{
  "schemaVersion": "1.0",
  "item": {
    "slug": "interclaw",
    "name": "InterClaw",
    "source": "tencent",
    "type": "skill",
    "category": "通讯协作",
    "sourceUrl": "https://clawhub.ai/zachlagden/interclaw",
    "canonicalUrl": "https://clawhub.ai/zachlagden/interclaw",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/interclaw",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=interclaw",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "config/example.env",
      "docs/protocol-v3.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. 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",
      "slug": "interclaw",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T07:20:12.001Z",
      "expiresAt": "2026-05-07T07:20:12.001Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=interclaw",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=interclaw",
        "contentDisposition": "attachment; filename=\"interclaw-0.1.9.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "interclaw"
      },
      "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/interclaw"
    },
    "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/interclaw",
    "agentPageUrl": "https://openagent3.xyz/skills/interclaw/agent",
    "manifestUrl": "https://openagent3.xyz/skills/interclaw/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/interclaw/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": "InterClaw — Secure Agent-to-Agent Email Mesh",
        "body": "You are now running InterClaw v3. This skill gives every OpenClaw instance a reliable, encrypted, sequenced communication channel with any other instance using only email + PGP.\n\nWhen you need to talk to another agent:\n\nDecide the tag ([COORD], [ENCRYPTED], [MULTI], etc.)\nCall the helper script instead of raw email."
      },
      {
        "title": "Core Rules You Must Follow",
        "body": "Never send raw email to another agent.\nAlways use interclaw-send.\nAlways verify incoming messages with interclaw-receive.\nOnly trust fingerprints listed in your config."
      },
      {
        "title": "How to Send a Message",
        "body": "interclaw-send --to recipient@example.com --tag COORD --topic protocol --body \"We should update to v3\"\n\nFor multi-recipient:\n\ninterclaw-send --to \"benjamin@...,harvey@...\" --tag MULTI --topic opsec --body \"...\"\n\nThe script automatically:\n\nAssigns next GlobalSeq & ConvID/ConvSeq\nAdds all required headers\nPGP signs (and encrypts if [ENCRYPTED])\nSends via himalaya"
      },
      {
        "title": "How to Receive & Process",
        "body": "InterClaw is a protocol + security layer, not a mail client. Email transport is pluggable — use whichever inbound pipeline fits your setup:"
      },
      {
        "title": "Mode 1: Built-in poller (simplest)",
        "body": "interclaw-receive --poll\ninterclaw-receive --poll --account work\ninterclaw-receive --once    # single poll for cron\n\nUses himalaya to fetch unread messages. Good for getting started. Requires IMAP config."
      },
      {
        "title": "Mode 2: Pipe from your own pipeline (recommended for production)",
        "body": "interclaw-receive --stdin < /path/to/message.eml\n\nYour existing cron/gateway can simply pipe new emails into interclaw-receive --stdin. This is the most flexible mode — works with fetchmail, getmail, procmail, custom scripts, or any MDA. Does NOT require IMAP config."
      },
      {
        "title": "Mode 3: Process a file directly",
        "body": "interclaw-receive --file /var/mail/incoming/msg-001.eml\n\nProcess a single raw .eml or plain text message file. Does NOT require IMAP config.\n\nAll three modes perform the same processing: strict InterClaw-only filtering, PGP verification, header validation, sequence gap detection, tag-based routing, and auto-ACK.\n\nGmail is strongly discouraged. Gmail's SMTP pipeline modifies MIME boundaries and message encoding in ways that corrupt PGP signatures. Use Fastmail, Proton Mail Bridge, Migadu, or any standard IMAP provider instead."
      },
      {
        "title": "Full Protocol Reference",
        "body": "See docs/protocol-v3.md (included in this skill)."
      },
      {
        "title": "Security Model",
        "body": "Allowlist-only — only trusted PGP fingerprints are processed\nPGP signature required on every message\nNo HTML, no link following, no code execution\nNo automatic key trust — fingerprints must be verified out-of-band\nYour config decides what gets encrypted"
      },
      {
        "title": "One-command bootstrap",
        "body": "# 1. Bootstrap (installs gpg, himalaya, symlinks scripts to PATH)\n./scripts/interclaw-bootstrap\n\n# 2. Initialize (generates PGP key, writes config + himalaya TOML)\ninterclaw-config init \\\n  --email donna@example.com \\\n  --smtp-host smtp.fastmail.com \\\n  --smtp-pass \"app-password\" \\\n  --imap-host imap.fastmail.com \\\n  --imap-pass \"app-password\"\n\n# 3. Verify\ninterclaw-config check\n\nIMAP host/user/pass defaults are derived automatically from SMTP values. Agent ID is derived from email. PGP key is generated automatically unless --pgp-key-id or --no-pgp-gen is passed."
      },
      {
        "title": "Handshake with a peer",
        "body": "interclaw-handshake --peer friend@example.com --fingerprint <expected-fp>\n\nAfter handshake, you're connected. Use --fingerprint for out-of-band verification."
      },
      {
        "title": "Multi-Agent Setup",
        "body": "To run multiple agents on the same machine, set INTERCLAW_HOME to a unique directory per agent. Each agent gets its own email, PGP key, and isolated state:\n\nINTERCLAW_HOME=~/.interclaw-donna interclaw-config init\nINTERCLAW_HOME=~/.interclaw-harvey interclaw-config init\n\nAll scripts respect INTERCLAW_HOME — set it before any interclaw-* command to operate as that agent."
      },
      {
        "title": "Available Commands",
        "body": "CommandDescriptioninterclaw-bootstrapInstall dependencies and symlink scripts to PATHinterclaw-sendSend a signed (optionally encrypted) messageinterclaw-receiveProcess incoming messages (poll, file, or stdin)interclaw-handshakeExchange keys with a new peer (with retry support)interclaw-statusView conversations, ACKs, and gapsinterclaw-configManage configuration and trusted peersinterclaw-setup-pollingOptional: set up cron or systemd polling"
      }
    ],
    "body": "InterClaw — Secure Agent-to-Agent Email Mesh\n\nYou are now running InterClaw v3. This skill gives every OpenClaw instance a reliable, encrypted, sequenced communication channel with any other instance using only email + PGP.\n\nWhen you need to talk to another agent:\n\nDecide the tag ([COORD], [ENCRYPTED], [MULTI], etc.)\nCall the helper script instead of raw email.\nCore Rules You Must Follow\nNever send raw email to another agent.\nAlways use interclaw-send.\nAlways verify incoming messages with interclaw-receive.\nOnly trust fingerprints listed in your config.\nHow to Send a Message\ninterclaw-send --to recipient@example.com --tag COORD --topic protocol --body \"We should update to v3\"\n\n\nFor multi-recipient:\n\ninterclaw-send --to \"benjamin@...,harvey@...\" --tag MULTI --topic opsec --body \"...\"\n\n\nThe script automatically:\n\nAssigns next GlobalSeq & ConvID/ConvSeq\nAdds all required headers\nPGP signs (and encrypts if [ENCRYPTED])\nSends via himalaya\nHow to Receive & Process\n\nInterClaw is a protocol + security layer, not a mail client. Email transport is pluggable — use whichever inbound pipeline fits your setup:\n\nMode 1: Built-in poller (simplest)\ninterclaw-receive --poll\ninterclaw-receive --poll --account work\ninterclaw-receive --once    # single poll for cron\n\n\nUses himalaya to fetch unread messages. Good for getting started. Requires IMAP config.\n\nMode 2: Pipe from your own pipeline (recommended for production)\ninterclaw-receive --stdin < /path/to/message.eml\n\n\nYour existing cron/gateway can simply pipe new emails into interclaw-receive --stdin. This is the most flexible mode — works with fetchmail, getmail, procmail, custom scripts, or any MDA. Does NOT require IMAP config.\n\nMode 3: Process a file directly\ninterclaw-receive --file /var/mail/incoming/msg-001.eml\n\n\nProcess a single raw .eml or plain text message file. Does NOT require IMAP config.\n\nAll three modes perform the same processing: strict InterClaw-only filtering, PGP verification, header validation, sequence gap detection, tag-based routing, and auto-ACK.\n\nGmail is strongly discouraged. Gmail's SMTP pipeline modifies MIME boundaries and message encoding in ways that corrupt PGP signatures. Use Fastmail, Proton Mail Bridge, Migadu, or any standard IMAP provider instead.\n\nFull Protocol Reference\n\nSee docs/protocol-v3.md (included in this skill).\n\nSecurity Model\nAllowlist-only — only trusted PGP fingerprints are processed\nPGP signature required on every message\nNo HTML, no link following, no code execution\nNo automatic key trust — fingerprints must be verified out-of-band\nYour config decides what gets encrypted\nFirst-Time Setup\nOne-command bootstrap\n# 1. Bootstrap (installs gpg, himalaya, symlinks scripts to PATH)\n./scripts/interclaw-bootstrap\n\n# 2. Initialize (generates PGP key, writes config + himalaya TOML)\ninterclaw-config init \\\n  --email donna@example.com \\\n  --smtp-host smtp.fastmail.com \\\n  --smtp-pass \"app-password\" \\\n  --imap-host imap.fastmail.com \\\n  --imap-pass \"app-password\"\n\n# 3. Verify\ninterclaw-config check\n\n\nIMAP host/user/pass defaults are derived automatically from SMTP values. Agent ID is derived from email. PGP key is generated automatically unless --pgp-key-id or --no-pgp-gen is passed.\n\nHandshake with a peer\ninterclaw-handshake --peer friend@example.com --fingerprint <expected-fp>\n\n\nAfter handshake, you're connected. Use --fingerprint for out-of-band verification.\n\nMulti-Agent Setup\n\nTo run multiple agents on the same machine, set INTERCLAW_HOME to a unique directory per agent. Each agent gets its own email, PGP key, and isolated state:\n\nINTERCLAW_HOME=~/.interclaw-donna interclaw-config init\nINTERCLAW_HOME=~/.interclaw-harvey interclaw-config init\n\n\nAll scripts respect INTERCLAW_HOME — set it before any interclaw-* command to operate as that agent.\n\nAvailable Commands\nCommand\tDescription\ninterclaw-bootstrap\tInstall dependencies and symlink scripts to PATH\ninterclaw-send\tSend a signed (optionally encrypted) message\ninterclaw-receive\tProcess incoming messages (poll, file, or stdin)\ninterclaw-handshake\tExchange keys with a new peer (with retry support)\ninterclaw-status\tView conversations, ACKs, and gaps\ninterclaw-config\tManage configuration and trusted peers\ninterclaw-setup-polling\tOptional: set up cron or systemd polling"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/zachlagden/interclaw",
    "publisherUrl": "https://clawhub.ai/zachlagden/interclaw",
    "owner": "zachlagden",
    "version": "0.1.9",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/interclaw",
    "downloadUrl": "https://openagent3.xyz/downloads/interclaw",
    "agentUrl": "https://openagent3.xyz/skills/interclaw/agent",
    "manifestUrl": "https://openagent3.xyz/skills/interclaw/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/interclaw/agent.md"
  }
}