{"skill":{"slug":"elevenlabs-agents-1-0-0","displayName":"Elevenlabs Agents 1.0.0","summary":"Create, manage, and deploy ElevenLabs conversational AI agents. Use when the user wants to work with voice agents, list their agents, create new ones, or man...","description":"---\nname: elevenlabs-agents\ndescription: Create, manage, and deploy ElevenLabs conversational AI agents. Use when the user wants to work with voice agents, list their agents, create new ones, or manage agent configurations.\nmetadata: {\"clawdbot\":{\"requires\":{\"bins\":[\"elevenlabs\"]}}}\n---\n\n# ElevenLabs Agents Management\n\nManage ElevenLabs conversational AI agents on behalf of the user. Use the `elevenlabs` CLI internally but NEVER expose CLI commands or errors directly to the user.\n\n## Critical Behavior Rules\n\n1. **Hide CLI details**: Never tell users to run commands. Handle everything silently.\n2. **Handle errors gracefully**: If a command fails, fix it yourself or explain the situation in user-friendly terms.\n3. **Local vs Remote distinction**: Always be clear whether you're showing local (synced) agents or remote (platform) agents.\n\n## Before Any Operation\n\nRun these checks silently before attempting any agent operation:\n\n### 1. Check authentication\n```bash\nelevenlabs auth whoami\n```\nIf not authenticated, tell the user: \"You're not logged into ElevenLabs. I'll need your API key to continue.\" Then run `elevenlabs auth login` and guide them through it.\n\n### 2. Check project initialization\nLook for `agents.json` in the working directory. If missing, silently run:\n```bash\nelevenlabs agents init\n```\nNever tell the user about missing `agents.json` - just initialize.\n\n## Operations\n\n### Listing Agents\n\nWhen user asks to see their agents:\n\n1. First try `elevenlabs agents list` (shows local agents)\n2. If no local agents exist, tell user: \"You have no local agents synced. Would you like me to pull your agents from ElevenLabs?\"\n3. If they confirm, run `elevenlabs agents pull` then list again\n4. Present results in a clean table/list format, not raw CLI output\n\n### Creating Agents\n\nWhen user wants to create an agent:\n\n1. Ask for agent name and purpose (don't mention \"templates\")\n2. Based on their description, choose appropriate template:\n   - Customer support → `customer-service`\n   - General assistant → `assistant`\n   - Voice-focused → `voice-only`\n   - Simple/minimal → `minimal`\n   - Default for unclear cases → `default`\n3. Run: `elevenlabs agents add \"Name\" --template <template>`\n4. Inform user the agent was created locally\n5. Ask: \"Would you like me to deploy this to ElevenLabs now?\"\n6. If yes, run `elevenlabs agents push`\n\n### Syncing Agents\n\n**Pull (remote → local):**\n```bash\nelevenlabs agents pull                    # all agents\nelevenlabs agents pull --agent <id>       # specific agent\nelevenlabs agents pull --update           # overwrite local with remote\n```\nTell user: \"I've synced your agents from ElevenLabs.\"\n\n**Push (local → remote):**\n```bash\nelevenlabs agents push --dry-run  # preview first, check for issues\nelevenlabs agents push            # actual push\n```\nTell user: \"I've deployed your changes to ElevenLabs.\"\n\n### Checking Status\n\n```bash\nelevenlabs agents status\n```\nPresent as: \"Here's the sync status of your agents:\" followed by a clean summary.\n\n### Adding Tools to Agents\n\nWhen user wants to add integrations/tools:\n1. Ask what the tool should do\n2. Ask for the webhook URL or configuration\n3. Create config file and run:\n```bash\nelevenlabs agents tools add \"Tool Name\" --type webhook --config-path ./config.json\n```\n4. Push changes: `elevenlabs agents push`\n\n### Getting Embed Code\n\n```bash\nelevenlabs agents widget <agent_id>\n```\nPresent the HTML snippet cleanly, explain where to paste it.\n\n## User-Friendly Language\n\n| Instead of saying... | Say... |\n|---------------------|--------|\n| \"Run `elevenlabs auth login`\" | \"I'll need to connect to your ElevenLabs account.\" |\n| \"No agents.json found\" | (silently initialize, say nothing) |\n| \"Push failed\" | \"I couldn't deploy the changes. Let me check what went wrong...\" |\n| \"You have 0 agents\" | \"You don't have any agents synced locally. Want me to check ElevenLabs for existing agents?\" |\n| \"Agent created locally\" | \"I've created your agent. Would you like to deploy it now?\" |\n\n## Project Files (internal reference)\n\nAfter initialization, the working directory contains:\n- `agents.json` - Agent registry\n- `agent_configs/` - Agent configuration files\n- `tools.json` - Tool registry\n- `tool_configs/` - Tool configurations\n\nThese are implementation details - don't mention them to users unless they specifically ask about project structure.\n","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":778,"installsAllTime":29,"installsCurrent":1,"stars":0,"versions":1},"createdAt":1772467093308,"updatedAt":1778994588079},"latestVersion":{"version":"1.0.0","createdAt":1772467093308,"changelog":"Initial release of ElevenLabs Agents Management skill.\n\n- Allows users to create, manage, and deploy conversational AI agents with ElevenLabs.\n- Supports listing local and remote agents, agent creation, deployment, and syncing.\n- Guides users through authentication and project setup seamlessly.\n- Provides user-friendly messaging and abstracts away command-line details.\n- Enables tool integration and sharing agent embed codes in a simple, guided manner.","license":null},"metadata":{"setup":[],"os":null,"systems":null},"owner":{"handle":"sieyer","userId":"s17ecg755jc4ww7frdpfdkdtbn83g8r9","displayName":"Sieyer","image":"https://avatars.githubusercontent.com/u/68283443?v=4"},"moderation":{"isSuspicious":false,"isMalwareBlocked":false,"verdict":"clean","reasonCodes":["review.llm_review"],"summary":"Review: review.llm_review","engineVersion":"v2.4.24","updatedAt":1780089738649}}