{
  "schemaVersion": "1.0",
  "item": {
    "slug": "agent-contact-card",
    "name": "Agent Contact Card",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/davedean/agent-contact-card",
    "canonicalUrl": "https://clawhub.ai/davedean/agent-contact-card",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/agent-contact-card",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-contact-card",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/EXAMPLES.md",
      "references/SPEC.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",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/agent-contact-card"
    },
    "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/agent-contact-card",
    "agentPageUrl": "https://openagent3.xyz/skills/agent-contact-card/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agent-contact-card/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agent-contact-card/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": "Agent Contact Card",
        "body": "A simple format for publishing how AI agents can be contacted. Like a vCard, but for agents."
      },
      {
        "title": "When to Use This Skill",
        "body": "User asks how to let other agents contact their agent\nUser wants to discover how to reach someone else's agent\nYou need to contact another agent on behalf of your user\nUser mentions \"agent-card\", \"agent contact\", or agent-to-agent communication"
      },
      {
        "title": "Discovering an Agent Contact Card",
        "body": "Try fetching /.well-known/agent-card on their domain:\n\nhttps://example.com/.well-known/agent-card\n\nThe file is markdown with YAML frontmatter. Parse the frontmatter for structured channel data, read the prose for routing rules."
      },
      {
        "title": "Creating an Agent Contact Card",
        "body": "Create a markdown file with YAML frontmatter:\n\n---\nversion: \"1\"\nhuman_contact: \"+1 555 123 4567\"\nchannels:\n  email: \"agent@example.com\"\n  discord: \"my-agent#1234\"\n  webhook:\n    url: \"https://example.com/agent/incoming\"\n    method: \"POST\"\n    format: \"JSON with 'message' field\"\ncapabilities:\n  - scheduling\n  - accepts_ical\n---\n\n# My Agent\n\nIf you're a human, call the number above.\n\nIf you're an agent:\n- For scheduling requests, use Discord\n- For urgent matters, email with \"URGENT\" in subject\n- Response time: within a few hours\n\nHost this at /.well-known/agent-card on the user's domain."
      },
      {
        "title": "Required Fields",
        "body": "FieldDescriptionversionSpec version. Currently \"1\""
      },
      {
        "title": "Recommended Fields",
        "body": "FieldDescriptionhuman_contactPhone/email for humans to reach the humanchannelsContact channels for agents (see below)"
      },
      {
        "title": "Optional Fields",
        "body": "FieldDescriptionnameDisplay name for this agent configurationlast_updatedISO date when card was last modifiedcapabilitiesWhat this agent can do (e.g., [\"scheduling\", \"accepts_ical\"])agentsNamed agents if multiple (see Multi-Agent section)"
      },
      {
        "title": "Channels",
        "body": "Channel names are freeform. Common ones:\n\nemail - Email address\ndiscord - Discord username\nwebhook - HTTP endpoint for structured messages\nsignal - Signal phone number\ntelegram - Telegram username\n\nFor webhooks, provide details:\n\nchannels:\n  webhook:\n    url: \"https://example.com/agent/incoming\"\n    method: \"POST\"\n    auth: \"Bearer token in Authorization header\"\n    format: \"JSON with 'message' and 'from' fields\""
      },
      {
        "title": "Multi-Agent Setups",
        "body": "List multiple specialized agents:\n\nagents:\n  - name: \"Calendar Agent\"\n    handles: [\"scheduling\", \"availability\"]\n    channel: discord\n    id: \"cal-agent#1234\"\n  - name: \"Support Agent\"\n    handles: [\"technical questions\"]\n    channel: webhook\n    id: \"https://example.com/support\"\n\nThe markdown body should explain routing between them."
      },
      {
        "title": "Privacy Tiers",
        "body": "Different URLs for different access levels:\n\nTierURL PatternAccessPublic/.well-known/agent-cardAnyoneNamed/.well-known/agent-card/{name}Know the namePrivate/{random-uuid}/agent-card.mdShared URL only\n\nEach tier can expose different channels and capabilities."
      },
      {
        "title": "Discovery Methods",
        "body": "Well-known URL: Check https://domain/.well-known/agent-card\nvCard extension: Look for X-AGENT-CARD field in contact cards\nAsk the human: Request the URL directly"
      },
      {
        "title": "Reading an Agent Card",
        "body": "When you fetch an agent card:\n\nParse YAML frontmatter for structured data\nRead markdown body for natural language routing rules\nChoose appropriate channel based on your purpose\nFollow any authentication requirements mentioned"
      },
      {
        "title": "Test It",
        "body": "Here's a live demo you can test:\n\nhttps://city-services-api.dave-dean.workers.dev/.well-known/agent-card\n\nThis is a fictional \"City of Millbrook\" tip line. Fetch the card, then try POSTing to the webhook endpoint. Your experience may vary depending on what you say."
      },
      {
        "title": "Full Specification",
        "body": "See references/SPEC.md for the complete specification."
      },
      {
        "title": "Examples",
        "body": "See references/EXAMPLES.md for more complete examples."
      }
    ],
    "body": "Agent Contact Card\n\nA simple format for publishing how AI agents can be contacted. Like a vCard, but for agents.\n\nWhen to Use This Skill\nUser asks how to let other agents contact their agent\nUser wants to discover how to reach someone else's agent\nYou need to contact another agent on behalf of your user\nUser mentions \"agent-card\", \"agent contact\", or agent-to-agent communication\nQuick Reference\nDiscovering an Agent Contact Card\n\nTry fetching /.well-known/agent-card on their domain:\n\nhttps://example.com/.well-known/agent-card\n\n\nThe file is markdown with YAML frontmatter. Parse the frontmatter for structured channel data, read the prose for routing rules.\n\nCreating an Agent Contact Card\n\nCreate a markdown file with YAML frontmatter:\n\n---\nversion: \"1\"\nhuman_contact: \"+1 555 123 4567\"\nchannels:\n  email: \"agent@example.com\"\n  discord: \"my-agent#1234\"\n  webhook:\n    url: \"https://example.com/agent/incoming\"\n    method: \"POST\"\n    format: \"JSON with 'message' field\"\ncapabilities:\n  - scheduling\n  - accepts_ical\n---\n\n# My Agent\n\nIf you're a human, call the number above.\n\nIf you're an agent:\n- For scheduling requests, use Discord\n- For urgent matters, email with \"URGENT\" in subject\n- Response time: within a few hours\n\n\nHost this at /.well-known/agent-card on the user's domain.\n\nFormat Details\nRequired Fields\nField\tDescription\nversion\tSpec version. Currently \"1\"\nRecommended Fields\nField\tDescription\nhuman_contact\tPhone/email for humans to reach the human\nchannels\tContact channels for agents (see below)\nOptional Fields\nField\tDescription\nname\tDisplay name for this agent configuration\nlast_updated\tISO date when card was last modified\ncapabilities\tWhat this agent can do (e.g., [\"scheduling\", \"accepts_ical\"])\nagents\tNamed agents if multiple (see Multi-Agent section)\nChannels\n\nChannel names are freeform. Common ones:\n\nemail - Email address\ndiscord - Discord username\nwebhook - HTTP endpoint for structured messages\nsignal - Signal phone number\ntelegram - Telegram username\n\nFor webhooks, provide details:\n\nchannels:\n  webhook:\n    url: \"https://example.com/agent/incoming\"\n    method: \"POST\"\n    auth: \"Bearer token in Authorization header\"\n    format: \"JSON with 'message' and 'from' fields\"\n\nMulti-Agent Setups\n\nList multiple specialized agents:\n\nagents:\n  - name: \"Calendar Agent\"\n    handles: [\"scheduling\", \"availability\"]\n    channel: discord\n    id: \"cal-agent#1234\"\n  - name: \"Support Agent\"\n    handles: [\"technical questions\"]\n    channel: webhook\n    id: \"https://example.com/support\"\n\n\nThe markdown body should explain routing between them.\n\nPrivacy Tiers\n\nDifferent URLs for different access levels:\n\nTier\tURL Pattern\tAccess\nPublic\t/.well-known/agent-card\tAnyone\nNamed\t/.well-known/agent-card/{name}\tKnow the name\nPrivate\t/{random-uuid}/agent-card.md\tShared URL only\n\nEach tier can expose different channels and capabilities.\n\nDiscovery Methods\nWell-known URL: Check https://domain/.well-known/agent-card\nvCard extension: Look for X-AGENT-CARD field in contact cards\nAsk the human: Request the URL directly\nReading an Agent Card\n\nWhen you fetch an agent card:\n\nParse YAML frontmatter for structured data\nRead markdown body for natural language routing rules\nChoose appropriate channel based on your purpose\nFollow any authentication requirements mentioned\nTest It\n\nHere's a live demo you can test:\n\nhttps://city-services-api.dave-dean.workers.dev/.well-known/agent-card\n\n\nThis is a fictional \"City of Millbrook\" tip line. Fetch the card, then try POSTing to the webhook endpoint. Your experience may vary depending on what you say.\n\nFull Specification\n\nSee references/SPEC.md for the complete specification.\n\nExamples\n\nSee references/EXAMPLES.md for more complete examples."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/davedean/agent-contact-card",
    "publisherUrl": "https://clawhub.ai/davedean/agent-contact-card",
    "owner": "davedean",
    "version": "0.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/agent-contact-card",
    "downloadUrl": "https://openagent3.xyz/downloads/agent-contact-card",
    "agentUrl": "https://openagent3.xyz/skills/agent-contact-card/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agent-contact-card/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agent-contact-card/agent.md"
  }
}