[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71DXS0XJCT9TMMPWF98ZDVX":3,"skill-same:01M71DXS0XJCT9TMMPWF98ZDVX":79},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":6,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M71DXS0XJCT9TMMPWF98ZDVX","handoff-all",null,"Tell every open Claude Code desktop session to run \u002Fhandoff, then collect each session's \u002Fresumework command. Triggers: \"handoff all sessions\", \"wrap up every session\".","indigoai-us\u002Fhq-core","indigoai-us","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F122242446?v=4","01M71DTQ5NGD10GT1Z7E6XKWC5","HQ","01M71DTQ6BKSYYBNC9RAKT3YDK",94,"MIT","https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fhandoff-all\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"handoff","handoff all","wrap up","wrap","read","run","command","desktop","message","code","Bash","MCP","open","triggers","sessions","up","send","session","collect","get","2026-11-10 10:12:30",false,"---\nname: handoff-all\ndescription: \"Tell every open Claude Code desktop session to run \u002Fhandoff, then collect each session's \u002Fresumework command. Triggers: \\\"handoff all sessions\\\", \\\"wrap up every session\\\".\"\nallowed-tools: Bash, Read, AskUserQuestion, mcp__ccd_session_mgmt__list_sessions, mcp__ccd_session_mgmt__get_session, mcp__ccd_session_mgmt__send_message, mcp__ccd_session_mgmt__list_events\n---\n\n# Handoff All Sessions\n\nBroadcast `\u002Fhandoff` to every open desktop session and return one HQ resume\ncommand (`\u002Fresumework \u003Cthread-id>`) per session. Never return Claude-native\nresume commands (`claude --resume`, session links) as the resume path.\n\n**Arguments:** `$ARGUMENTS` — optional `--dry-run` (stop after step 2),\n`--running-only` (skip idle sessions), `--include \u003Cid,...>`, `--exclude \u003Cid,...>`.\n\n## Requirements\n\n- Desktop app runtime with the `ccd_session_mgmt` tools. In the terminal CLI\n  or headless (`CLAUDE_HEADLESS=1`), STOP and say this skill needs the desktop app.\n\n## Process\n\n### 1. Inventory\n\nCall `list_sessions` with `limit: 100`, `include_archived: false`. The current\nsession is excluded automatically. Apply `--running-only`, `--include`,\n`--exclude`. Skip unattended sessions (scheduled-task runs); `send_message`\ncannot deliver to them.\n\n### 2. Readiness table and confirm\n\nShow a table: title, running\u002Fidle, last activity, session id. Sending a\nmessage starts a turn in each target session, so this is an outward action.\nAsk for an explicit go with `AskUserQuestion` (options: send to all listed \u002F\nrunning only \u002F cancel). `--dry-run` stops here.\n\n### 3. Broadcast\n\nFor each target, call `send_message` with this body (verbatim, fill nothing):\n\n> Run `\u002Fhandoff` now to close out this session. In the handoff, record every\n> active \u002Fconduct lane, background agent, PR watch, and other tracked item with\n> its id, state, and next step, plus whether this session was in conduct mode\n> (engine and child model). When it finishes, reply with\n> exactly one final line in the form `HQ-RESUME: \u002Fresumework \u003Cthread-id>`. If\n> this session produced no resumable state, reply `HQ-RESUME: none (\u003Creason>)`.\n\nRecord the returned delivery status (`delivered` \u002F `queued` \u002F error) and\n`message_id` per session. Do not retry errors blindly; report them.\n\n### 4. Collect\n\nPoll each session with `list_events` (back off, roughly every 60s, cap ~20\nminutes) for the `HQ-RESUME:` line. As a fallback, match new thread files:\n`ls -t workspace\u002Fthreads\u002FT-*.json | grep -v changeset` created after the\nbroadcast, using each thread's session\u002Ftitle fields to map it to a session.\n\n### 5. Write the batch manifest\n\nWrite `workspace\u002Fhandoff-all\u002F\u003Cbatch-id>.json` where `\u003Cbatch-id>` is\n`HA-YYYYMMDD-HHMMSS`. This file is the only input `\u002Fresume-all` trusts.\n\n```json\n{\n  \"batch_id\": \"HA-20261003-031500\",\n  \"created_at\": \"\u003CISO-8601>\",\n  \"resumed_at\": null,\n  \"sessions\": [\n    {\"session_id\": \"local_...\", \"title\": \"...\", \"cwd\": \"...\",\n     \"status\": \"handed_off|no_state|failed|no_reply\",\n     \"thread_id\": \"T-...\", \"resume_command\": \"\u002Fresumework T-...\",\n     \"conduct\": {\"enabled\": true, \"engine\": \"claude\", \"child_model\": \"...\"}}\n  ]\n}\n```\n\n### 6. Report\n\nFinal message lists one row per session:\n\n| Session | Status | Resume command |\n|---|---|---|\n| title | handed off \u002F no state \u002F failed \u002F still running | `\u002Fresumework T-...` |\n\nFlag sessions that never answered or errored. Do not run `\u002Fhandoff` for this\nsession unless the user asks.\n","# Handoff All Sessions\n\nBroadcast `\u002Fhandoff` to every open desktop session and return one HQ resume\ncommand (`\u002Fresumework \u003Cthread-id>`) per session. Never return Claude-native\nresume commands (`claude --resume`, session links) as the resume path.\n\n**Arguments:** `$ARGUMENTS` — optional `--dry-run` (stop after step 2),\n`--running-only` (skip idle sessions), `--include \u003Cid,...>`, `--exclude \u003Cid,...>`.\n\n## Requirements\n\n- Desktop app runtime with the `ccd_session_mgmt` tools. In the terminal CLI\n  or headless (`CLAUDE_HEADLESS=1`), STOP and say this skill needs the desktop app.\n\n## Process\n\n### 1. Inventory\n\nCall `list_sessions` with `limit: 100`, `include_archived: false`. The current\nsession is excluded automatically. Apply `--running-only`, `--include`,\n`--exclude`. Skip unattended sessions (scheduled-task runs); `send_message`\ncannot deliver to them.\n\n### 2. Readiness table and confirm\n\nShow a table: title, running\u002Fidle, last activity, session id. Sending a\nmessage starts a turn in each target session, so this is an outward action.\nAsk for an explicit go with `AskUserQuestion` (options: send to all listed \u002F\nrunning only \u002F cancel). `--dry-run` stops here.\n\n### 3. Broadcast\n\nFor each target, call `send_message` with this body (verbatim, fill nothing):\n\n> Run `\u002Fhandoff` now to close out this session. In the handoff, record every\n> active \u002Fconduct lane, background agent, PR watch, and other tracked item with\n> its id, state, and next step, plus whether this session was in conduct mode\n> (engine and child model). When it finishes, reply with\n> exactly one final line in the form `HQ-RESUME: \u002Fresumework \u003Cthread-id>`. If\n> this session produced no resumable state, reply `HQ-RESUME: none (\u003Creason>)`.\n\nRecord the returned delivery status (`delivered` \u002F `queued` \u002F error) and\n`message_id` per session. Do not retry errors blindly; report them.\n\n### 4. Collect\n\nPoll each session with `list_events` (back off, roughly every 60s, cap ~20\nminutes) for the `HQ-RESUME:` line. As a fallback, match new thread files:\n`ls -t workspace\u002Fthreads\u002FT-*.json | grep -v changeset` created after the\nbroadcast, using each thread's session\u002Ftitle fields to map it to a session.\n\n### 5. Write the batch manifest\n\nWrite `workspace\u002Fhandoff-all\u002F\u003Cbatch-id>.json` where `\u003Cbatch-id>` is\n`HA-YYYYMMDD-HHMMSS`. This file is the only input `\u002Fresume-all` trusts.\n\n```json\n{\n  \"batch_id\": \"HA-20261003-031500\",\n  \"created_at\": \"\u003CISO-8601>\",\n  \"resumed_at\": null,\n  \"sessions\": [\n    {\"session_id\": \"local_...\", \"title\": \"...\", \"cwd\": \"...\",\n     \"status\": \"handed_off|no_state|failed|no_reply\",\n     \"thread_id\": \"T-...\", \"resume_command\": \"\u002Fresumework T-...\",\n     \"conduct\": {\"enabled\": true, \"engine\": \"claude\", \"child_model\": \"...\"}}\n  ]\n}\n```\n\n### 6. Report\n\nFinal message lists one row per session:\n\n| Session | Status | Resume command |\n|---|---|---|\n| title | handed off \u002F no state \u002F failed \u002F still running | `\u002Fresumework T-...` |\n\nFlag sessions that never answered or errored. Do not run `\u002Fhandoff` for this\nsession unless the user asks.\n",{"name":5,"description":7,"allowed-tools":49},"Bash, Read, AskUserQuestion, mcp__ccd_session_mgmt__list_sessions, mcp__ccd_session_mgmt__get_session, mcp__ccd_session_mgmt__send_message, mcp__ccd_session_mgmt__list_events","main","205cf61728a27ef15e9153aa38df5856fc8d82f5",".claude\u002Fskills\u002Fhandoff-all",18,"https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core","https:\u002F\u002Fgithub.com\u002Findigoai-us","https:\u002F\u002Fhqforwork.com\u002F","The AI Context Layer for Teams","2026-11-09 23:36:37",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add indigoai-us\u002Fhq-core --skill handoff-all",{"tool":65,"command":66},"bunx","bunx skills add indigoai-us\u002Fhq-core --skill handoff-all",{"tool":68,"command":69},"pnpm","pnpm dlx skills add indigoai-us\u002Fhq-core --skill handoff-all","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fhandoff-all\u002FSKILL.md",true,[73],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"agents\u002Fopenai.yaml","REFERENCE","参考文档",137,"https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fhandoff-all\u002Fagents\u002Fopenai.yaml",[80,99,125,148,159,168],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":44},"01M71E4MQ04WPK1EVDS7VKJ3E8","social-graphic","Generate 1080x1080 HTML social graphics for HQ update posts.","https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002Fcore\u002Fworkers\u002Fpublic\u002Fsocial-strategist\u002Fskills\u002Fsocial-graphic\u002FSKILL.md",[],[87,88,34,89,90,91,28,92,93,94,95,36,96,97,98],"social","social graphic","html","edit","write","update","generate","graphics","browser","agent-browser","for","posts",{"skillNo":100,"name":96,"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":108,"publishedAt":44},"01M71E4H33K4P5H5M7ENPTMFSC","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002Fcore\u002Fworkers\u002Fpublic\u002Fqa-tester\u002Fskills\u002Fagent-browser\u002FSKILL.md",[104,107],{"categoryNo":105,"categoryName":106,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[109,95,110,111,112,113,34,114,115,116,117,118,36,119,96,120,121,122,123,124],"agent browser","click","ai agents","app","scrape","when","apps","actions","extracting","take a screenshot","testing","programmatic","browser automation","website","cli","interaction",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":44},"01M71E4FDBD7J8Y45JJ9KMMYGN","work-mesh","Work Mesh Live — automatic presence via hq mesh daemon; context reconcile\u002Forganize; manual session task-status, blocked, and note only.","https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fwork-mesh\u002FSKILL.md",[],[132,133,134,34,135,136,137,138,139,140,141,142,143,144,28,41,145,146,147],"work mesh","work","mesh","status","context","note","live","presence","automatic","reconcile","only","organize","task","manual","daemon","via",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":154,"publishedAt":44},"01M71E4EGHNAAGWAPV6KGBMQ9W","review","Parity worker review skill (materialization fixture).","https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002Fcore\u002Fscripts\u002Ftests\u002Ffixtures\u002Fagent-session\u002Fworker-materialization\u002Fparity-worker\u002Fskills\u002Freview\u002FSKILL.md",[],[150,155,156,157,158],"review skill","fixture","parity","worker",{"skillNo":160,"name":29,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":164,"publishedAt":44},"01M71E4D1FZDJPDC15DRERKX8Y","Run or list HQ workers (parity fixture).","https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002Fcore\u002Fscripts\u002Ftests\u002Ffixtures\u002Fagent-session\u002Fskills\u002Frun\u002FSKILL.md",[],[29,165,166,157,167,156],"parity fixture","workers","list",{"skillNo":169,"name":24,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":173,"publishedAt":44},"01M71E4BF4MV5SEWZJZ4T1QPQW","Preserve session state for a follow-up agent (parity fixture).","https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002Fcore\u002Fscripts\u002Ftests\u002Ffixtures\u002Fagent-session\u002Fskills\u002Fhandoff\u002FSKILL.md",[],[24,165,39,174,41,175,97,157,176,177,156],"preserve","session state","follow-up","state"]