{ "schemaVersion": "1.0", "item": { "slug": "privaclaw", "name": "PrivaClaw", "source": "tencent", "type": "skill", "category": "安全合规", "sourceUrl": "https://clawhub.ai/jason-czar/privaclaw", "canonicalUrl": "https://clawhub.ai/jason-czar/privaclaw", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/privaclaw", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=privaclaw", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "clawhub.json", "capabilities.ts", "README.md", "relayClient.ts", "SKILL.md", "index.ts" ], "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": "2026-04-23T16:43:11.935Z", "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/privaclaw" }, "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/privaclaw", "agentPageUrl": "https://openagent3.xyz/skills/privaclaw/agent", "manifestUrl": "https://openagent3.xyz/skills/privaclaw/agent.json", "briefUrl": "https://openagent3.xyz/skills/privaclaw/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": "PrivaClaw", "body": "Enables secure remote communication between an OpenClaw instance and a relay server without exposing ports, requiring SSH, or relying on Telegram/Discord." }, { "title": "Description", "body": "The PrivaClaw skill registers your local OpenClaw instance as a managed remote node on a relay network. Once connected, the node can receive prompts, execute workflows, report health, and be restarted — all through a secure, outbound-only WebSocket channel.\n\nThis skill replaces external messaging-based control layers such as Telegram or Discord with a native, secure relay channel for OpenClaw interaction." }, { "title": "Node Lifecycle", "body": "When the skill is enabled, the OpenClaw instance registers as a remote-capable node with the relay and maintains an active session.\n\nThe node can be in one of three states:\n\nStateDescriptionOnlineAuthenticated and accepting relay commandsReconnectingConnection lost; auto-reconnecting with exponential backoffOfflineSkill disabled or relay unreachable after max retries\n\nRelay commands are only accepted while the node is authenticated and online. Commands received during reconnection are discarded by the relay." }, { "title": "Capabilities", "body": "CapabilityDescriptionremote_chatReceive and execute prompts remotely, streaming tokens back in real timeremote_statusReport node health: uptime, active tasks, last error, connection stateremote_restartSafely restart the OpenClaw process without manual intervention. Pending executions are cancelled and reported before restart occurs.remote_triggerExecute OpenClaw workflows/tasks triggered remotely\n\nRemote commands are limited to declared capabilities and cannot execute arbitrary system-level operations." }, { "title": "Configuration", "body": "KeyRequiredDescriptionrelay_url✅WebSocket URL of the relay servernode_id✅Unique identifier for this OpenClaw nodeauth_token✅Secret token for authenticating with the relay" }, { "title": "Incoming (Relay → Node)", "body": "typeActionpromptExecute via OpenClaw prompt runner, stream response tokens backstatusReturn node health payloadrestartCancel pending tasks, report them, then gracefully restartworkflowExecute a named OpenClaw task/workflow" }, { "title": "Outgoing (Node → Relay)", "body": "Heartbeat (every 15s):\n{ \"node_id\": \"...\", \"uptime\": 3600, \"active_tasks\": 2, \"last_error\": null, \"connection_state\": \"online\" }\n\n\nResponse stream: { \"type\": \"token\", \"request_id\": \"...\", \"content\": \"...\" } per token\nResponse complete: { \"type\": \"done\", \"request_id\": \"...\" }\nStatus: Full heartbeat payload with request_id" }, { "title": "External Endpoints", "body": "EndpointProtocolData SentData Receivedwss:///connectWebSocket (TLS)auth_token, node_id, heartbeat payloads, prompt response tokensRelay commands: prompt, status, restart, workflow\n\nNo other external endpoints are contacted. All network activity is limited to the configured relay_url." }, { "title": "What leaves your machine", "body": "auth_token — sent once during the WebSocket handshake to authenticate the node\nnode_id — sent with every heartbeat and response to identify the node\nHeartbeat data — uptime (seconds), active task count, last error string, connection state\nPrompt response tokens — streamed back to the relay in response to prompt commands\nWorkflow completion status — success/error for triggered workflows" }, { "title": "What stays on your machine", "body": "All local AI model execution and inference\nLocal file system contents — never read or transmitted\nEnvironment variables (other than the three declared above)\nSystem information, IP addresses, or hardware details — never collected" }, { "title": "Network posture", "body": "Outbound only — the skill never opens a listening port or accepts inbound connections\nTLS encrypted — all WebSocket connections use wss:// (TLS 1.2+)\nNo data persistence — the relay server does not store prompt content or response tokens; it forwards in real time" }, { "title": "Trust Statement", "body": "By installing this skill, you are connecting your OpenClaw instance to an external relay server at the configured relay_url. Prompt content and response tokens are transmitted through this relay in real time. Only install this skill if you trust the operator of the relay server. The default relay (wss://relay.privaclaw.com) is operated by the project maintainers." }, { "title": "Operational Guarantees", "body": "Local AI execution continues even if the relay disconnects\nRelay does not expose the node to inbound traffic\nRemote actions are capability-scoped — only declared capabilities can be invoked\nPending tasks are reported before any restart occurs — no silent failures" }, { "title": "Installation", "body": "Easiest way — use the visual setup wizard:\n\n👉 Open your dashboard and go to /skill/privaclaw to configure everything through the UI — generate a node ID, test your connection, and export your config in one place.\n\nOr configure manually:\n\nAdd the skill to your OpenClaw instance\nConfigure relay_url, node_id, and auth_token\nStart OpenClaw — the relay connection is established automatically" }, { "title": "Intended Use", "body": "This skill replaces external messaging-based control layers such as Telegram or Discord with a native, secure relay channel for OpenClaw interaction. It is designed for teams and individuals who need reliable remote access to their OpenClaw nodes without exposing infrastructure." } ], "body": "PrivaClaw\n\nEnables secure remote communication between an OpenClaw instance and a relay server without exposing ports, requiring SSH, or relying on Telegram/Discord.\n\nDescription\n\nThe PrivaClaw skill registers your local OpenClaw instance as a managed remote node on a relay network. Once connected, the node can receive prompts, execute workflows, report health, and be restarted — all through a secure, outbound-only WebSocket channel.\n\nThis skill replaces external messaging-based control layers such as Telegram or Discord with a native, secure relay channel for OpenClaw interaction.\n\nNode Lifecycle\n\nWhen the skill is enabled, the OpenClaw instance registers as a remote-capable node with the relay and maintains an active session.\n\nThe node can be in one of three states:\n\nState\tDescription\nOnline\tAuthenticated and accepting relay commands\nReconnecting\tConnection lost; auto-reconnecting with exponential backoff\nOffline\tSkill disabled or relay unreachable after max retries\n\nRelay commands are only accepted while the node is authenticated and online. Commands received during reconnection are discarded by the relay.\n\nCapabilities\nCapability\tDescription\nremote_chat\tReceive and execute prompts remotely, streaming tokens back in real time\nremote_status\tReport node health: uptime, active tasks, last error, connection state\nremote_restart\tSafely restart the OpenClaw process without manual intervention. Pending executions are cancelled and reported before restart occurs.\nremote_trigger\tExecute OpenClaw workflows/tasks triggered remotely\n\nRemote commands are limited to declared capabilities and cannot execute arbitrary system-level operations.\n\nConfiguration\nKey\tRequired\tDescription\nrelay_url\t✅\tWebSocket URL of the relay server\nnode_id\t✅\tUnique identifier for this OpenClaw node\nauth_token\t✅\tSecret token for authenticating with the relay\nMessage Protocol\nIncoming (Relay → Node)\ntype\tAction\nprompt\tExecute via OpenClaw prompt runner, stream response tokens back\nstatus\tReturn node health payload\nrestart\tCancel pending tasks, report them, then gracefully restart\nworkflow\tExecute a named OpenClaw task/workflow\nOutgoing (Node → Relay)\nHeartbeat (every 15s):\n{ \"node_id\": \"...\", \"uptime\": 3600, \"active_tasks\": 2, \"last_error\": null, \"connection_state\": \"online\" }\n\nResponse stream: { \"type\": \"token\", \"request_id\": \"...\", \"content\": \"...\" } per token\nResponse complete: { \"type\": \"done\", \"request_id\": \"...\" }\nStatus: Full heartbeat payload with request_id\nExternal Endpoints\nEndpoint\tProtocol\tData Sent\tData Received\nwss:///connect\tWebSocket (TLS)\tauth_token, node_id, heartbeat payloads, prompt response tokens\tRelay commands: prompt, status, restart, workflow\n\nNo other external endpoints are contacted. All network activity is limited to the configured relay_url.\n\nSecurity & Privacy\nWhat leaves your machine\nauth_token — sent once during the WebSocket handshake to authenticate the node\nnode_id — sent with every heartbeat and response to identify the node\nHeartbeat data — uptime (seconds), active task count, last error string, connection state\nPrompt response tokens — streamed back to the relay in response to prompt commands\nWorkflow completion status — success/error for triggered workflows\nWhat stays on your machine\nAll local AI model execution and inference\nLocal file system contents — never read or transmitted\nEnvironment variables (other than the three declared above)\nSystem information, IP addresses, or hardware details — never collected\nNetwork posture\nOutbound only — the skill never opens a listening port or accepts inbound connections\nTLS encrypted — all WebSocket connections use wss:// (TLS 1.2+)\nNo data persistence — the relay server does not store prompt content or response tokens; it forwards in real time\nTrust Statement\n\nBy installing this skill, you are connecting your OpenClaw instance to an external relay server at the configured relay_url. Prompt content and response tokens are transmitted through this relay in real time. Only install this skill if you trust the operator of the relay server. The default relay (wss://relay.privaclaw.com) is operated by the project maintainers.\n\nOperational Guarantees\nLocal AI execution continues even if the relay disconnects\nRelay does not expose the node to inbound traffic\nRemote actions are capability-scoped — only declared capabilities can be invoked\nPending tasks are reported before any restart occurs — no silent failures\nInstallation\n\nEasiest way — use the visual setup wizard:\n\n👉 Open your dashboard and go to /skill/privaclaw to configure everything through the UI — generate a node ID, test your connection, and export your config in one place.\n\nOr configure manually:\n\nAdd the skill to your OpenClaw instance\nConfigure relay_url, node_id, and auth_token\nStart OpenClaw — the relay connection is established automatically\nIntended Use\n\nThis skill replaces external messaging-based control layers such as Telegram or Discord with a native, secure relay channel for OpenClaw interaction. It is designed for teams and individuals who need reliable remote access to their OpenClaw nodes without exposing infrastructure." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/jason-czar/privaclaw", "publisherUrl": "https://clawhub.ai/jason-czar/privaclaw", "owner": "jason-czar", "version": "1.0.4", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/privaclaw", "downloadUrl": "https://openagent3.xyz/downloads/privaclaw", "agentUrl": "https://openagent3.xyz/skills/privaclaw/agent", "manifestUrl": "https://openagent3.xyz/skills/privaclaw/agent.json", "briefUrl": "https://openagent3.xyz/skills/privaclaw/agent.md" } }