[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6J9CT2SSWMS1Y7BC76SAWS3":3,"skill-same:01M6J9CT2SSWMS1Y7BC76SAWS3":93},{"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":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":71,"commitSha":72,"skillDirectory":73,"forksCount":65,"repositoryHtmlUrl":74,"repositoryHomepageUrl":6,"ownerHtmlUrl":75,"ownerBlogUrl":76,"ownerDescription":77,"updatedAt":78,"install":79,"resources":92},"01M6J9CT2SSWMS1Y7BC76SAWS3","openfang-agent-create",null,"Create, configure and manage OpenFang agents via the openfang-agents MCP server. Use when the user asks to spawn, create, build or list OpenFang agents, customize their tools \u002F MCP servers \u002F model \u002F system prompt, or kill a running agent. Triggers on \"create openfang agent\", \"spawn agent\", \"neuen agent bauen\", \"openfang agent anpassen\", \"list agents\", \"agent X starten\", \"build a code-review agent\", \"kill agent \u003Cid>\".","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\u002Fopenfang\u002Fagent-create\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"openfang agent create","create","spawn","new","when","display","system prompt","spawn agent","false","brain","patch","orchestrator","MCP","model","template","configure","server","code-review","code","connect","mcp server","review","2026-11-10 10:12:30",false,"---\nname: openfang-agent-create\ndescription: Create, configure and manage OpenFang agents via the openfang-agents\n  MCP server. Use when the user asks to spawn, create, build or list OpenFang\n  agents, customize their tools \u002F MCP servers \u002F model \u002F system prompt, or kill\n  a running agent. Triggers on \"create openfang agent\", \"spawn agent\", \"neuen\n  agent bauen\", \"openfang agent anpassen\", \"list agents\", \"agent X starten\",\n  \"build a code-review agent\", \"kill agent \u003Cid>\".\napp: openfang\nrequires_approval: false\nagents: ['*']\ninputs:\n  - template: agent template name from vibemind-os\u002Fopenfang\u002Fagents\u002F (e.g. brain-coder,\n      brain-researcher, brain-orchestrator); use openfang_agents_list to see what's running\n  - name: optional new display name override (via openfang_agent_patch after spawn)\n  - model: optional model override, e.g. claude-sonnet-4-20250514, llama-3.1-70b-versatile\n  - tool_allowlist: optional list of tool names the agent may call\n  - mcp_servers: optional list of MCP server names the agent may connect to\nexpected_state:\n  description: target agent is in the openfang_agents_list output with state=Running\n  verification_tool: openfang_agents_list\nconfidence: 0.9\nattempts: 0\nsuccesses: 0\nlast_adjusted: '2026-05-20T00:00:00Z'\n---\n\n# OpenFang Agent Create \u002F Configure\n\nSpawn and customize OpenFang agents from natural language. OpenFang's agent\nregistry is **in-memory** — agents live until the daemon restarts. The 49\ntemplates under `vibemind-os\u002Fopenfang\u002Fagents\u002F*\u002Fagent.toml.tmpl` are the\ntyped starting points; patch + set_tools + set_mcp_servers refine after spawn.\n\nThe dashboard at `http:\u002F\u002F127.0.0.1:4200\u002F` (also embedded as the \"OpenFang\"\nsub-tab in AgentFarm) reflects every change live. After spawning, the new\nagent appears in the dashboard's agent list immediately.\n\n## Available MCP tools\n\nThis skill uses the **openfang-agents** MCP server (registered in `.mcp.json`).\nAll 8 tools wrap `http:\u002F\u002F127.0.0.1:4200\u002Fapi\u002Fagents\u002F*`:\n\n| Tool | When to call |\n|---|---|\n| `openfang_agents_list` | first — see what's already running |\n| `openfang_agent_get` | inspect one agent's full manifest before patching |\n| `openfang_agent_spawn_from_template` | create from a named template |\n| `openfang_agent_spawn_from_toml` | create from a raw TOML manifest (custom config) |\n| `openfang_agent_patch` | rename \u002F change model \u002F change provider in-place |\n| `openfang_agent_set_tools` | restrict callable tools (allow\u002Fblock lists) |\n| `openfang_agent_set_mcp_servers` | restrict which MCP servers the agent may use |\n| `openfang_agent_kill` | terminate + unregister |\n\n## Procedure (5 steps)\n\n1. **Look before you leap.** Call `openfang_agents_list`. If an agent with\n   the requested role already exists and is Running, prefer reusing it\n   (return its id to the user). Avoid duplicates.\n\n2. **Spawn from template.** Prefer `openfang_agent_spawn_from_template`\n   with one of the canonical names — saves writing a TOML from scratch:\n   - `brain-coder` — code editing, builds, file ops\n   - `brain-researcher` — web search + summarization\n   - `brain-knowledge` — KG \u002F Rowboat \u002F Obsidian queries\n   - `brain-orchestrator` — multi-agent coordination\n   - `brain-planner` — task decomposition\n   - `brain-devops` — docker \u002F git \u002F CI ops\n   - `brain-security` — vuln scans\n   - `analyst`, `architect`, `assistant` — general-purpose\n   Capture the returned `agent_id`.\n\n3. **Patch metadata if needed.** Display name, description, model and\n   provider can all change via `openfang_agent_patch` with just the fields\n   you want to set. Skip if the template defaults are fine. System prompt\n   changes require a full respawn (Bewusst nicht in v1).\n\n4. **Restrict capabilities if needed.** For tight sandboxes:\n   - `openfang_agent_set_tools` with `tool_allowlist: [\"file_read\",\"web_fetch\"]`\n     limits the agent to just those tools.\n   - `openfang_agent_set_mcp_servers` with `mcp_servers: [\"fungus-search\"]`\n     restricts which MCP servers the agent may connect to.\n   Skip both if the template defaults (often `\"*\"` \u002F all) are fine.\n\n5. **Verify.** Call `openfang_agent_get` with the new agent_id — confirm\n   state=Running, manifest matches your edits. Then the AgentFarm OpenFang\n   iframe (and the `:4200` dashboard) will show the new agent in its list.\n\n## Beispielfluss\n\n> Erstelle einen Code-Review-Agent basierend auf brain-coder mit fungus-search\n> als MCP-Server.\n\n```\n1. openfang_agents_list\n   → [{id:\"...\", name:\"brain-coder\", state:\"Running\"}, ...]\n   (already one running — but user wants a NEW one for code-review)\n\n2. openfang_agent_spawn_from_template {template: \"brain-coder\"}\n   → {agent_id: \"abc-123\", name: \"brain-coder\"}\n\n3. openfang_agent_patch {agent_id:\"abc-123\", name:\"code-reviewer\",\n                         description:\"Reviews PRs, suggests fixes\"}\n   → {status: \"ok\"}\n\n4. openfang_agent_set_mcp_servers {agent_id:\"abc-123\",\n                                   mcp_servers:[\"fungus-search\"]}\n   → {status: \"ok\"}\n\n5. openfang_agent_get {agent_id:\"abc-123\"}\n   → {name:\"code-reviewer\", state:\"Running\",\n      manifest:{mcp_servers:{servers:[\"fungus-search\"]}, ...}}\n```\n\nDone — der neue Code-Reviewer ist im AgentFarm OpenFang-Tab sichtbar und kann\nüber `POST \u002Fapi\u002Fagents\u002Fabc-123\u002Fmessage` (dashboard chat) angesprochen werden.\n\n## Error handling\n\nEvery MCP tool returns a `TextContent` starting with `error:` on failure —\nnever throws. Typical errors and what to do:\n\n| Error prefix | Cause | Action |\n|---|---|---|\n| `cannot reach OpenFang at ...` | daemon down | tell user to run `Vibemind.debug.ps1 -Modules openfang` or `target\u002Frelease\u002Fopenfang.exe start --config openfang.vibemind.toml`; do NOT silently retry |\n| `OpenFang returned HTTP 404` | bad agent_id or template name | re-list first, suggest a similar name to the user |\n| `OpenFang returned HTTP 400 ...Provide 'tool_allowlist' and\u002For...` | empty set_tools body | warn user, skip the call (don't infinite-loop) |\n| `OpenFang timed out after 60s` | LLM call in spawn took too long (unusual) | suggest a smaller template \u002F different model; once it times out, the agent may have spawned anyway — re-list to check |\n\n## Voice-Pfad\n\nMit `VOICE_BRAIN_MULTIHOP=true` in `.env` routet die Voice-Pipeline „erstelle\neinen openfang agent für X\" durch dieselbe Capability und denselben MCP-Pfad\nwie Claude Code — keine separate Tool-Registry-Pflege nötig. Der Pfad:\n\n```\nvoice → brain (\u002Fapi\u002Fmultihop\u002Fexecute) → cap (openfang_agent_create)\n      → MCPExecutor → openfang-agents stdio → :4200\u002Fapi\u002Fagents → Agent läuft\n```\n\nBrain's Phase -2 (BrainMultihopBridge in `vibemind-os\u002Fvoice\u002Fpython\u002Fswarm\u002Frouting\u002F`)\nruft `\u002Fapi\u002Fmultihop\u002Fexecute` mit dem rohen Intent-Text auf; bei No-Match\nfällt sie sauber auf Phase -1 (cortex\u002Froute → Space) durch.\n\n## Bewusst NICHT in dieser Skill-Version\n\n- System-prompt change at runtime — needs `PUT \u002Fapi\u002Fagents\u002F{id}\u002Fupdate` + full\n  respawn cycle; out of Builder-Fokus scope.\n- Session management — handled by the `:4200` dashboard \u002F AgentFarm-iframe.\n- Sending messages to an agent (`POST \u002Fapi\u002Fagents\u002F{id}\u002Fmessage`) — that's the\n  user's job via dashboard\u002Fiframe or a separate skill (e.g. rowboat_chat\n  equivalent). This skill builds & configures only.\n# fungus-hook-v6-1779358492\n","# OpenFang Agent Create \u002F Configure\n\nSpawn and customize OpenFang agents from natural language. OpenFang's agent\nregistry is **in-memory** — agents live until the daemon restarts. The 49\ntemplates under `vibemind-os\u002Fopenfang\u002Fagents\u002F*\u002Fagent.toml.tmpl` are the\ntyped starting points; patch + set_tools + set_mcp_servers refine after spawn.\n\nThe dashboard at `http:\u002F\u002F127.0.0.1:4200\u002F` (also embedded as the \"OpenFang\"\nsub-tab in AgentFarm) reflects every change live. After spawning, the new\nagent appears in the dashboard's agent list immediately.\n\n## Available MCP tools\n\nThis skill uses the **openfang-agents** MCP server (registered in `.mcp.json`).\nAll 8 tools wrap `http:\u002F\u002F127.0.0.1:4200\u002Fapi\u002Fagents\u002F*`:\n\n| Tool | When to call |\n|---|---|\n| `openfang_agents_list` | first — see what's already running |\n| `openfang_agent_get` | inspect one agent's full manifest before patching |\n| `openfang_agent_spawn_from_template` | create from a named template |\n| `openfang_agent_spawn_from_toml` | create from a raw TOML manifest (custom config) |\n| `openfang_agent_patch` | rename \u002F change model \u002F change provider in-place |\n| `openfang_agent_set_tools` | restrict callable tools (allow\u002Fblock lists) |\n| `openfang_agent_set_mcp_servers` | restrict which MCP servers the agent may use |\n| `openfang_agent_kill` | terminate + unregister |\n\n## Procedure (5 steps)\n\n1. **Look before you leap.** Call `openfang_agents_list`. If an agent with\n   the requested role already exists and is Running, prefer reusing it\n   (return its id to the user). Avoid duplicates.\n\n2. **Spawn from template.** Prefer `openfang_agent_spawn_from_template`\n   with one of the canonical names — saves writing a TOML from scratch:\n   - `brain-coder` — code editing, builds, file ops\n   - `brain-researcher` — web search + summarization\n   - `brain-knowledge` — KG \u002F Rowboat \u002F Obsidian queries\n   - `brain-orchestrator` — multi-agent coordination\n   - `brain-planner` — task decomposition\n   - `brain-devops` — docker \u002F git \u002F CI ops\n   - `brain-security` — vuln scans\n   - `analyst`, `architect`, `assistant` — general-purpose\n   Capture the returned `agent_id`.\n\n3. **Patch metadata if needed.** Display name, description, model and\n   provider can all change via `openfang_agent_patch` with just the fields\n   you want to set. Skip if the template defaults are fine. System prompt\n   changes require a full respawn (Bewusst nicht in v1).\n\n4. **Restrict capabilities if needed.** For tight sandboxes:\n   - `openfang_agent_set_tools` with `tool_allowlist: [\"file_read\",\"web_fetch\"]`\n     limits the agent to just those tools.\n   - `openfang_agent_set_mcp_servers` with `mcp_servers: [\"fungus-search\"]`\n     restricts which MCP servers the agent may connect to.\n   Skip both if the template defaults (often `\"*\"` \u002F all) are fine.\n\n5. **Verify.** Call `openfang_agent_get` with the new agent_id — confirm\n   state=Running, manifest matches your edits. Then the AgentFarm OpenFang\n   iframe (and the `:4200` dashboard) will show the new agent in its list.\n\n## Beispielfluss\n\n> Erstelle einen Code-Review-Agent basierend auf brain-coder mit fungus-search\n> als MCP-Server.\n\n```\n1. openfang_agents_list\n   → [{id:\"...\", name:\"brain-coder\", state:\"Running\"}, ...]\n   (already one running — but user wants a NEW one for code-review)\n\n2. openfang_agent_spawn_from_template {template: \"brain-coder\"}\n   → {agent_id: \"abc-123\", name: \"brain-coder\"}\n\n3. openfang_agent_patch {agent_id:\"abc-123\", name:\"code-reviewer\",\n                         description:\"Reviews PRs, suggests fixes\"}\n   → {status: \"ok\"}\n\n4. openfang_agent_set_mcp_servers {agent_id:\"abc-123\",\n                                   mcp_servers:[\"fungus-search\"]}\n   → {status: \"ok\"}\n\n5. openfang_agent_get {agent_id:\"abc-123\"}\n   → {name:\"code-reviewer\", state:\"Running\",\n      manifest:{mcp_servers:{servers:[\"fungus-search\"]}, ...}}\n```\n\nDone — der neue Code-Reviewer ist im AgentFarm OpenFang-Tab sichtbar und kann\nüber `POST \u002Fapi\u002Fagents\u002Fabc-123\u002Fmessage` (dashboard chat) angesprochen werden.\n\n## Error handling\n\nEvery MCP tool returns a `TextContent` starting with `error:` on failure —\nnever throws. Typical errors and what to do:\n\n| Error prefix | Cause | Action |\n|---|---|---|\n| `cannot reach OpenFang at ...` | daemon down | tell user to run `Vibemind.debug.ps1 -Modules openfang` or `target\u002Frelease\u002Fopenfang.exe start --config openfang.vibemind.toml`; do NOT silently retry |\n| `OpenFang returned HTTP 404` | bad agent_id or template name | re-list first, suggest a similar name to the user |\n| `OpenFang returned HTTP 400 ...Provide 'tool_allowlist' and\u002For...` | empty set_tools body | warn user, skip the call (don't infinite-loop) |\n| `OpenFang timed out after 60s` | LLM call in spawn took too long (unusual) | suggest a smaller template \u002F different model; once it times out, the agent may have spawned anyway — re-list to check |\n\n## Voice-Pfad\n\nMit `VOICE_BRAIN_MULTIHOP=true` in `.env` routet die Voice-Pipeline „erstelle\neinen openfang agent für X\" durch dieselbe Capability und denselben MCP-Pfad\nwie Claude Code — keine separate Tool-Registry-Pflege nötig. Der Pfad:\n\n```\nvoice → brain (\u002Fapi\u002Fmultihop\u002Fexecute) → cap (openfang_agent_create)\n      → MCPExecutor → openfang-agents stdio → :4200\u002Fapi\u002Fagents → Agent läuft\n```\n\nBrain's Phase -2 (BrainMultihopBridge in `vibemind-os\u002Fvoice\u002Fpython\u002Fswarm\u002Frouting\u002F`)\nruft `\u002Fapi\u002Fmultihop\u002Fexecute` mit dem rohen Intent-Text auf; bei No-Match\nfällt sie sauber auf Phase -1 (cortex\u002Froute → Space) durch.\n\n## Bewusst NICHT in dieser Skill-Version\n\n- System-prompt change at runtime — needs `PUT \u002Fapi\u002Fagents\u002F{id}\u002Fupdate` + full\n  respawn cycle; out of Builder-Fokus scope.\n- Session management — handled by the `:4200` dashboard \u002F AgentFarm-iframe.\n- Sending messages to an agent (`POST \u002Fapi\u002Fagents\u002F{id}\u002Fmessage`) — that's the\n  user's job via dashboard\u002Fiframe or a separate skill (e.g. rowboat_chat\n  equivalent). This skill builds & configures only.\n# fungus-hook-v6-1779358492\n",{"app":51,"name":5,"agents":52,"inputs":54,"attempts":65,"successes":65,"confidence":66,"description":7,"last_adjusted":67,"expected_state":68,"requires_approval":47},"openfang",[53],"*",[55,57,59,61,63],{"template":56},"agent template name from vibemind-os\u002Fopenfang\u002Fagents\u002F (e.g. brain-coder, brain-researcher, brain-orchestrator); use openfang_agents_list to see what's running",{"name":58},"optional new display name override (via openfang_agent_patch after spawn)",{"model":60},"optional model override, e.g. claude-sonnet-4-20250514, llama-3.1-70b-versatile",{"tool_allowlist":62},"optional list of tool names the agent may call",{"mcp_servers":64},"optional list of MCP server names the agent may connect to",0,0.9,"2026-05-20T00:00:00Z",{"description":69,"verification_tool":70},"target agent is in the openfang_agents_list output with state=Running","openfang_agents_list","master","5f13b5d2b532c0ab6f847e3aa24d4bfe66f7d461","skills\u002Fopenfang\u002Fagent-create","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.","2026-11-11 05:34:01",{"source":8,"skillName":5,"commands":80,"prompt":90,"zipAvailable":91},[81,84,87],{"tool":82,"command":83},"npx","npx skills add Flissel\u002Fvibemind-os --skill openfang-agent-create",{"tool":85,"command":86},"bunx","bunx skills add Flissel\u002Fvibemind-os --skill openfang-agent-create",{"tool":88,"command":89},"pnpm","pnpm dlx skills add Flissel\u002Fvibemind-os --skill openfang-agent-create","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FFlissel\u002Fvibemind-os\u002Fblob\u002Fmaster\u002Fskills\u002Fopenfang\u002Fagent-create\u002FSKILL.md",true,[],[94,101,108,136,144,158],{"skillNo":95,"name":45,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":46},"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",[],[45,100],"change",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":46},"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",[],[103,100],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":46},"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",[],[115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135],"zentrale werkzeuge","grep","file","README","list","fetch","todo","gitea","add","URL","mkdir","prs","commits","ci","actions","issues","status","repos","dashboard","github","docs",{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":46},"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",[],[143],"wissen suchen",{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":150,"publishedAt":46},"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",[],[151,152,153,154,155,156,157],"material","reel","reel aus material","person","videos","Art","clip",{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":164,"publishedAt":46},"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",[],[152,165,166,156],"reel aus bildern","logo"]