{
  "schemaVersion": "1.0",
  "item": {
    "slug": "vapi-skill",
    "name": "Vapi Skill",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/colygon/vapi-skill",
    "canonicalUrl": "https://clawhub.ai/colygon/vapi-skill",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/vapi-skill",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=vapi-skill",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md"
    ],
    "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. 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. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "slug": "vapi-skill",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-10T13:19:46.767Z",
      "expiresAt": "2026-05-17T13:19:46.767Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=vapi-skill",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=vapi-skill",
        "contentDisposition": "attachment; filename=\"vapi-skill-0.1.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "vapi-skill"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/vapi-skill"
    },
    "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/vapi-skill",
    "agentPageUrl": "https://openagent3.xyz/skills/vapi-skill/agent",
    "manifestUrl": "https://openagent3.xyz/skills/vapi-skill/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/vapi-skill/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. 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. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Vapi (vapi.ai) — OpenClaw Skill",
        "body": "Use this skill when you need to manage Vapi voice agents (assistants), calls, phone numbers, tools, and webhooks from an OpenClaw agent.\n\nThis skill is API-first (Vapi REST) and optionally integrates with the Vapi CLI for MCP docs / local workflows."
      },
      {
        "title": "What you can do",
        "body": "Create/update/list assistants\nStart/inspect/end calls\nManage phone numbers\nCreate/manage tools (function calling)\nConfigure webhooks and inspect events"
      },
      {
        "title": "Required secrets",
        "body": "Set one of:\n\nVAPI_API_KEY (recommended) — Vapi dashboard API key."
      },
      {
        "title": "How to provide the key (recommended)",
        "body": "Store as a Gateway secret/env var (preferred), or\nExport in your shell before running helper scripts.\n\nNever paste the key into public logs."
      },
      {
        "title": "Endpoints",
        "body": "Base URL:\n\nhttps://api.vapi.ai\n\nAuth:\n\nAuthorization: Bearer $VAPI_API_KEY\n\nAPI reference:\n\nhttps://api.vapi.ai/api (Swagger)"
      },
      {
        "title": "Tooling options",
        "body": "This skill supports both approaches; you can decide later per deployment.\n\nSet VAPI_MODE=api to prefer REST (default)\nSet VAPI_MODE=cli to prefer the Vapi CLI (interactive)"
      },
      {
        "title": "Option A — REST via helper script (works everywhere)",
        "body": "This repo includes a tiny Node helper:\n\nskills/vapi/bin/vapi-api.mjs\n\nExamples:\n\n# list assistants\nVAPI_API_KEY=... node skills/vapi/bin/vapi-api.mjs assistants:list\n\n# create assistant\nVAPI_API_KEY=... node skills/vapi/bin/vapi-api.mjs assistants:create \\\n  --name \"Claw Con Concierge\" \\\n  --modelProvider openai --model gpt-4o-mini \\\n  --voiceProvider 11labs --voiceId rachel\n\n# start an outbound call (example shape; see swagger for required fields)\nVAPI_API_KEY=... node skills/vapi/bin/vapi-api.mjs calls:create \\\n  --assistantId asst_xxx \\\n  --to \"+14155551234\" \\\n  --from \"+14155559876\""
      },
      {
        "title": "Option B — Vapi CLI (good for interactive ops)",
        "body": "If VAPI_MODE=cli, prefer using the CLI for management tasks and fall back to REST if the CLI isn’t installed.\n\nDocs:\n\nhttps://docs.vapi.ai/cli\nhttps://github.com/VapiAI/cli\n\nInstall:\n\ncurl -sSL https://vapi.ai/install.sh | bash\nvapi login"
      },
      {
        "title": "Option C — MCP docs server for your IDE",
        "body": "This improves IDE assistance (Cursor/Windsurf/VSCode):\n\nhttps://docs.vapi.ai/cli/mcp\n\nvapi mcp setup"
      },
      {
        "title": "Agent usage guidance",
        "body": "When the user asks for Vapi changes:\n\nClarify scope: assistants vs phone numbers vs webhooks vs tool calls.\nPrefer read-only queries first (list/get) before destructive changes.\nWhen creating an assistant, ask for:\n\nassistant name\nmodel provider/model\nvoice provider/voice id\ntools/function calling needs\nwebhook URL (if using server events)\n\n\nWhen initiating calls, confirm:\n\nto/from numbers\nassistantId\ncompliance constraints (recording, consent)"
      },
      {
        "title": "Files in this skill",
        "body": "skills/vapi/SKILL.md — this file\nskills/vapi/bin/vapi-api.mjs — minimal REST helper"
      },
      {
        "title": "Sources",
        "body": "Vapi docs intro: https://docs.vapi.ai/quickstart/introduction\nVapi CLI: https://github.com/VapiAI/cli\nVapi MCP: https://docs.vapi.ai/cli/mcp\nVapi API (Swagger): https://api.vapi.ai/api\nExample server (Node): https://github.com/VapiAI/example-server-javascript-node\nOpenClaw: https://github.com/openclaw/openclaw"
      }
    ],
    "body": "Vapi (vapi.ai) — OpenClaw Skill\n\nUse this skill when you need to manage Vapi voice agents (assistants), calls, phone numbers, tools, and webhooks from an OpenClaw agent.\n\nThis skill is API-first (Vapi REST) and optionally integrates with the Vapi CLI for MCP docs / local workflows.\n\nWhat you can do\nCreate/update/list assistants\nStart/inspect/end calls\nManage phone numbers\nCreate/manage tools (function calling)\nConfigure webhooks and inspect events\nRequired secrets\n\nSet one of:\n\nVAPI_API_KEY (recommended) — Vapi dashboard API key.\nHow to provide the key (recommended)\nStore as a Gateway secret/env var (preferred), or\nExport in your shell before running helper scripts.\n\nNever paste the key into public logs.\n\nEndpoints\n\nBase URL:\n\nhttps://api.vapi.ai\n\nAuth:\n\nAuthorization: Bearer $VAPI_API_KEY\n\nAPI reference:\n\nhttps://api.vapi.ai/api (Swagger)\nTooling options\n\nThis skill supports both approaches; you can decide later per deployment.\n\nSet VAPI_MODE=api to prefer REST (default)\nSet VAPI_MODE=cli to prefer the Vapi CLI (interactive)\nOption A — REST via helper script (works everywhere)\n\nThis repo includes a tiny Node helper:\n\nskills/vapi/bin/vapi-api.mjs\n\nExamples:\n\n# list assistants\nVAPI_API_KEY=... node skills/vapi/bin/vapi-api.mjs assistants:list\n\n# create assistant\nVAPI_API_KEY=... node skills/vapi/bin/vapi-api.mjs assistants:create \\\n  --name \"Claw Con Concierge\" \\\n  --modelProvider openai --model gpt-4o-mini \\\n  --voiceProvider 11labs --voiceId rachel\n\n# start an outbound call (example shape; see swagger for required fields)\nVAPI_API_KEY=... node skills/vapi/bin/vapi-api.mjs calls:create \\\n  --assistantId asst_xxx \\\n  --to \"+14155551234\" \\\n  --from \"+14155559876\"\n\nOption B — Vapi CLI (good for interactive ops)\n\nIf VAPI_MODE=cli, prefer using the CLI for management tasks and fall back to REST if the CLI isn’t installed.\n\nDocs:\n\nhttps://docs.vapi.ai/cli\nhttps://github.com/VapiAI/cli\n\nInstall:\n\ncurl -sSL https://vapi.ai/install.sh | bash\nvapi login\n\nOption C — MCP docs server for your IDE\n\nThis improves IDE assistance (Cursor/Windsurf/VSCode):\n\nhttps://docs.vapi.ai/cli/mcp\nvapi mcp setup\n\nAgent usage guidance\n\nWhen the user asks for Vapi changes:\n\nClarify scope: assistants vs phone numbers vs webhooks vs tool calls.\nPrefer read-only queries first (list/get) before destructive changes.\nWhen creating an assistant, ask for:\nassistant name\nmodel provider/model\nvoice provider/voice id\ntools/function calling needs\nwebhook URL (if using server events)\nWhen initiating calls, confirm:\nto/from numbers\nassistantId\ncompliance constraints (recording, consent)\nFiles in this skill\nskills/vapi/SKILL.md — this file\nskills/vapi/bin/vapi-api.mjs — minimal REST helper\nSources\nVapi docs intro: https://docs.vapi.ai/quickstart/introduction\nVapi CLI: https://github.com/VapiAI/cli\nVapi MCP: https://docs.vapi.ai/cli/mcp\nVapi API (Swagger): https://api.vapi.ai/api\nExample server (Node): https://github.com/VapiAI/example-server-javascript-node\nOpenClaw: https://github.com/openclaw/openclaw"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/colygon/vapi-skill",
    "publisherUrl": "https://clawhub.ai/colygon/vapi-skill",
    "owner": "colygon",
    "version": "0.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/vapi-skill",
    "downloadUrl": "https://openagent3.xyz/downloads/vapi-skill",
    "agentUrl": "https://openagent3.xyz/skills/vapi-skill/agent",
    "manifestUrl": "https://openagent3.xyz/skills/vapi-skill/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/vapi-skill/agent.md"
  }
}