[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6J9CMRCEPZEZB9FXF5P3H3F":3,"skill-same:01M6J9CMRCEPZEZB9FXF5P3H3F":81},{"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":45,"linkOnly":46,"markdownContent":47,"markdownBody":48,"frontMatter":49,"refName":60,"commitSha":61,"skillDirectory":62,"forksCount":54,"repositoryHtmlUrl":63,"repositoryHomepageUrl":6,"ownerHtmlUrl":64,"ownerBlogUrl":65,"ownerDescription":66,"updatedAt":67,"install":68,"resources":80},"01M6J9CMRCEPZEZB9FXF5P3H3F","openclaw-official-telegram-crabbox-e2e-proof",null,"Use when reviewing, reproducing, or proving OpenClaw Telegram behavior with a real Telegram user on Crabbox, including PR review workflows that need an agent-controlled Telegram Desktop recording, TDLib user-driver commands, Convex-leased credentials, WebVNC observation, and motion-trimmed artifacts.","Flissel\u002Fvibemind-os","Flissel","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F104565236?v=4","01M6J8Q88NWAJGKPC5TEG9YCNV","Felix Baumann","01M6J8Q8D7XAFY44P70XTJFZBW",1,"MIT","https:\u002F\u002Fgithub.com\u002FFlissel\u002Fvibemind-os\u002Fblob\u002Fmaster\u002Fskills\u002Fopenclaw-official\u002Ftelegram-crabbox-e2e-proof\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44],"openclaw","openclaw official telegram crabbox e2e proof","proof","telegram","e2e proof","e2e","official","crabbox","pr","artifacts","pr review","workflows","repo","use","convex","motion","imported","review","recording","true","when","2026-11-10 10:12:30",false,"---\nname: openclaw-official-telegram-crabbox-e2e-proof\ndescription: Use when reviewing, reproducing, or proving OpenClaw Telegram behavior\n  with a real Telegram user on Crabbox, including PR review workflows that need an\n  agent-controlled Telegram Desktop recording, TDLib user-driver commands, Convex-leased\n  credentials, WebVNC observation, and motion-trimmed artifacts.\napp: openclaw-official\nrequires_approval: true\nagents:\n- '*'\ninputs: []\nexpected_state:\n  description: Imported skill — behavior matches source repo\n  verification_tool: none\nconfidence: 1.0\nattempts: 0\nsuccesses: 0\nlast_adjusted: '2026-05-11T21:59:15+00:00'\n---\n\n# Telegram Crabbox E2E Proof\n\nUse this for Telegram PR review or bug reproduction when bot-to-bot proof is\nnot enough. The goal is to let the agent keep a real Telegram user session open\nuntil it is satisfied, then attach visual proof.\n\nDo not use personal accounts. Do not add credentials to the repo, prompt, or\nartifact bundle. The runner leases the shared burner account from Convex.\n\n## Start\n\nRun from the OpenClaw repo and branch under test:\n\n```bash\npnpm qa:telegram-user:crabbox -- start \\\n  --tdlib-url http:\u002F\u002Fartifacts.openclaw.ai\u002Ftdlib-v1.8.0-linux-x64.tgz \\\n  --output-dir .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-review\n```\n\nThis starts one held session:\n\n- leases the exclusive `telegram-user` Convex credential\n- restores TDLib and Telegram Desktop with the same user account\n- starts a mock OpenClaw Telegram SUT from the current checkout\n- selects the configured Telegram chat in the visible Linux desktop\n- starts a 24fps desktop recording\n- writes `.artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-review\u002Fsession.json`\n\nKeep the session alive while investigating. It is valid for the agent to test\nfor minutes, run several commands, use WebVNC, inspect transcripts, and only\nfinish once the behavior is understood.\n\nFor deterministic visual repros, put the exact mock-model reply in a file and\npass it to `start`:\n\n```bash\npnpm qa:telegram-user:crabbox -- start \\\n  --tdlib-url http:\u002F\u002Fartifacts.openclaw.ai\u002Ftdlib-v1.8.0-linux-x64.tgz \\\n  --mock-response-file .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Freply.txt \\\n  --output-dir .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-review\n```\n\nThe runner defaults to `--class standard`, `--record-fps 24`,\n`--preview-fps 24`, and `--preview-width 1920`. Keep those defaults unless the\nproof needs something else.\n\n## While Testing\n\nFor visual proof, first send or identify a bottom marker message, then open the\ngroup\u002Ftopic directly by message id:\n\n```bash\npnpm qa:telegram-user:crabbox -- view \\\n  --session .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-review\u002Fsession.json \\\n  --message-id \u003Cmessage-id>\n```\n\nThis uses Telegram Desktop directly with `tg:\u002F\u002Fprivatepost`, not `xdg-open`.\nIt also resizes Telegram to `650x1000` at the tested desktop position so\nTelegram switches to single-chat mode with no left chat list or right info\npane. Do not press Escape after this; Escape can close the selected chat.\n\nBottom behavior matters:\n\n- deep-linking to the newest message keeps Telegram pinned to the bottom, so\n  later messages appear live in the recording\n- deep-linking to an older message does not auto-scroll to new arrivals; link\n  again to the newest\u002Ffinal marker instead of clicking the down-arrow\n- `650px` is the largest tested clean width; `660px` switches Telegram back to\n  split\u002Fsidebar layout\n\nSend as the real Telegram user:\n\n```bash\npnpm qa:telegram-user:crabbox -- send \\\n  --session .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-review\u002Fsession.json \\\n  --text \u002Fstatus\n```\n\nFor slash commands, omit the bot username; the runner targets the SUT bot.\n\nRun arbitrary commands on the Crabbox:\n\n```bash\npnpm qa:telegram-user:crabbox -- run \\\n  --session .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-review\u002Fsession.json \\\n  -- bash -lc 'source \u002Ftmp\u002Fopenclaw-telegram-user-crabbox\u002Fenv.sh && python3 \u002Ftmp\u002Fopenclaw-telegram-user-crabbox\u002Fuser-driver.py transcript --limit 20 --json'\n```\n\nUseful remote user-driver commands:\n\n```bash\nsource \u002Ftmp\u002Fopenclaw-telegram-user-crabbox\u002Fenv.sh\npython3 \u002Ftmp\u002Fopenclaw-telegram-user-crabbox\u002Fuser-driver.py status --json\npython3 \u002Ftmp\u002Fopenclaw-telegram-user-crabbox\u002Fuser-driver.py chats --json\npython3 \u002Ftmp\u002Fopenclaw-telegram-user-crabbox\u002Fuser-driver.py transcript --limit 20 --json\npython3 \u002Ftmp\u002Fopenclaw-telegram-user-crabbox\u002Fuser-driver.py send --text '\u002Fstatus@{sut}'\npython3 \u002Ftmp\u002Fopenclaw-telegram-user-crabbox\u002Fuser-driver.py probe --text '@{sut} Reply exactly: USER-E2E-{run}' --expect USER-E2E-\n```\n\nCapture the current desktop without ending the session:\n\n```bash\npnpm qa:telegram-user:crabbox -- screenshot \\\n  --session .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-review\u002Fsession.json\n```\n\nCheck lease state and get the WebVNC command:\n\n```bash\npnpm qa:telegram-user:crabbox -- status \\\n  --session .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-review\u002Fsession.json\n```\n\n## Finish\n\nAlways finish or explicitly keep the box:\n\n```bash\npnpm qa:telegram-user:crabbox -- finish \\\n  --session .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-review\u002Fsession.json \\\n  --preview-crop telegram-window\n```\n\n`finish` stops recording, creates motion-trimmed MP4\u002FGIF artifacts, captures a\nfinal screenshot and logs, releases the Convex credential, stops the local SUT,\nand stops the Crabbox lease. `--preview-crop telegram-window` also creates a\nfixed-geometry GIF from the tested Telegram proof window for clean side-by-side\nPR tables; the full desktop video\u002FGIF remains in the artifact directory. Pass\n`--keep-box` only when a human needs to continue VNC debugging after the\ncredential is released.\n\nAfter any failure or interruption, verify cleanup:\n\n```bash\ncrabbox list --provider aws\n```\n\nIf a session file exists and the credential may still be leased, run `finish`\nwith that session file before retrying.\n\n## Attach Proof\n\nAttach only the useful visual artifact to the PR unless logs are needed. The\nrunner is GIF-only by default:\n\n```bash\npnpm qa:telegram-user:crabbox -- publish \\\n  --session .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-review\u002Fsession.json \\\n  --pr \u003Cpr-number> \\\n  --summary 'Telegram real-user Crabbox session motion GIF'\n```\n\nThis copies only the useful GIF into a temporary publish bundle and comments\nthat GIF. If `finish --preview-crop telegram-window` produced a cropped GIF,\npublish uses that; otherwise it uses `telegram-user-crabbox-session-motion.gif`.\nUse `--full-artifacts` only when the PR needs logs or JSON output. Never publish\ncredential payloads, local env files, TDLib databases, Telegram Desktop\nprofiles, or raw session archives.\n\nFor before\u002Fafter proof, run one session on `main` and one on the PR head, then\npublish only the intended GIFs from a clean bundle:\n\n```bash\nmkdir -p .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-123\u002Fcomparison\ncp \u003Cmain-output>\u002Ftelegram-user-crabbox-session-motion-telegram-window.gif \\\n  .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-123\u002Fcomparison\u002Fmain-before.gif\ncp \u003Cpr-output>\u002Ftelegram-user-crabbox-session-motion-telegram-window.gif \\\n  .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-123\u002Fcomparison\u002Fpr-after.gif\ncrabbox artifacts publish \\\n  --repo openclaw\u002Fopenclaw \\\n  --pr 123 \\\n  --dir .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-123\u002Fcomparison \\\n  --summary 'Telegram before\u002Fafter proof' \\\n  --no-comment\n```\n\nThen post a concise markdown table with those two URLs. Do not publish working\ndirectories that contain screenshots, raw videos, logs, session JSON, or crop\nexperiments unless those artifacts are explicitly needed.\n\n## Quick Smoke\n\nFor a fast one-shot check, use:\n\n```bash\npnpm qa:telegram-user:crabbox -- --text \u002Fstatus\n```\n\nThis is a start\u002Fsend\u002Ffinish shortcut. Prefer the held session for PR review,\nissue reproduction, or any task where the agent may need several attempts.\n","# Telegram Crabbox E2E Proof\n\nUse this for Telegram PR review or bug reproduction when bot-to-bot proof is\nnot enough. The goal is to let the agent keep a real Telegram user session open\nuntil it is satisfied, then attach visual proof.\n\nDo not use personal accounts. Do not add credentials to the repo, prompt, or\nartifact bundle. The runner leases the shared burner account from Convex.\n\n## Start\n\nRun from the OpenClaw repo and branch under test:\n\n```bash\npnpm qa:telegram-user:crabbox -- start \\\n  --tdlib-url http:\u002F\u002Fartifacts.openclaw.ai\u002Ftdlib-v1.8.0-linux-x64.tgz \\\n  --output-dir .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-review\n```\n\nThis starts one held session:\n\n- leases the exclusive `telegram-user` Convex credential\n- restores TDLib and Telegram Desktop with the same user account\n- starts a mock OpenClaw Telegram SUT from the current checkout\n- selects the configured Telegram chat in the visible Linux desktop\n- starts a 24fps desktop recording\n- writes `.artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-review\u002Fsession.json`\n\nKeep the session alive while investigating. It is valid for the agent to test\nfor minutes, run several commands, use WebVNC, inspect transcripts, and only\nfinish once the behavior is understood.\n\nFor deterministic visual repros, put the exact mock-model reply in a file and\npass it to `start`:\n\n```bash\npnpm qa:telegram-user:crabbox -- start \\\n  --tdlib-url http:\u002F\u002Fartifacts.openclaw.ai\u002Ftdlib-v1.8.0-linux-x64.tgz \\\n  --mock-response-file .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Freply.txt \\\n  --output-dir .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-review\n```\n\nThe runner defaults to `--class standard`, `--record-fps 24`,\n`--preview-fps 24`, and `--preview-width 1920`. Keep those defaults unless the\nproof needs something else.\n\n## While Testing\n\nFor visual proof, first send or identify a bottom marker message, then open the\ngroup\u002Ftopic directly by message id:\n\n```bash\npnpm qa:telegram-user:crabbox -- view \\\n  --session .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-review\u002Fsession.json \\\n  --message-id \u003Cmessage-id>\n```\n\nThis uses Telegram Desktop directly with `tg:\u002F\u002Fprivatepost`, not `xdg-open`.\nIt also resizes Telegram to `650x1000` at the tested desktop position so\nTelegram switches to single-chat mode with no left chat list or right info\npane. Do not press Escape after this; Escape can close the selected chat.\n\nBottom behavior matters:\n\n- deep-linking to the newest message keeps Telegram pinned to the bottom, so\n  later messages appear live in the recording\n- deep-linking to an older message does not auto-scroll to new arrivals; link\n  again to the newest\u002Ffinal marker instead of clicking the down-arrow\n- `650px` is the largest tested clean width; `660px` switches Telegram back to\n  split\u002Fsidebar layout\n\nSend as the real Telegram user:\n\n```bash\npnpm qa:telegram-user:crabbox -- send \\\n  --session .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-review\u002Fsession.json \\\n  --text \u002Fstatus\n```\n\nFor slash commands, omit the bot username; the runner targets the SUT bot.\n\nRun arbitrary commands on the Crabbox:\n\n```bash\npnpm qa:telegram-user:crabbox -- run \\\n  --session .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-review\u002Fsession.json \\\n  -- bash -lc 'source \u002Ftmp\u002Fopenclaw-telegram-user-crabbox\u002Fenv.sh && python3 \u002Ftmp\u002Fopenclaw-telegram-user-crabbox\u002Fuser-driver.py transcript --limit 20 --json'\n```\n\nUseful remote user-driver commands:\n\n```bash\nsource \u002Ftmp\u002Fopenclaw-telegram-user-crabbox\u002Fenv.sh\npython3 \u002Ftmp\u002Fopenclaw-telegram-user-crabbox\u002Fuser-driver.py status --json\npython3 \u002Ftmp\u002Fopenclaw-telegram-user-crabbox\u002Fuser-driver.py chats --json\npython3 \u002Ftmp\u002Fopenclaw-telegram-user-crabbox\u002Fuser-driver.py transcript --limit 20 --json\npython3 \u002Ftmp\u002Fopenclaw-telegram-user-crabbox\u002Fuser-driver.py send --text '\u002Fstatus@{sut}'\npython3 \u002Ftmp\u002Fopenclaw-telegram-user-crabbox\u002Fuser-driver.py probe --text '@{sut} Reply exactly: USER-E2E-{run}' --expect USER-E2E-\n```\n\nCapture the current desktop without ending the session:\n\n```bash\npnpm qa:telegram-user:crabbox -- screenshot \\\n  --session .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-review\u002Fsession.json\n```\n\nCheck lease state and get the WebVNC command:\n\n```bash\npnpm qa:telegram-user:crabbox -- status \\\n  --session .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-review\u002Fsession.json\n```\n\n## Finish\n\nAlways finish or explicitly keep the box:\n\n```bash\npnpm qa:telegram-user:crabbox -- finish \\\n  --session .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-review\u002Fsession.json \\\n  --preview-crop telegram-window\n```\n\n`finish` stops recording, creates motion-trimmed MP4\u002FGIF artifacts, captures a\nfinal screenshot and logs, releases the Convex credential, stops the local SUT,\nand stops the Crabbox lease. `--preview-crop telegram-window` also creates a\nfixed-geometry GIF from the tested Telegram proof window for clean side-by-side\nPR tables; the full desktop video\u002FGIF remains in the artifact directory. Pass\n`--keep-box` only when a human needs to continue VNC debugging after the\ncredential is released.\n\nAfter any failure or interruption, verify cleanup:\n\n```bash\ncrabbox list --provider aws\n```\n\nIf a session file exists and the credential may still be leased, run `finish`\nwith that session file before retrying.\n\n## Attach Proof\n\nAttach only the useful visual artifact to the PR unless logs are needed. The\nrunner is GIF-only by default:\n\n```bash\npnpm qa:telegram-user:crabbox -- publish \\\n  --session .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-review\u002Fsession.json \\\n  --pr \u003Cpr-number> \\\n  --summary 'Telegram real-user Crabbox session motion GIF'\n```\n\nThis copies only the useful GIF into a temporary publish bundle and comments\nthat GIF. If `finish --preview-crop telegram-window` produced a cropped GIF,\npublish uses that; otherwise it uses `telegram-user-crabbox-session-motion.gif`.\nUse `--full-artifacts` only when the PR needs logs or JSON output. Never publish\ncredential payloads, local env files, TDLib databases, Telegram Desktop\nprofiles, or raw session archives.\n\nFor before\u002Fafter proof, run one session on `main` and one on the PR head, then\npublish only the intended GIFs from a clean bundle:\n\n```bash\nmkdir -p .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-123\u002Fcomparison\ncp \u003Cmain-output>\u002Ftelegram-user-crabbox-session-motion-telegram-window.gif \\\n  .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-123\u002Fcomparison\u002Fmain-before.gif\ncp \u003Cpr-output>\u002Ftelegram-user-crabbox-session-motion-telegram-window.gif \\\n  .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-123\u002Fcomparison\u002Fpr-after.gif\ncrabbox artifacts publish \\\n  --repo openclaw\u002Fopenclaw \\\n  --pr 123 \\\n  --dir .artifacts\u002Fqa-e2e\u002Ftelegram-user-crabbox\u002Fpr-123\u002Fcomparison \\\n  --summary 'Telegram before\u002Fafter proof' \\\n  --no-comment\n```\n\nThen post a concise markdown table with those two URLs. Do not publish working\ndirectories that contain screenshots, raw videos, logs, session JSON, or crop\nexperiments unless those artifacts are explicitly needed.\n\n## Quick Smoke\n\nFor a fast one-shot check, use:\n\n```bash\npnpm qa:telegram-user:crabbox -- --text \u002Fstatus\n```\n\nThis is a start\u002Fsend\u002Ffinish shortcut. Prefer the held session for PR review,\nissue reproduction, or any task where the agent may need several attempts.\n",{"app":50,"name":5,"agents":51,"inputs":53,"attempts":54,"successes":54,"confidence":14,"description":7,"last_adjusted":55,"expected_state":56,"requires_approval":59},"openclaw-official",[52],"*",[],0,"2026-05-11T21:59:15+00:00",{"description":57,"verification_tool":58},"Imported skill — behavior matches source repo","none",true,"master","5f13b5d2b532c0ab6f847e3aa24d4bfe66f7d461","skills\u002Fopenclaw-official\u002Ftelegram-crabbox-e2e-proof","https:\u002F\u002Fgithub.com\u002FFlissel\u002Fvibemind-os","https:\u002F\u002Fgithub.com\u002FFlissel","https:\u002F\u002Fvibemind.space","Co-founder & CTO, VibeMind - a voice-first agentic OS for non-technical founders. Agents that do the work, not describe it.","2026-11-15 02:57:54",{"source":8,"skillName":5,"commands":69,"prompt":79,"zipAvailable":59},[70,73,76],{"tool":71,"command":72},"npx","npx skills add Flissel\u002Fvibemind-os --skill openclaw-official-telegram-crabbox-e2e-proof",{"tool":74,"command":75},"bunx","bunx skills add Flissel\u002Fvibemind-os --skill openclaw-official-telegram-crabbox-e2e-proof",{"tool":77,"command":78},"pnpm","pnpm dlx skills add Flissel\u002Fvibemind-os --skill openclaw-official-telegram-crabbox-e2e-proof","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FFlissel\u002Fvibemind-os\u002Fblob\u002Fmaster\u002Fskills\u002Fopenclaw-official\u002Ftelegram-crabbox-e2e-proof\u002FSKILL.md",[],[82,89,96,124,132,146],{"skillNo":83,"name":41,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":45},"01M6JAA67M92TRE7GWDJDBTA9T","Review a change.","https:\u002F\u002Fgithub.com\u002FFlissel\u002Fvibemind-os\u002Fblob\u002Fmaster\u002Fspaces\u002Frowboat\u002Frowboat\u002Fpackages\u002Fopenai-plugin-runtime\u002Ftest\u002Ffixtures\u002Fcomplete-plugin\u002Fskills\u002Freview\u002FSKILL.md",[],[41,88],"change",{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":45},"01M6JAA3DZR55G8ZY493BE9NBB","triage","Triage a change.","https:\u002F\u002Fgithub.com\u002FFlissel\u002Fvibemind-os\u002Fblob\u002Fmaster\u002Fspaces\u002Frowboat\u002Frowboat\u002Fpackages\u002Fopenai-plugin-runtime\u002Ftest\u002Ffixtures\u002Fcomplete-plugin\u002Fskills\u002Fgroup\u002Ftriage\u002FSKILL.md",[],[91,88],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":45},"01M6JA9XPVHENK0FQN7HBK54NV","zentrale-werkzeuge","Werkzeuge der Zentrale – nutzen bei GitHub-Fragen (Projekte updaten, Repos, Issues, PRs, Commits, CI\u002FActions-Status, README), bei Fragen zum eigenen Gitea (Sicherung\u002FSpiegel, Repos, Issues, Commits), wenn neueste Docs\u002FDoku zu einer Bibliothek oder einem Dienst geholt werden sollen, wenn ein Dashboard aus meinen Daten gebaut werden soll und wenn ich sage 'auf meinem PC suchen' oder 'such auf dem Rechner nach …'.","https:\u002F\u002Fgithub.com\u002FFlissel\u002Fvibemind-os\u002Fblob\u002Fmaster\u002Fspaces\u002Frowboat\u002Fdeploy\u002Fheadless\u002Fskills\u002Fzentrale-werkzeuge\u002FSKILL.md",[],[103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123],"zentrale werkzeuge","grep","file","README","list","fetch","todo","gitea","add","URL","mkdir","prs","commits","ci","actions","issues","status","repos","dashboard","github","docs",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":45},"01M6JA9SQPX187CVC148SQT1SP","wissen-suchen","Bedeutungssuche im Rowboat-Wissen – IMMER zuerst nutzen, wenn nach Kunden, Kontakten, Themen, Interessen, Notizen oder 'was wissen wir über …' gefragt wird, besonders wenn die genauen Wörter unklar sind.","https:\u002F\u002Fgithub.com\u002FFlissel\u002Fvibemind-os\u002Fblob\u002Fmaster\u002Fspaces\u002Frowboat\u002Fdeploy\u002Fheadless\u002Fskills\u002Fwissen-suchen\u002FSKILL.md",[],[131],"wissen suchen",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":138,"publishedAt":45},"01M6JA9P6GNFPE21101SDZS3BT","reel-aus-material","Reel aus vorhandenen Laura-Videos: passende Stellen im Transkript finden; spricht dort eine Person, bleibt ihr Originalton (mit Untertiteln aus dem Transkript), sonst trägt ein eingesprochener Satz den Clip. Bei Aufträgen der Art 'material'.","https:\u002F\u002Fgithub.com\u002FFlissel\u002Fvibemind-os\u002Fblob\u002Fmaster\u002Fspaces\u002Fmarketing\u002Fvideo_claw\u002Fskills\u002Freel-aus-material\u002FSKILL.md",[],[139,140,141,142,143,144,145],"material","reel","reel aus material","person","videos","Art","clip",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":152,"publishedAt":45},"01M6JA9KSATRT42ACWT66514ZP","reel-aus-bildern","Reel ohne Filmmaterial: Titelkarte, 3–5 Markenbilder mit wechselnder Bewegung, Schlusskarte mit Handlung; Farben und Logo der Firma. Bei Aufträgen der Art 'bilder'.","https:\u002F\u002Fgithub.com\u002FFlissel\u002Fvibemind-os\u002Fblob\u002Fmaster\u002Fspaces\u002Fmarketing\u002Fvideo_claw\u002Fskills\u002Freel-aus-bildern\u002FSKILL.md",[],[140,153,154,144],"reel aus bildern","logo"]