{
  "schemaVersion": "1.0",
  "item": {
    "slug": "videochat-withme",
    "name": "Video Chat With Me",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/sxu75374/videochat-withme",
    "canonicalUrl": "https://clawhub.ai/sxu75374/videochat-withme",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/videochat-withme",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=videochat-withme",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "assets/index.html",
      "scripts/call.sh",
      "scripts/server.py",
      "scripts/setup.sh"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/videochat-withme"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/videochat-withme",
    "agentPageUrl": "https://openagent3.xyz/skills/videochat-withme/agent",
    "manifestUrl": "https://openagent3.xyz/skills/videochat-withme/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/videochat-withme/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "videochat-withme",
        "body": "Real-time video call with your OpenClaw agent — full personality, memory, and vision."
      },
      {
        "title": "First-Time Setup",
        "body": "New users run once after installing the skill:\n\nbash skills/videochat-withme/scripts/setup.sh\n\nThis handles everything: dependencies, Groq API key, SSL certs, launchd service."
      },
      {
        "title": "Prerequisites",
        "body": "macOS (launchd required)\nPython 3.10+, ffmpeg\nOpenClaw gateway running with chatCompletions enabled"
      },
      {
        "title": "Groq API Key (required for voice recognition)",
        "body": "Get a free key at: https://console.groq.com/keys\nSave it:\nmkdir -p ~/.openclaw/secrets\necho \"your-key-here\" > ~/.openclaw/secrets/groq_api_key.txt\n\nOr set env var: export GROQ_API_KEY=\"your-key-here\""
      },
      {
        "title": "Enable chatCompletions",
        "body": "Add to ~/.openclaw/openclaw.json:\n\n{\n  \"gateway\": {\n    \"http\": {\n      \"endpoints\": {\n        \"chatCompletions\": { \"enabled\": true }\n      }\n    }\n  }\n}\n\nThen restart OpenClaw."
      },
      {
        "title": "How to Use (Agent Instructions)",
        "body": "When the user requests a video/voice call:\n\nStep 1: Check if service is running:\n\ncurl -sk https://localhost:8766/api/config 2>/dev/null || curl -s http://localhost:8766/api/config 2>/dev/null\n\nStep 2: If no response, setup needed:\n\nCheck Groq key: cat ~/.openclaw/secrets/groq_api_key.txt 2>/dev/null\n\nIf missing, ask user to get one at https://console.groq.com/keys\nSave it: echo \"key\" > ~/.openclaw/secrets/groq_api_key.txt\n\n\nAsk user: \"What name should I display for you in the video call?\"\nRun setup:\nbash skills/videochat-withme/scripts/setup.sh --auto --agent-name \"YourName\" --user-name \"TheirName\"\n\nStep 3: Initiate the call based on context:\n\nDetermine how the user is connecting and pick the best method:\n\nUser is at the computer (message from webchat/desktop):\nbash skills/videochat-withme/scripts/call.sh\n\nThis pops up a macOS incoming call notification → user clicks Accept → browser opens.\n\n\nUser is on mobile/remote (message from Telegram/phone):\nPick the right URL automatically:\n# Prefer Tailscale IP (works from any network)\nTS_IP=$(tailscale ip -4 2>/dev/null)\n# Fallback to local IP (same WiFi only)\nLOCAL_IP=$(python3 -c \"import socket; s=socket.socket(socket.AF_INET,socket.SOCK_DGRAM); s.connect(('8.8.8.8',80)); print(s.getsockname()[0]); s.close()\" 2>/dev/null)\n\n\nIf Tailscale is available → send https://<tailscale-ip>:8766 (works everywhere)\nOtherwise → send https://<local-ip>:8766 (same WiFi only)\nNote: first visit requires tapping \"Advanced → Continue\" (self-signed cert)"
      },
      {
        "title": "Architecture",
        "body": "🎤 Voice → Groq Whisper (STT)\n📷 Camera → base64 frame\n    ↓\nOpenClaw /v1/chat/completions → Your Agent\n    ↓\nedge-tts (TTS) → 🔊 Audio playback"
      },
      {
        "title": "Scripts",
        "body": "Agent runs these automatically:\n\nScriptWhensetup.sh --autoFirst use (service not running)call.shEvery call request\n\nUser can run manually if needed:\n\nScriptPurposesetup.shInteractive setup (without --auto)start.shStart servicestop.shStop service"
      },
      {
        "title": "Configuration",
        "body": "VariableDefaultDescriptionGROQ_API_KEY(secrets file)Groq API key for Whisper STTPORT8766Server portAGENT_NAMEAI AssistantDisplay name for the agentUSER_NAMEUserDisplay name for the userSSL_CERT(auto-detect)Path to SSL certificateSSL_KEY(auto-detect)Path to SSL private key"
      }
    ],
    "body": "videochat-withme\n\nReal-time video call with your OpenClaw agent — full personality, memory, and vision.\n\nFirst-Time Setup\n\nNew users run once after installing the skill:\n\nbash skills/videochat-withme/scripts/setup.sh\n\n\nThis handles everything: dependencies, Groq API key, SSL certs, launchd service.\n\nPrerequisites\nmacOS (launchd required)\nPython 3.10+, ffmpeg\nOpenClaw gateway running with chatCompletions enabled\nGroq API Key (required for voice recognition)\nGet a free key at: https://console.groq.com/keys\nSave it:\nmkdir -p ~/.openclaw/secrets\necho \"your-key-here\" > ~/.openclaw/secrets/groq_api_key.txt\n\nOr set env var: export GROQ_API_KEY=\"your-key-here\"\nEnable chatCompletions\n\nAdd to ~/.openclaw/openclaw.json:\n\n{\n  \"gateway\": {\n    \"http\": {\n      \"endpoints\": {\n        \"chatCompletions\": { \"enabled\": true }\n      }\n    }\n  }\n}\n\n\nThen restart OpenClaw.\n\nHow to Use (Agent Instructions)\n\nWhen the user requests a video/voice call:\n\nStep 1: Check if service is running:\n\ncurl -sk https://localhost:8766/api/config 2>/dev/null || curl -s http://localhost:8766/api/config 2>/dev/null\n\n\nStep 2: If no response, setup needed:\n\nCheck Groq key: cat ~/.openclaw/secrets/groq_api_key.txt 2>/dev/null\nIf missing, ask user to get one at https://console.groq.com/keys\nSave it: echo \"key\" > ~/.openclaw/secrets/groq_api_key.txt\nAsk user: \"What name should I display for you in the video call?\"\nRun setup:\nbash skills/videochat-withme/scripts/setup.sh --auto --agent-name \"YourName\" --user-name \"TheirName\"\n\n\nStep 3: Initiate the call based on context:\n\nDetermine how the user is connecting and pick the best method:\n\nUser is at the computer (message from webchat/desktop):\n\nbash skills/videochat-withme/scripts/call.sh\n\n\nThis pops up a macOS incoming call notification → user clicks Accept → browser opens.\n\nUser is on mobile/remote (message from Telegram/phone): Pick the right URL automatically:\n\n# Prefer Tailscale IP (works from any network)\nTS_IP=$(tailscale ip -4 2>/dev/null)\n# Fallback to local IP (same WiFi only)\nLOCAL_IP=$(python3 -c \"import socket; s=socket.socket(socket.AF_INET,socket.SOCK_DGRAM); s.connect(('8.8.8.8',80)); print(s.getsockname()[0]); s.close()\" 2>/dev/null)\n\nIf Tailscale is available → send https://<tailscale-ip>:8766 (works everywhere)\nOtherwise → send https://<local-ip>:8766 (same WiFi only)\nNote: first visit requires tapping \"Advanced → Continue\" (self-signed cert)\nArchitecture\n🎤 Voice → Groq Whisper (STT)\n📷 Camera → base64 frame\n    ↓\nOpenClaw /v1/chat/completions → Your Agent\n    ↓\nedge-tts (TTS) → 🔊 Audio playback\n\nScripts\n\nAgent runs these automatically:\n\nScript\tWhen\nsetup.sh --auto\tFirst use (service not running)\ncall.sh\tEvery call request\n\nUser can run manually if needed:\n\nScript\tPurpose\nsetup.sh\tInteractive setup (without --auto)\nstart.sh\tStart service\nstop.sh\tStop service\nConfiguration\nVariable\tDefault\tDescription\nGROQ_API_KEY\t(secrets file)\tGroq API key for Whisper STT\nPORT\t8766\tServer port\nAGENT_NAME\tAI Assistant\tDisplay name for the agent\nUSER_NAME\tUser\tDisplay name for the user\nSSL_CERT\t(auto-detect)\tPath to SSL certificate\nSSL_KEY\t(auto-detect)\tPath to SSL private key"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/sxu75374/videochat-withme",
    "publisherUrl": "https://clawhub.ai/sxu75374/videochat-withme",
    "owner": "sxu75374",
    "version": "1.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/videochat-withme",
    "downloadUrl": "https://openagent3.xyz/downloads/videochat-withme",
    "agentUrl": "https://openagent3.xyz/skills/videochat-withme/agent",
    "manifestUrl": "https://openagent3.xyz/skills/videochat-withme/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/videochat-withme/agent.md"
  }
}