fcrossframe\u002Freferences\u002Fsource-ledger-workflow.md` 建来源台账。优先找原始材料、官方文本、平台规则、政策原文、监管\u002F司法\u002F审计文件、当事方一手声明、可信媒体交叉报道和可复核数据。\n\n如果用户明确禁止联网或当前无法查源：\n\n- 不输出强判断。\n- 不把热度、转述、截图、平台声明或机构自评当事实。\n- 输出 `证据边界摘要` 或 `行动边界`，并标注“未查源，只能作为待核验框架”；若已有用户材料，也要写明这些材料能支持什么、不能证明什么。\n\n## 核心检查\n\n公共议题输出必须检查五组问题：\n\n- 程序正义：规则是否事前公开、适用是否一致、证据是否可见、复核是否独立。\n- 申诉有效性：申诉入口是否可达、理由是否可提交、回复是否具体、纠错是否真实改变结果。\n- 弱信号保护：投诉、异常数据、少数证词、边缘群体受损是否被热度或机构话术淹没。\n- 公共承诺偿付：道歉、整改、补偿、承诺是否转成可检验的资源、期限、责任人和反馈机制。\n- AI 合规表演风险：漂亮报告、自评清单、模型生成材料、伦理口号是否替代了外部验证和真实约束。\n\n## 证据档位\n\n输出前把材料分为：\n\n- 已核验事实：能被原文、记录、可复核数据或多源交叉支持。\n- 高成本证据：会带来法律、组织、经济、声誉或操作成本的材料。\n- 低成本声明：平台公告、机构自评、PR 文案、无细节道歉、AI 生成合规文本。\n- 弱信号：尚未形成定论，但指向受损、失灵、压制或异常的早期信号。\n- 热度信号：搜索量、转发、评论、话题排名；只能说明关注，不直接说明真伪。\n- 解释\u002F判断：基于事实和机制候选形成的开放断言或评论判断。\n\n## 输出模式\n\n按用户意图选择一个主输出：\n\n- 公共制度诊断：说明制度对象、事实边界、程序\u002F申诉\u002F弱信号\u002F承诺偿付\u002FAI 合规风险和机制候选。\n- 公共评论底稿：先给证据边界和中心命题，再写可发表的评论草稿。\n- 证据边界摘要：列出已核验、未核验、低成本声明、热度信号、反向条件和下一步核验。\n- 行动边界：给出低风险、可撤回、可记录、可复核的行动建议；不替代法律、医疗、安全或专业意见。\n\n## 硬规则\n\n- 不查源时不得装作已经查源；只能降档。\n- 不得把热度当事实，不得把平台\u002F机构声明当强证据。\n- 不得省略来源台账中的“不能证明什么”和“降档理由”。\n- 不得把公共议题写成人格审判、道德宣判、阵营标签或羞辱动员。\n- 不得用 CrossFrame 术语替代证据核验、专业领域知识或法律判断。\n- 不得把“合规材料存在”写成“合规已经发生”。\n- 不得为了评论锋利而隐藏证据缺口、反向条件或可能撤回判断的材料。\n- 涉及现实人物、组织、权利、处分、资格、公共记忆时，按 `..\u002Fcrossframe\u002Freferences\u002Fread-routing-map.md` 进入高责任\u002F命题验证\u002F公共制度相关路由。\n\n## 最低合格输出\n\n一次合格输出至少回答：\n\n- 这次讨论的公共对象是什么？\n- 哪些事实已经核验，哪些只是声明、热度或解释？\n- 程序正义和申诉有效性是否可见？\n- 谁承担成本，谁拥有改变条件？\n- 弱信号是否被保护，还是被热度\u002F话术淹没？\n- 公共承诺是否有偿付路径？\n- 是否存在 AI 合规表演风险？\n- 本次判断处于什么档位，什么证据会使它撤回或升级？\n- 下一步应查什么、说什么、做什么，以及不能做什么？\n","# CrossFrame Public\n\n\n\n## When to Use This Skill\n\n- Use when `crossframe-suite` routes an explicit CrossFrame task about public issues, platform governance, policy, institutional responsibility, public commitments, appeals, or compliance materials.\n- Use when source ledgers, evidence downgrades, public responsibility boundaries, and low-power subject protection matter.\n- Do not use independently unless the user explicitly names this sibling skill.\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> **本 skill 不独立触发。** 所有 CrossFrame 任务统一从 `crossframe-suite` 入口调度。用户无需直接调用本 skill；suite 根据路由规则在需要时自动加载。\n\n如果公共议题分析之后要写评论文章、组织建议、辩论论证或质量评审，先读取 `..\u002Fcrossframe-suite\u002FSKILL.md` 做总调度；本 skill 只负责公共事实、证据边界、程序与制度专项判断。\n\nCrossFrame Public 是 `crossframe` 的公共议题\u002F制度评论专项轻入口，不复制 canonical CrossFrame 全文。中文是权威语义；英文只作为 skill id、文件名或对外简介。\n\n## 必须读取\n\n每次触发后先读取：\n\n1. `..\u002Fcrossframe\u002FSKILL.md`\n2. `..\u002Fcrossframe\u002Freferences\u002Fread-routing-map.md`\n3. 若公共判断触发高责任、公共制度、长期演化、框架治理、AI 现实验证、弱信号\u002F不透明、无法退出、工具化、隐喻\u002F来源透明或文章输出，追加读取 `..\u002Fcrossframe\u002Freferences\u002Fcontinuity-bundles.md`，并按需使用 `..\u002Fcrossframe\u002Fworksheets\u002Fsource-continuity-check.md`；未完成联读时只能降档。\n4. 复用 `..\u002Fcrossframe\u002Ftemplates\u002Fread-state-capsule.md` 规定的 `v5-read-state-capsule`，并在高责任、公共、AI\u002F过程性产物、生命周期、无法退出主体或文章输出场景执行 `..\u002Fcrossframe\u002Fworksheets\u002Fsource-anchor-integrity-check.md`。如果胶囊缺失，回到 `..\u002Fcrossframe\u002FSKILL.md` 补齐；本 skill 不重新发明源路由。\n5. `protocols\u002Fpublic-issue-protocol.md`\n6. `references\u002Fsource-and-evidence-rules.md`\n7. `..\u002Fcrossframe\u002Freferences\u002Fsource-ledger-workflow.md`，用于统一记录来源、时间、来源类型、支持命题、不能证明什么、证据档位、使用位置、降档理由和仍需补证处。\n\n公共评论、平台治理、机构合规、公共强判断默认触发 `v5-public-power-institution-pack`、`v5-low-power-protection-pack`、`v5-evidence-downgrade-action-ceiling-pack`；AI 报告或合规材料追加 `v5-ai-process-artifact-boundary-pack`。\n\n按任务类型追加：\n\n- 平台处罚、封禁、限流、删帖、账号申诉：读 `protocols\u002Fplatform-appeal-protocol.md` 和 `templates\u002Faction-boundary.md`。\n- 公共政策、制度评论、公共承诺兑现：读 `protocols\u002Fpublic-policy-protocol.md` 和 `templates\u002Fpublic-comment-draft.md`。\n- 机构自查、整改报告、AI 合规材料、伦理\u002F安全声明：读 `protocols\u002Finstitutional-compliance-protocol.md` 和 `references\u002Fai-compliance-performance.md`。\n- 需要写成公共评论文章：再读 `..\u002Fcrossframe-essay\u002FSKILL.md`，但事实边界和证据档位仍以本 skill 为入口。\n- 只要求边界、不要求评论：使用 `templates\u002Fevidence-boundary-summary.md` 或 `templates\u002Faction-boundary.md`。\n\n## 默认查源\n\n真实公共议题默认需要查源，并按 `..\u002Fcrossframe\u002Freferences\u002Fsource-ledger-workflow.md` 建来源台账。优先找原始材料、官方文本、平台规则、政策原文、监管\u002F司法\u002F审计文件、当事方一手声明、可信媒体交叉报道和可复核数据。\n\n如果用户明确禁止联网或当前无法查源：\n\n- 不输出强判断。\n- 不把热度、转述、截图、平台声明或机构自评当事实。\n- 输出 `证据边界摘要` 或 `行动边界`，并标注“未查源，只能作为待核验框架”；若已有用户材料，也要写明这些材料能支持什么、不能证明什么。\n\n## 核心检查\n\n公共议题输出必须检查五组问题：\n\n- 程序正义：规则是否事前公开、适用是否一致、证据是否可见、复核是否独立。\n- 申诉有效性：申诉入口是否可达、理由是否可提交、回复是否具体、纠错是否真实改变结果。\n- 弱信号保护：投诉、异常数据、少数证词、边缘群体受损是否被热度或机构话术淹没。\n- 公共承诺偿付：道歉、整改、补偿、承诺是否转成可检验的资源、期限、责任人和反馈机制。\n- AI 合规表演风险：漂亮报告、自评清单、模型生成材料、伦理口号是否替代了外部验证和真实约束。\n\n## 证据档位\n\n输出前把材料分为：\n\n- 已核验事实：能被原文、记录、可复核数据或多源交叉支持。\n- 高成本证据：会带来法律、组织、经济、声誉或操作成本的材料。\n- 低成本声明：平台公告、机构自评、PR 文案、无细节道歉、AI 生成合规文本。\n- 弱信号：尚未形成定论，但指向受损、失灵、压制或异常的早期信号。\n- 热度信号：搜索量、转发、评论、话题排名；只能说明关注，不直接说明真伪。\n- 解释\u002F判断：基于事实和机制候选形成的开放断言或评论判断。\n\n## 输出模式\n\n按用户意图选择一个主输出：\n\n- 公共制度诊断：说明制度对象、事实边界、程序\u002F申诉\u002F弱信号\u002F承诺偿付\u002FAI 合规风险和机制候选。\n- 公共评论底稿：先给证据边界和中心命题，再写可发表的评论草稿。\n- 证据边界摘要：列出已核验、未核验、低成本声明、热度信号、反向条件和下一步核验。\n- 行动边界：给出低风险、可撤回、可记录、可复核的行动建议；不替代法律、医疗、安全或专业意见。\n\n## 硬规则\n\n- 不查源时不得装作已经查源；只能降档。\n- 不得把热度当事实，不得把平台\u002F机构声明当强证据。\n- 不得省略来源台账中的“不能证明什么”和“降档理由”。\n- 不得把公共议题写成人格审判、道德宣判、阵营标签或羞辱动员。\n- 不得用 CrossFrame 术语替代证据核验、专业领域知识或法律判断。\n- 不得把“合规材料存在”写成“合规已经发生”。\n- 不得为了评论锋利而隐藏证据缺口、反向条件或可能撤回判断的材料。\n- 涉及现实人物、组织、权利、处分、资格、公共记忆时，按 `..\u002Fcrossframe\u002Freferences\u002Fread-routing-map.md` 进入高责任\u002F命题验证\u002F公共制度相关路由。\n\n## 最低合格输出\n\n一次合格输出至少回答：\n\n- 这次讨论的公共对象是什么？\n- 哪些事实已经核验，哪些只是声明、热度或解释？\n- 程序正义和申诉有效性是否可见？\n- 谁承担成本，谁拥有改变条件？\n- 弱信号是否被保护，还是被热度\u002F话术淹没？\n- 公共承诺是否有偿付路径？\n- 是否存在 AI 合规表演风险？\n- 本次判断处于什么档位，什么证据会使它撤回或升级？\n- 下一步应查什么、说什么、做什么，以及不能做什么？\n",{"name":5,"risk":24,"tags":25,"tools":31,"author":35,"source":36,"license":15,"category":37,"date_added":38,"description":7,"source_repo":39,"source_type":36,"license_source":40},"safe",[26,27,28,29,30],"crossframe","chinese","public-policy","governance","evidence",[32,33,34],"Agent Skills","Codex","Claude","xi-kari","community","workflow",1781568000000,"xi-kari\u002Fcrossframe-skill","https:\u002F\u002Fgithub.com\u002Fxi-kari\u002Fcrossframe-skill\u002Fblob\u002Fmain\u002FLICENSE","main","c475fc64e94e803b50d14a791dfee8853fbb2c5c","integrations\u002Fantigravity-skills\u002Fskills\u002Fcrossframe-public","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory","https:\u002F\u002Fgithub.com\u002FElogic360","2026-11-08 22:21:22",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add Elogic360\u002Fsoftware-factory --skill crossframe-public",{"tool":53,"command":54},"bunx","bunx skills add Elogic360\u002Fsoftware-factory --skill crossframe-public",{"tool":56,"command":57},"pnpm","pnpm dlx skills add Elogic360\u002Fsoftware-factory --skill crossframe-public","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fskills\u002Fcrossframe-public\u002FSKILL.md",true,[61,67,71,75,79,83,87,91,95,99,103,107,111,115,119,123,127,131],{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"agents\u002Fopenai.yaml","REFERENCE","参考文档",349,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fskills\u002Fcrossframe-public\u002Fagents\u002Fopenai.yaml",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"evals\u002Fcrossframe-public-smoke-tests.md",2951,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fskills\u002Fcrossframe-public\u002Fevals\u002Fcrossframe-public-smoke-tests.md",{"path":72,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":73,"sourceHtmlUrl":74},"examples\u002Ffailure-samples.md",901,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fskills\u002Fcrossframe-public\u002Fexamples\u002Ffailure-samples.md",{"path":76,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":77,"sourceHtmlUrl":78},"examples\u002Finstitutional-compliance-case.md",810,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fskills\u002Fcrossframe-public\u002Fexamples\u002Finstitutional-compliance-case.md",{"path":80,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":81,"sourceHtmlUrl":82},"examples\u002Fplatform-appeal-case.md",902,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fskills\u002Fcrossframe-public\u002Fexamples\u002Fplatform-appeal-case.md",{"path":84,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":85,"sourceHtmlUrl":86},"examples\u002Fpublic-policy-case.md",696,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fskills\u002Fcrossframe-public\u002Fexamples\u002Fpublic-policy-case.md",{"path":88,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":89,"sourceHtmlUrl":90},"protocols\u002Finstitutional-compliance-protocol.md",1179,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fskills\u002Fcrossframe-public\u002Fprotocols\u002Finstitutional-compliance-protocol.md",{"path":92,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":93,"sourceHtmlUrl":94},"protocols\u002Fplatform-appeal-protocol.md",1340,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fskills\u002Fcrossframe-public\u002Fprotocols\u002Fplatform-appeal-protocol.md",{"path":96,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":97,"sourceHtmlUrl":98},"protocols\u002Fpublic-issue-protocol.md",2284,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fskills\u002Fcrossframe-public\u002Fprotocols\u002Fpublic-issue-protocol.md",{"path":100,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":101,"sourceHtmlUrl":102},"protocols\u002Fpublic-policy-protocol.md",1045,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fskills\u002Fcrossframe-public\u002Fprotocols\u002Fpublic-policy-protocol.md",{"path":104,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":105,"sourceHtmlUrl":106},"references\u002Fai-compliance-performance.md",1133,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fskills\u002Fcrossframe-public\u002Freferences\u002Fai-compliance-performance.md",{"path":108,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":109,"sourceHtmlUrl":110},"references\u002Fpublic-evidence-ladder.md",778,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fskills\u002Fcrossframe-public\u002Freferences\u002Fpublic-evidence-ladder.md",{"path":112,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":113,"sourceHtmlUrl":114},"references\u002Frisk-language-boundaries.md",762,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fskills\u002Fcrossframe-public\u002Freferences\u002Frisk-language-boundaries.md",{"path":116,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":117,"sourceHtmlUrl":118},"references\u002Fsource-and-evidence-rules.md",1731,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fskills\u002Fcrossframe-public\u002Freferences\u002Fsource-and-evidence-rules.md",{"path":120,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":121,"sourceHtmlUrl":122},"templates\u002Faction-boundary.md",532,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fskills\u002Fcrossframe-public\u002Ftemplates\u002Faction-boundary.md",{"path":124,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":125,"sourceHtmlUrl":126},"templates\u002Fevidence-boundary-summary.md",479,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fskills\u002Fcrossframe-public\u002Ftemplates\u002Fevidence-boundary-summary.md",{"path":128,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":129,"sourceHtmlUrl":130},"templates\u002Fpublic-comment-draft.md",774,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fskills\u002Fcrossframe-public\u002Ftemplates\u002Fpublic-comment-draft.md",{"path":132,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":133,"sourceHtmlUrl":134},"templates\u002Fpublic-institution-diagnosis.md",708,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fantigravity-skills\u002Fskills\u002Fcrossframe-public\u002Ftemplates\u002Fpublic-institution-diagnosis.md",[136,144,151,158,165,172],{"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":140,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":143,"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":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":140,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":150,"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":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":140,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":157,"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":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":140,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":164,"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":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":140,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":171,"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":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":140,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":178,"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",[],[]]