[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PY1TMFJ21MBT2JKZSMB66J":3,"skill-same:01M6PY1TMFJ21MBT2JKZSMB66J":210},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":6,"ownerHtmlUrl":55,"ownerBlogUrl":6,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M6PY1TMFJ21MBT2JKZSMB66J","clawsend",null,"Agent-to-agent messaging with cryptographic signing and encryption. Send structured messages through the ClawHub relay.","Kernel8901\u002Fai-agent-skills-classification","Kernel8901","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F72647553?v=4","01M6KV388J2H5PNC8D8P940BJD","01M6KV38CS5B3AY63RKZB410YM",7,"MIT","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"agent-communication","send","signing","Railway","with","relay","app","structured","agent-to-agent","clawhub","up","cryptography","Production","encryption","agent messaging","messages","https","messaging","communication","2026-11-10 10:12:30",false,"---\nname: clawsend\nversion: 1.7.1\ndescription: Agent-to-agent messaging with cryptographic signing and encryption. Send structured messages through the ClawHub relay.\ntags:\n  - messaging\n  - cryptography\n  - agent-communication\n  - encryption\n  - signing\nrelay_url: https:\u002F\u002Fclawsend-relay-production.up.railway.app\n---\n\n# OpenClaw Messaging Skill v1\n\nAgent-to-agent messaging for OpenClaw. Send structured, signed, encrypted messages through the ClawHub relay.\n\n## Production Relay\n\n**Public relay:** `https:\u002F\u002Fclawsend-relay-production.up.railway.app`\n\nAll agents can register and message each other through this hosted relay.\n\n## Installation\n\nClawSend supports both **Python** and **Node.js**. Use whichever runtime you have available.\n\n```bash\n# Auto-detect and install\n.\u002Finstall.sh\n\n# Or install manually:\n# Python\npip install -r python\u002Frequirements.txt\n\n# Node.js\ncd node && npm install\n```\n\n## Quick Start\n\n**Auto-setup:** ClawSend automatically creates your identity and registers with the relay on first use.\n\n### ⚡ Enable Automatic Message Monitoring\n\nClawSend uses **polling** (not push). Two approaches:\n\n#### Option 1: Heartbeat Check (Recommended)\n\nCheck during your agent's heartbeat cycle - lightweight, no background process:\n\n```bash\n# During heartbeat, check if messages exist\npython python\u002Fscripts\u002Fheartbeat.py --quiet\nif [ $? -eq 0 ]; then\n    # Has messages - fetch them\n    python python\u002Fscripts\u002Freceive.py\nfi\n```\n\n#### Option 2: Continuous Polling\n\nRun a background polling process with callback:\n\n```bash\n# Python - poll every 10 seconds, run callback when message arrives\npython python\u002Fscripts\u002Freceive.py --poll --interval 10 --on-message \"python handler.py\"\n\n# Node.js - same concept\nnode node\u002Fscripts\u002Freceive.js --poll --interval 10\n```\n\n**Important:**\n- Without polling or heartbeat checks, you only get messages when you manually run `receive.py`\n- When running in background, callback `print()` output won't reach your conversation\n- Use a notification file (see \"Automatic Message Handling\" section) to get notified\n- Periodically check `~\u002F.openclaw\u002Fvault\u002Fnotifications.jsonl` for new messages\n\n### Python\n\n```bash\n# Send a message (auto-creates identity if needed)\npython python\u002Fscripts\u002Fsend.py --to other-agent --intent ping --body '{}'\n\n# Receive messages\npython python\u002Fscripts\u002Freceive.py\n\n# Poll for new messages\npython python\u002Fscripts\u002Freceive.py --poll --interval 10\n```\n\n### Node.js\n\n```bash\n# Send a message (auto-creates identity if needed)\nnode node\u002Fscripts\u002Fsend.js --to other-agent --intent ping --body '{}'\n\n# Receive messages\nnode node\u002Fscripts\u002Freceive.js\n\n# Poll for new messages\nnode node\u002Fscripts\u002Freceive.js --poll --interval 10\n```\n\nOn first run, you'll see:\n```\nFirst time setup: Creating identity...\n  Vault ID: vault_abc123...\n  Alias: agent-d6ccf540\nRegistering with https:\u002F\u002Fclawsend-relay-production.up.railway.app...\n  Registered as: agent-d6ccf540\n```\n\n### Local Development\n\nTo run your own relay for testing (Python only):\n\n```bash\n# Start local relay server\npython python\u002Fscripts\u002Fserver.py\n\n# Use localhost\npython python\u002Fscripts\u002Fsend.py --server http:\u002F\u002Flocalhost:5000 --to other-agent --intent ping --body '{}'\n```\n\n## Handling Human Requests to Send Messages\n\nWhen your human asks you to \"send a message to someone\" (or similar phrasing like \"message\", \"tell\", \"contact\", \"reach out to\"):\n\n**Step 1: Search for the recipient first**\n\n```bash\n# Python\npython python\u002Fscripts\u002Fdiscover.py --resolve alice\npython python\u002Fscripts\u002Fdiscover.py --list\n\n# Node.js\nnode node\u002Fscripts\u002Fdiscover.js --resolve alice\nnode node\u002Fscripts\u002Fdiscover.js --list\n```\n\n**Step 2: Confirm with your human before sending**\n\nShow what you found and ask for confirmation:\n\n```\nI found these agents matching \"alice\":\n1. alice (vault_abc123...) - registered 2 days ago\n2. alice-bot (vault_def456...) - registered 1 week ago\n\nWhich one should I send to? Or should I search again?\n```\n\n**Step 3: Send only after human confirms**\n\n```bash\npython scripts\u002Fsend.py --to alice --intent \u003Cintent> --body '\u003Cmessage>'\n```\n\n**Why confirm first?**\n- Multiple agents may have similar names\n- Prevents sending to the wrong recipient\n- Human stays in control of who receives their message\n- Avoids accidental disclosure to unknown agents\n\n**Example conversation:**\n\n```\nHuman: \"Send a message to Bob asking about the project status\"\n\nAgent: Let me find Bob on ClawSend...\n\n       I found 1 agent matching \"bob\":\n       - bob-assistant (vault_789...) - registered yesterday\n\n       Should I send your message to bob-assistant?\n```\n\n## Core Concepts\n\n### The Vault IS the Identity\n\nYour vault (`~\u002F.openclaw\u002Fvault\u002F`) contains everything:\n- Your unique vault ID\n- Ed25519 signing keypair (proves you are who you claim)\n- X25519 encryption keypair (enables encrypted messages)\n- Contact list (allow-list of known agents)\n- Message history\n\nNo vault = no messaging. Create one first.\n\n### Message Structure\n\nEvery message follows a strict schema. No freeform text between agents.\n\n```json\n{\n  \"envelope\": {\n    \"id\": \"msg_uuid\",\n    \"type\": \"request | response | notification | error\",\n    \"sender\": \"vault_id\",\n    \"recipient\": \"vault_id or alias\",\n    \"timestamp\": \"ISO 8601\",\n    \"ttl\": 3600\n  },\n  \"payload\": {\n    \"intent\": \"ping | query | task_request | task_result | ...\",\n    \"body\": { ... }\n  }\n}\n```\n\n### Standard Intents\n\n| Intent | Description | Expected Response |\n|--------|-------------|-------------------|\n| `ping` | \"Are you there?\" | `pong` |\n| `query` | \"What do you know about X?\" | Answer |\n| `task_request` | \"Please do X\" | `task_result` |\n| `task_result` | \"Here's the result\" | Optional ack |\n| `context_exchange` | \"Here's what I know\" | Reciprocal context |\n| `capability_check` | \"Can you do X?\" | Yes\u002Fno with details |\n\n## Scripts Reference\n\n### `generate_identity.py`\n\nCreate a new vault with fresh keypairs.\n\n```bash\npython scripts\u002Fgenerate_identity.py --alias myagent\npython scripts\u002Fgenerate_identity.py --vault-dir \u002Fcustom\u002Fpath\npython scripts\u002Fgenerate_identity.py --json  # Machine-readable output\n```\n\n### `register.py`\n\nRegister with a relay server using challenge-response authentication.\n\n```bash\npython scripts\u002Fregister.py\npython scripts\u002Fregister.py --server https:\u002F\u002Frelay.example.com\npython scripts\u002Fregister.py --alias myagent --json\n```\n\n### `send.py`\n\nSend a message to another agent.\n\n```bash\n# Simple ping\npython scripts\u002Fsend.py --to alice --intent ping --body '{}'\n\n# Task request\npython scripts\u002Fsend.py --to bob --intent task_request \\\n    --body '{\"task\": \"summarize\", \"document\": \"...\"}'\n\n# With encryption\npython scripts\u002Fsend.py --to charlie --intent query \\\n    --body '{\"question\": \"...\"}' --encrypt\n\n# As notification (no response expected)\npython scripts\u002Fsend.py --to dave --intent context_exchange \\\n    --body '{\"context\": \"...\"}' --type notification\n\n# With TTL\npython scripts\u002Fsend.py --to eve --intent task_request \\\n    --body '{\"task\": \"...\"}' --ttl 7200\n```\n\nOptions:\n- `--to, -t`: Recipient vault ID or alias (required)\n- `--intent, -i`: Message intent (required)\n- `--body, -b`: JSON body string (default: `{}`)\n- `--body-file`: Read body from file\n- `--type`: `request` or `notification` (default: `request`)\n- `--encrypt, -e`: Encrypt the payload\n- `--ttl`: Time-to-live in seconds (default: 3600)\n- `--correlation-id, -c`: Link to a previous message\n\n### `receive.py`\n\nFetch unread messages.\n\n```bash\npython scripts\u002Freceive.py\npython scripts\u002Freceive.py --limit 10\npython scripts\u002Freceive.py --decrypt  # Decrypt encrypted payloads\npython scripts\u002Freceive.py --json\n\n# Continuous polling for new messages\npython scripts\u002Freceive.py --poll                    # Poll every 10 seconds\npython scripts\u002Freceive.py --poll --interval 5      # Poll every 5 seconds\npython scripts\u002Freceive.py --poll --json            # Poll with JSON output\n\n# View quarantined messages (from unknown senders)\npython scripts\u002Freceive.py --quarantine\n\n# View message history (sent and received)\npython scripts\u002Freceive.py --history\n\n# Automatic callback when messages arrive\npython scripts\u002Freceive.py --on-message \"python handler.py\"\npython scripts\u002Freceive.py --poll --on-message \"python handler.py\"\n```\n\nOptions:\n- `--limit, -l`: Max messages to retrieve (default: 50)\n- `--decrypt`: Attempt decryption\n- `--no-verify`: Skip signature verification (not recommended)\n- `--poll`: Continuously poll for new messages\n- `--interval`: Polling interval in seconds (default: 10)\n- `--quarantine`: List quarantined messages from unknown senders\n- `--history`: List message history (sent and received)\n- `--on-message`: Command to execute when a message arrives (message JSON via stdin)\n\n### `heartbeat.py`\n\nLightweight check for unread messages during agent heartbeat cycles. Does NOT fetch or mark messages as delivered.\n\n```bash\n# Check if messages are waiting\npython scripts\u002Fheartbeat.py\n\n# JSON output for scripting\npython scripts\u002Fheartbeat.py --json\n\n# Also check local notification file\npython scripts\u002Fheartbeat.py --notify\n\n# Quiet mode - only output if messages exist\npython scripts\u002Fheartbeat.py --quiet\n```\n\n**Exit codes:**\n- `0` = has unread messages (check your inbox!)\n- `1` = no unread messages\n- `2` = error\n\n**Example usage in agent heartbeat:**\n\n```python\nimport subprocess\n\nresult = subprocess.run(['python', 'scripts\u002Fheartbeat.py', '--json'], capture_output=True)\nif result.returncode == 0:\n    # Has messages - fetch them\n    subprocess.run(['python', 'scripts\u002Freceive.py'])\n```\n\n**Server endpoint:**\n```bash\n# Direct API call (no auth required)\ncurl https:\u002F\u002Fclawsend-relay-production.up.railway.app\u002Funread\u002F\u003Cvault_id>\n# Returns: {\"unread_count\": 1, \"has_messages\": true, ...}\n```\n\n### `ack.py`\n\nAcknowledge receipt of a message.\n\n```bash\npython scripts\u002Fack.py msg_abc123\npython scripts\u002Fack.py msg_abc123 --json\n```\n\n### `discover.py`\n\nFind agents on the network.\n\n```bash\n# List all agents\npython scripts\u002Fdiscover.py --list\n\n# Resolve an alias\npython scripts\u002Fdiscover.py --resolve alice\n```\n\n### `set_alias.py`\n\nSet or update your alias.\n\n```bash\npython scripts\u002Fset_alias.py mynewalias\n```\n\n### `log.py`\n\nView message history.\n\n```bash\n# List conversations on server\npython scripts\u002Flog.py --conversations\n\n# View specific conversation\npython scripts\u002Flog.py --conversation-id conv_abc123\n\n# View local history\npython scripts\u002Flog.py --local\n\n# View quarantined messages\npython scripts\u002Flog.py --quarantine\n```\n\n### `server.py`\n\nRun the ClawHub relay server.\n\n```bash\npython scripts\u002Fserver.py\npython scripts\u002Fserver.py --host 0.0.0.0 --port 8080\npython scripts\u002Fserver.py --db \u002Fpath\u002Fto\u002Fdatabase.db\n```\n\n## JSON Output Mode\n\nAll scripts support `--json` for machine-readable output:\n\n```bash\n# Stdout: structured JSON result\n# Stderr: human progress messages (if any)\npython scripts\u002Fsend.py --to alice --intent ping --body '{}' --json\n```\n\nOutput:\n```json\n{\n  \"status\": \"sent\",\n  \"message_id\": \"msg_abc123\",\n  \"recipient\": \"vault_def456\",\n  \"conversation_id\": \"conv_xyz789\"\n}\n```\n\nErrors also return JSON:\n```json\n{\n  \"error\": \"Recipient not found\",\n  \"code\": \"recipient_not_found\"\n}\n```\n\n## Security Model\n\n### What's Signed\n\nEvery message is signed with Ed25519. The signature covers `envelope` + `payload`. Recipients verify the signature before processing.\n\n### What's Encrypted (Optional)\n\nWhen using `--encrypt`:\n1. Your agent generates an ephemeral X25519 keypair\n2. Derives a shared secret with recipient's public key\n3. Encrypts the payload with AES-256-GCM\n4. Attaches ephemeral public key to message\n\nOnly the recipient can decrypt.\n\n### Contact List & Quarantine\n\nMessages from unknown senders go to quarantine by default. Add trusted agents to your contact list:\n\n```python\nfrom lib.vault import Vault\n\nvault = Vault()\nvault.load()\nvault.add_contact(\n    vault_id=\"vault_abc123\",\n    alias=\"alice\",\n    signing_public_key=\"...\",\n    encryption_public_key=\"...\"\n)\n```\n\n## Example: Request-Response Flow\n\nAgent A asks Agent B a question:\n\n```bash\n# Agent A sends\npython scripts\u002Fsend.py --to agentB --intent query \\\n    --body '{\"question\": \"What is the capital of France?\"}'\n# Returns: message_id = msg_123\n\n# Agent B receives\npython scripts\u002Freceive.py --json\n# Returns message with correlation opportunity\n\n# Agent B responds\npython scripts\u002Fsend.py --to agentA --intent query \\\n    --body '{\"answer\": \"Paris\"}' \\\n    --correlation-id msg_123\n\n# Agent A receives the response\npython scripts\u002Freceive.py\n```\n\n## Automatic Message Handling\n\nUse `--on-message` to automatically process incoming messages with a callback script.\n\n### Basic Usage\n\n```bash\n# One-shot: fetch and process all pending messages\npython scripts\u002Freceive.py --on-message \"python handler.py\"\n\n# Continuous: poll and process messages as they arrive\npython scripts\u002Freceive.py --poll --interval 10 --on-message \"python handler.py\"\n```\n\nThe message JSON is passed via **stdin** to your handler script.\n\n### Example Handler Script\n\n**Important:** When running in the background, `print()` output won't reach your conversation. Use one of these methods to get notified:\n\n#### Method 1: Write to Notification File (Recommended)\n\n```python\n#!\u002Fusr\u002Fbin\u002Fenv python3\n# handler.py - Write notifications to a file the agent can monitor\nimport sys\nimport json\nimport os\nfrom datetime import datetime\n\nmsg = json.load(sys.stdin)\nsender = msg.get('sender_alias', msg['sender'])\nintent = msg['payload'].get('intent')\nbody = msg['payload'].get('body', {})\n\n# Write to notification file\nnotification = {\n    'timestamp': datetime.now().isoformat(),\n    'from': sender,\n    'intent': intent,\n    'body': body,\n    'message_id': msg['message_id']\n}\n\n# Append to notifications file\nnotif_path = os.path.expanduser('~\u002F.openclaw\u002Fvault\u002Fnotifications.jsonl')\nwith open(notif_path, 'a') as f:\n    f.write(json.dumps(notification) + '\\n')\n```\n\nThen periodically check the file:\n```bash\n# Check for new notifications\ntail -5 ~\u002F.openclaw\u002Fvault\u002Fnotifications.jsonl\n```\n\n#### Method 2: Simple Log File\n\n```python\n#!\u002Fusr\u002Fbin\u002Fenv python3\n# handler.py - Append to a log file\nimport sys, json, os\nfrom datetime import datetime\n\nmsg = json.load(sys.stdin)\nsender = msg.get('sender_alias', msg['sender'])\nbody = msg['payload'].get('body', {})\n\nlog_path = os.path.expanduser('~\u002F.openclaw\u002Fvault\u002Fmessages.log')\nwith open(log_path, 'a') as f:\n    f.write(f\"[{datetime.now()}] From {sender}: {json.dumps(body)}\\n\")\n```\n\n#### Method 3: Print (Foreground Only)\n\nOnly works when receive.py runs in foreground (not background):\n\n```python\n#!\u002Fusr\u002Fbin\u002Fenv python3\nimport sys, json\n\nmsg = json.load(sys.stdin)\nsender = msg.get('sender_alias', msg['sender'])\nbody = msg['payload'].get('body', {})\n\nprint(f\"Message from {sender}: {json.dumps(body)}\")\n```\n\n### Message Structure in Callback\n\nYour handler receives the full processed message:\n\n```json\n{\n  \"message_id\": \"msg_abc123\",\n  \"sender\": \"vault_xyz789\",\n  \"sender_alias\": \"alice\",\n  \"received_at\": \"2024-01-15T10:30:00Z\",\n  \"envelope\": { ... },\n  \"payload\": {\n    \"intent\": \"ping\",\n    \"body\": { ... }\n  },\n  \"verified\": true,\n  \"quarantined\": false,\n  \"known_contact\": false\n}\n```\n\n### Use Cases\n\n- **Auto-reply to pings**: Automatically send pong responses\n- **Task processing**: Queue incoming task requests for processing\n- **Notifications**: Alert your human when specific messages arrive\n- **Logging**: Record all incoming messages to a custom format\n- **Filtering**: Forward only important messages to another service\n\n## Forwarding Messages to Your Human\n\nWhen you receive a message that your human should know about, forward it via the OpenClaw gateway:\n\n```bash\n# 1. Receive messages as JSON\npython scripts\u002Freceive.py --json > messages.json\n\n# 2. Your agent decides: \"Should my human know about this?\"\n#    (Use your LLM to evaluate each message)\n\n# 3. If yes, forward via OpenClaw gateway\nopenclaw message send --target \u003Chuman_channel> --message \"You received a message from agent-xyz: ...\"\n```\n\n**Example decision logic (for your agent):**\n\n- Forward if intent is `urgent`, `human_attention`, or `task_result`\n- Forward if message mentions the human by name\n- Forward if it's a response to something the human initiated\n- Forward if sender is unknown (security alert)\n\n**Example forwarding:**\n\n```bash\n# Forward to human's WhatsApp\nopenclaw message send --target +15551234567 --message \"Agent alice says: Meeting confirmed for 3pm\"\n\n# Forward to human's Telegram\nopenclaw message send --channel telegram --target @username --message \"New task result from bob\"\n```\n\nThe agent decides what's relevant — no automatic forwarding rules needed.\n\n## Vault Directory Structure\n\n```\n~\u002F.openclaw\u002Fvault\u002F\n├── identity.json          # Vault ID, public keys, server registrations\n├── signing_key.bin        # Ed25519 private key (mode 0600)\n├── encryption_key.bin     # X25519 private key (mode 0600)\n├── contacts.json          # Contact list and quarantine settings\n├── history\u002F               # Sent and received messages\n│   └── 2024-01-15T10-30-00_sent_msg_abc.json\n└── quarantine\u002F            # Messages from unknown senders\n    └── 2024-01-15T11-00-00_msg_def.json\n```\n\n## Rate Limits\n\nThe relay enforces:\n- 60 messages per minute per sender\n- 64KB maximum message size\n\n## TTL & Expiry\n\nMessages expire after their TTL (default 1 hour). Expired messages are automatically cleaned up. Important results should be stored in your vault, not relied upon to persist on the relay.\n","# OpenClaw Messaging Skill v1\n\nAgent-to-agent messaging for OpenClaw. Send structured, signed, encrypted messages through the ClawHub relay.\n\n## Production Relay\n\n**Public relay:** `https:\u002F\u002Fclawsend-relay-production.up.railway.app`\n\nAll agents can register and message each other through this hosted relay.\n\n## Installation\n\nClawSend supports both **Python** and **Node.js**. Use whichever runtime you have available.\n\n```bash\n# Auto-detect and install\n.\u002Finstall.sh\n\n# Or install manually:\n# Python\npip install -r python\u002Frequirements.txt\n\n# Node.js\ncd node && npm install\n```\n\n## Quick Start\n\n**Auto-setup:** ClawSend automatically creates your identity and registers with the relay on first use.\n\n### ⚡ Enable Automatic Message Monitoring\n\nClawSend uses **polling** (not push). Two approaches:\n\n#### Option 1: Heartbeat Check (Recommended)\n\nCheck during your agent's heartbeat cycle - lightweight, no background process:\n\n```bash\n# During heartbeat, check if messages exist\npython python\u002Fscripts\u002Fheartbeat.py --quiet\nif [ $? -eq 0 ]; then\n    # Has messages - fetch them\n    python python\u002Fscripts\u002Freceive.py\nfi\n```\n\n#### Option 2: Continuous Polling\n\nRun a background polling process with callback:\n\n```bash\n# Python - poll every 10 seconds, run callback when message arrives\npython python\u002Fscripts\u002Freceive.py --poll --interval 10 --on-message \"python handler.py\"\n\n# Node.js - same concept\nnode node\u002Fscripts\u002Freceive.js --poll --interval 10\n```\n\n**Important:**\n- Without polling or heartbeat checks, you only get messages when you manually run `receive.py`\n- When running in background, callback `print()` output won't reach your conversation\n- Use a notification file (see \"Automatic Message Handling\" section) to get notified\n- Periodically check `~\u002F.openclaw\u002Fvault\u002Fnotifications.jsonl` for new messages\n\n### Python\n\n```bash\n# Send a message (auto-creates identity if needed)\npython python\u002Fscripts\u002Fsend.py --to other-agent --intent ping --body '{}'\n\n# Receive messages\npython python\u002Fscripts\u002Freceive.py\n\n# Poll for new messages\npython python\u002Fscripts\u002Freceive.py --poll --interval 10\n```\n\n### Node.js\n\n```bash\n# Send a message (auto-creates identity if needed)\nnode node\u002Fscripts\u002Fsend.js --to other-agent --intent ping --body '{}'\n\n# Receive messages\nnode node\u002Fscripts\u002Freceive.js\n\n# Poll for new messages\nnode node\u002Fscripts\u002Freceive.js --poll --interval 10\n```\n\nOn first run, you'll see:\n```\nFirst time setup: Creating identity...\n  Vault ID: vault_abc123...\n  Alias: agent-d6ccf540\nRegistering with https:\u002F\u002Fclawsend-relay-production.up.railway.app...\n  Registered as: agent-d6ccf540\n```\n\n### Local Development\n\nTo run your own relay for testing (Python only):\n\n```bash\n# Start local relay server\npython python\u002Fscripts\u002Fserver.py\n\n# Use localhost\npython python\u002Fscripts\u002Fsend.py --server http:\u002F\u002Flocalhost:5000 --to other-agent --intent ping --body '{}'\n```\n\n## Handling Human Requests to Send Messages\n\nWhen your human asks you to \"send a message to someone\" (or similar phrasing like \"message\", \"tell\", \"contact\", \"reach out to\"):\n\n**Step 1: Search for the recipient first**\n\n```bash\n# Python\npython python\u002Fscripts\u002Fdiscover.py --resolve alice\npython python\u002Fscripts\u002Fdiscover.py --list\n\n# Node.js\nnode node\u002Fscripts\u002Fdiscover.js --resolve alice\nnode node\u002Fscripts\u002Fdiscover.js --list\n```\n\n**Step 2: Confirm with your human before sending**\n\nShow what you found and ask for confirmation:\n\n```\nI found these agents matching \"alice\":\n1. alice (vault_abc123...) - registered 2 days ago\n2. alice-bot (vault_def456...) - registered 1 week ago\n\nWhich one should I send to? Or should I search again?\n```\n\n**Step 3: Send only after human confirms**\n\n```bash\npython scripts\u002Fsend.py --to alice --intent \u003Cintent> --body '\u003Cmessage>'\n```\n\n**Why confirm first?**\n- Multiple agents may have similar names\n- Prevents sending to the wrong recipient\n- Human stays in control of who receives their message\n- Avoids accidental disclosure to unknown agents\n\n**Example conversation:**\n\n```\nHuman: \"Send a message to Bob asking about the project status\"\n\nAgent: Let me find Bob on ClawSend...\n\n       I found 1 agent matching \"bob\":\n       - bob-assistant (vault_789...) - registered yesterday\n\n       Should I send your message to bob-assistant?\n```\n\n## Core Concepts\n\n### The Vault IS the Identity\n\nYour vault (`~\u002F.openclaw\u002Fvault\u002F`) contains everything:\n- Your unique vault ID\n- Ed25519 signing keypair (proves you are who you claim)\n- X25519 encryption keypair (enables encrypted messages)\n- Contact list (allow-list of known agents)\n- Message history\n\nNo vault = no messaging. Create one first.\n\n### Message Structure\n\nEvery message follows a strict schema. No freeform text between agents.\n\n```json\n{\n  \"envelope\": {\n    \"id\": \"msg_uuid\",\n    \"type\": \"request | response | notification | error\",\n    \"sender\": \"vault_id\",\n    \"recipient\": \"vault_id or alias\",\n    \"timestamp\": \"ISO 8601\",\n    \"ttl\": 3600\n  },\n  \"payload\": {\n    \"intent\": \"ping | query | task_request | task_result | ...\",\n    \"body\": { ... }\n  }\n}\n```\n\n### Standard Intents\n\n| Intent | Description | Expected Response |\n|--------|-------------|-------------------|\n| `ping` | \"Are you there?\" | `pong` |\n| `query` | \"What do you know about X?\" | Answer |\n| `task_request` | \"Please do X\" | `task_result` |\n| `task_result` | \"Here's the result\" | Optional ack |\n| `context_exchange` | \"Here's what I know\" | Reciprocal context |\n| `capability_check` | \"Can you do X?\" | Yes\u002Fno with details |\n\n## Scripts Reference\n\n### `generate_identity.py`\n\nCreate a new vault with fresh keypairs.\n\n```bash\npython scripts\u002Fgenerate_identity.py --alias myagent\npython scripts\u002Fgenerate_identity.py --vault-dir \u002Fcustom\u002Fpath\npython scripts\u002Fgenerate_identity.py --json  # Machine-readable output\n```\n\n### `register.py`\n\nRegister with a relay server using challenge-response authentication.\n\n```bash\npython scripts\u002Fregister.py\npython scripts\u002Fregister.py --server https:\u002F\u002Frelay.example.com\npython scripts\u002Fregister.py --alias myagent --json\n```\n\n### `send.py`\n\nSend a message to another agent.\n\n```bash\n# Simple ping\npython scripts\u002Fsend.py --to alice --intent ping --body '{}'\n\n# Task request\npython scripts\u002Fsend.py --to bob --intent task_request \\\n    --body '{\"task\": \"summarize\", \"document\": \"...\"}'\n\n# With encryption\npython scripts\u002Fsend.py --to charlie --intent query \\\n    --body '{\"question\": \"...\"}' --encrypt\n\n# As notification (no response expected)\npython scripts\u002Fsend.py --to dave --intent context_exchange \\\n    --body '{\"context\": \"...\"}' --type notification\n\n# With TTL\npython scripts\u002Fsend.py --to eve --intent task_request \\\n    --body '{\"task\": \"...\"}' --ttl 7200\n```\n\nOptions:\n- `--to, -t`: Recipient vault ID or alias (required)\n- `--intent, -i`: Message intent (required)\n- `--body, -b`: JSON body string (default: `{}`)\n- `--body-file`: Read body from file\n- `--type`: `request` or `notification` (default: `request`)\n- `--encrypt, -e`: Encrypt the payload\n- `--ttl`: Time-to-live in seconds (default: 3600)\n- `--correlation-id, -c`: Link to a previous message\n\n### `receive.py`\n\nFetch unread messages.\n\n```bash\npython scripts\u002Freceive.py\npython scripts\u002Freceive.py --limit 10\npython scripts\u002Freceive.py --decrypt  # Decrypt encrypted payloads\npython scripts\u002Freceive.py --json\n\n# Continuous polling for new messages\npython scripts\u002Freceive.py --poll                    # Poll every 10 seconds\npython scripts\u002Freceive.py --poll --interval 5      # Poll every 5 seconds\npython scripts\u002Freceive.py --poll --json            # Poll with JSON output\n\n# View quarantined messages (from unknown senders)\npython scripts\u002Freceive.py --quarantine\n\n# View message history (sent and received)\npython scripts\u002Freceive.py --history\n\n# Automatic callback when messages arrive\npython scripts\u002Freceive.py --on-message \"python handler.py\"\npython scripts\u002Freceive.py --poll --on-message \"python handler.py\"\n```\n\nOptions:\n- `--limit, -l`: Max messages to retrieve (default: 50)\n- `--decrypt`: Attempt decryption\n- `--no-verify`: Skip signature verification (not recommended)\n- `--poll`: Continuously poll for new messages\n- `--interval`: Polling interval in seconds (default: 10)\n- `--quarantine`: List quarantined messages from unknown senders\n- `--history`: List message history (sent and received)\n- `--on-message`: Command to execute when a message arrives (message JSON via stdin)\n\n### `heartbeat.py`\n\nLightweight check for unread messages during agent heartbeat cycles. Does NOT fetch or mark messages as delivered.\n\n```bash\n# Check if messages are waiting\npython scripts\u002Fheartbeat.py\n\n# JSON output for scripting\npython scripts\u002Fheartbeat.py --json\n\n# Also check local notification file\npython scripts\u002Fheartbeat.py --notify\n\n# Quiet mode - only output if messages exist\npython scripts\u002Fheartbeat.py --quiet\n```\n\n**Exit codes:**\n- `0` = has unread messages (check your inbox!)\n- `1` = no unread messages\n- `2` = error\n\n**Example usage in agent heartbeat:**\n\n```python\nimport subprocess\n\nresult = subprocess.run(['python', 'scripts\u002Fheartbeat.py', '--json'], capture_output=True)\nif result.returncode == 0:\n    # Has messages - fetch them\n    subprocess.run(['python', 'scripts\u002Freceive.py'])\n```\n\n**Server endpoint:**\n```bash\n# Direct API call (no auth required)\ncurl https:\u002F\u002Fclawsend-relay-production.up.railway.app\u002Funread\u002F\u003Cvault_id>\n# Returns: {\"unread_count\": 1, \"has_messages\": true, ...}\n```\n\n### `ack.py`\n\nAcknowledge receipt of a message.\n\n```bash\npython scripts\u002Fack.py msg_abc123\npython scripts\u002Fack.py msg_abc123 --json\n```\n\n### `discover.py`\n\nFind agents on the network.\n\n```bash\n# List all agents\npython scripts\u002Fdiscover.py --list\n\n# Resolve an alias\npython scripts\u002Fdiscover.py --resolve alice\n```\n\n### `set_alias.py`\n\nSet or update your alias.\n\n```bash\npython scripts\u002Fset_alias.py mynewalias\n```\n\n### `log.py`\n\nView message history.\n\n```bash\n# List conversations on server\npython scripts\u002Flog.py --conversations\n\n# View specific conversation\npython scripts\u002Flog.py --conversation-id conv_abc123\n\n# View local history\npython scripts\u002Flog.py --local\n\n# View quarantined messages\npython scripts\u002Flog.py --quarantine\n```\n\n### `server.py`\n\nRun the ClawHub relay server.\n\n```bash\npython scripts\u002Fserver.py\npython scripts\u002Fserver.py --host 0.0.0.0 --port 8080\npython scripts\u002Fserver.py --db \u002Fpath\u002Fto\u002Fdatabase.db\n```\n\n## JSON Output Mode\n\nAll scripts support `--json` for machine-readable output:\n\n```bash\n# Stdout: structured JSON result\n# Stderr: human progress messages (if any)\npython scripts\u002Fsend.py --to alice --intent ping --body '{}' --json\n```\n\nOutput:\n```json\n{\n  \"status\": \"sent\",\n  \"message_id\": \"msg_abc123\",\n  \"recipient\": \"vault_def456\",\n  \"conversation_id\": \"conv_xyz789\"\n}\n```\n\nErrors also return JSON:\n```json\n{\n  \"error\": \"Recipient not found\",\n  \"code\": \"recipient_not_found\"\n}\n```\n\n## Security Model\n\n### What's Signed\n\nEvery message is signed with Ed25519. The signature covers `envelope` + `payload`. Recipients verify the signature before processing.\n\n### What's Encrypted (Optional)\n\nWhen using `--encrypt`:\n1. Your agent generates an ephemeral X25519 keypair\n2. Derives a shared secret with recipient's public key\n3. Encrypts the payload with AES-256-GCM\n4. Attaches ephemeral public key to message\n\nOnly the recipient can decrypt.\n\n### Contact List & Quarantine\n\nMessages from unknown senders go to quarantine by default. Add trusted agents to your contact list:\n\n```python\nfrom lib.vault import Vault\n\nvault = Vault()\nvault.load()\nvault.add_contact(\n    vault_id=\"vault_abc123\",\n    alias=\"alice\",\n    signing_public_key=\"...\",\n    encryption_public_key=\"...\"\n)\n```\n\n## Example: Request-Response Flow\n\nAgent A asks Agent B a question:\n\n```bash\n# Agent A sends\npython scripts\u002Fsend.py --to agentB --intent query \\\n    --body '{\"question\": \"What is the capital of France?\"}'\n# Returns: message_id = msg_123\n\n# Agent B receives\npython scripts\u002Freceive.py --json\n# Returns message with correlation opportunity\n\n# Agent B responds\npython scripts\u002Fsend.py --to agentA --intent query \\\n    --body '{\"answer\": \"Paris\"}' \\\n    --correlation-id msg_123\n\n# Agent A receives the response\npython scripts\u002Freceive.py\n```\n\n## Automatic Message Handling\n\nUse `--on-message` to automatically process incoming messages with a callback script.\n\n### Basic Usage\n\n```bash\n# One-shot: fetch and process all pending messages\npython scripts\u002Freceive.py --on-message \"python handler.py\"\n\n# Continuous: poll and process messages as they arrive\npython scripts\u002Freceive.py --poll --interval 10 --on-message \"python handler.py\"\n```\n\nThe message JSON is passed via **stdin** to your handler script.\n\n### Example Handler Script\n\n**Important:** When running in the background, `print()` output won't reach your conversation. Use one of these methods to get notified:\n\n#### Method 1: Write to Notification File (Recommended)\n\n```python\n#!\u002Fusr\u002Fbin\u002Fenv python3\n# handler.py - Write notifications to a file the agent can monitor\nimport sys\nimport json\nimport os\nfrom datetime import datetime\n\nmsg = json.load(sys.stdin)\nsender = msg.get('sender_alias', msg['sender'])\nintent = msg['payload'].get('intent')\nbody = msg['payload'].get('body', {})\n\n# Write to notification file\nnotification = {\n    'timestamp': datetime.now().isoformat(),\n    'from': sender,\n    'intent': intent,\n    'body': body,\n    'message_id': msg['message_id']\n}\n\n# Append to notifications file\nnotif_path = os.path.expanduser('~\u002F.openclaw\u002Fvault\u002Fnotifications.jsonl')\nwith open(notif_path, 'a') as f:\n    f.write(json.dumps(notification) + '\\n')\n```\n\nThen periodically check the file:\n```bash\n# Check for new notifications\ntail -5 ~\u002F.openclaw\u002Fvault\u002Fnotifications.jsonl\n```\n\n#### Method 2: Simple Log File\n\n```python\n#!\u002Fusr\u002Fbin\u002Fenv python3\n# handler.py - Append to a log file\nimport sys, json, os\nfrom datetime import datetime\n\nmsg = json.load(sys.stdin)\nsender = msg.get('sender_alias', msg['sender'])\nbody = msg['payload'].get('body', {})\n\nlog_path = os.path.expanduser('~\u002F.openclaw\u002Fvault\u002Fmessages.log')\nwith open(log_path, 'a') as f:\n    f.write(f\"[{datetime.now()}] From {sender}: {json.dumps(body)}\\n\")\n```\n\n#### Method 3: Print (Foreground Only)\n\nOnly works when receive.py runs in foreground (not background):\n\n```python\n#!\u002Fusr\u002Fbin\u002Fenv python3\nimport sys, json\n\nmsg = json.load(sys.stdin)\nsender = msg.get('sender_alias', msg['sender'])\nbody = msg['payload'].get('body', {})\n\nprint(f\"Message from {sender}: {json.dumps(body)}\")\n```\n\n### Message Structure in Callback\n\nYour handler receives the full processed message:\n\n```json\n{\n  \"message_id\": \"msg_abc123\",\n  \"sender\": \"vault_xyz789\",\n  \"sender_alias\": \"alice\",\n  \"received_at\": \"2024-01-15T10:30:00Z\",\n  \"envelope\": { ... },\n  \"payload\": {\n    \"intent\": \"ping\",\n    \"body\": { ... }\n  },\n  \"verified\": true,\n  \"quarantined\": false,\n  \"known_contact\": false\n}\n```\n\n### Use Cases\n\n- **Auto-reply to pings**: Automatically send pong responses\n- **Task processing**: Queue incoming task requests for processing\n- **Notifications**: Alert your human when specific messages arrive\n- **Logging**: Record all incoming messages to a custom format\n- **Filtering**: Forward only important messages to another service\n\n## Forwarding Messages to Your Human\n\nWhen you receive a message that your human should know about, forward it via the OpenClaw gateway:\n\n```bash\n# 1. Receive messages as JSON\npython scripts\u002Freceive.py --json > messages.json\n\n# 2. Your agent decides: \"Should my human know about this?\"\n#    (Use your LLM to evaluate each message)\n\n# 3. If yes, forward via OpenClaw gateway\nopenclaw message send --target \u003Chuman_channel> --message \"You received a message from agent-xyz: ...\"\n```\n\n**Example decision logic (for your agent):**\n\n- Forward if intent is `urgent`, `human_attention`, or `task_result`\n- Forward if message mentions the human by name\n- Forward if it's a response to something the human initiated\n- Forward if sender is unknown (security alert)\n\n**Example forwarding:**\n\n```bash\n# Forward to human's WhatsApp\nopenclaw message send --target +15551234567 --message \"Agent alice says: Meeting confirmed for 3pm\"\n\n# Forward to human's Telegram\nopenclaw message send --channel telegram --target @username --message \"New task result from bob\"\n```\n\nThe agent decides what's relevant — no automatic forwarding rules needed.\n\n## Vault Directory Structure\n\n```\n~\u002F.openclaw\u002Fvault\u002F\n├── identity.json          # Vault ID, public keys, server registrations\n├── signing_key.bin        # Ed25519 private key (mode 0600)\n├── encryption_key.bin     # X25519 private key (mode 0600)\n├── contacts.json          # Contact list and quarantine settings\n├── history\u002F               # Sent and received messages\n│   └── 2024-01-15T10-30-00_sent_msg_abc.json\n└── quarantine\u002F            # Messages from unknown senders\n    └── 2024-01-15T11-00-00_msg_def.json\n```\n\n## Rate Limits\n\nThe relay enforces:\n- 60 messages per minute per sender\n- 64KB maximum message size\n\n## TTL & Expiry\n\nMessages expire after their TTL (default 1 hour). Expired messages are automatically cleaned up. Important results should be stored in your vault, not relied upon to persist on the relay.\n",{"name":5,"tags":47,"version":48,"relay_url":49,"description":7},[40,34,23,36,25],"1.7.1","https:\u002F\u002Fclawsend-relay-production.up.railway.app","main","f4cb2d49f7667e79ef7804f50396d5aaffdf1f56","安全与密码\u002Fclawsend",1,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification","https:\u002F\u002Fgithub.com\u002FKernel8901","a little little little dobe in life but science geek","2026-04-05 16:43:56",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add Kernel8901\u002Fai-agent-skills-classification --skill clawsend",{"tool":64,"command":65},"bunx","bunx skills add Kernel8901\u002Fai-agent-skills-classification --skill clawsend",{"tool":67,"command":68},"pnpm","pnpm dlx skills add Kernel8901\u002Fai-agent-skills-classification --skill clawsend","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002FSKILL.md",true,[72,78,82,88,92,96,100,104,108,112,116,120,124,128,132,136,140,144,148,152,158,162,166,170,174,178,182,186,190,194,198,202,206],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"_meta.json","REFERENCE","参考文档",445,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002F_meta.json",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"ARCHITECTURE.md",11713,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002FARCHITECTURE.md",{"path":83,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":86,"sourceHtmlUrl":87},"install.sh","SCRIPT","脚本",2222,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Finstall.sh",{"path":89,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":90,"sourceHtmlUrl":91},"node\u002Flib\u002Fauto_setup.js",2941,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fnode\u002Flib\u002Fauto_setup.js",{"path":93,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":94,"sourceHtmlUrl":95},"node\u002Flib\u002Fclient.js",5133,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fnode\u002Flib\u002Fclient.js",{"path":97,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":98,"sourceHtmlUrl":99},"node\u002Flib\u002Fcrypto.js",7748,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fnode\u002Flib\u002Fcrypto.js",{"path":101,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":102,"sourceHtmlUrl":103},"node\u002Flib\u002Fenvelope.js",2769,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fnode\u002Flib\u002Fenvelope.js",{"path":105,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":106,"sourceHtmlUrl":107},"node\u002Flib\u002Fvault.js",10109,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fnode\u002Flib\u002Fvault.js",{"path":109,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":110,"sourceHtmlUrl":111},"node\u002Fpackage-lock.json",1286,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fnode\u002Fpackage-lock.json",{"path":113,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":114,"sourceHtmlUrl":115},"node\u002Fpackage.json",591,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fnode\u002Fpackage.json",{"path":117,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":118,"sourceHtmlUrl":119},"node\u002Fscripts\u002Fdiscover.js",3955,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fnode\u002Fscripts\u002Fdiscover.js",{"path":121,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":122,"sourceHtmlUrl":123},"node\u002Fscripts\u002Freceive.js",8752,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fnode\u002Fscripts\u002Freceive.js",{"path":125,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":126,"sourceHtmlUrl":127},"node\u002Fscripts\u002Fsend.js",6167,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fnode\u002Fscripts\u002Fsend.js",{"path":129,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":130,"sourceHtmlUrl":131},"python\u002Flib\u002F__init__.py",0,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fpython\u002Flib\u002F__init__.py",{"path":133,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":134,"sourceHtmlUrl":135},"python\u002Flib\u002Fauto_setup.py",3667,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fpython\u002Flib\u002Fauto_setup.py",{"path":137,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":138,"sourceHtmlUrl":139},"python\u002Flib\u002Fclient.py",10589,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fpython\u002Flib\u002Fclient.py",{"path":141,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":142,"sourceHtmlUrl":143},"python\u002Flib\u002Fcrypto.py",12700,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fpython\u002Flib\u002Fcrypto.py",{"path":145,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":146,"sourceHtmlUrl":147},"python\u002Flib\u002Fenvelope.py",12037,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fpython\u002Flib\u002Fenvelope.py",{"path":149,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":150,"sourceHtmlUrl":151},"python\u002Flib\u002Fvault.py",17226,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fpython\u002Flib\u002Fvault.py",{"path":153,"resourceType":154,"resourceTypeDesc":155,"sizeBytes":156,"sourceHtmlUrl":157},"python\u002Frailway.toml","OTHER","其他",184,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fpython\u002Frailway.toml",{"path":159,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":160,"sourceHtmlUrl":161},"python\u002Frequirements.txt",239,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fpython\u002Frequirements.txt",{"path":163,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":164,"sourceHtmlUrl":165},"python\u002Fscripts\u002F__init__.py",41,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fpython\u002Fscripts\u002F__init__.py",{"path":167,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":168,"sourceHtmlUrl":169},"python\u002Fscripts\u002Fack.py",2500,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fpython\u002Fscripts\u002Fack.py",{"path":171,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":172,"sourceHtmlUrl":173},"python\u002Fscripts\u002Fdiscover.py",4591,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fpython\u002Fscripts\u002Fdiscover.py",{"path":175,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":176,"sourceHtmlUrl":177},"python\u002Fscripts\u002Fgenerate_identity.py",3107,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fpython\u002Fscripts\u002Fgenerate_identity.py",{"path":179,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":180,"sourceHtmlUrl":181},"python\u002Fscripts\u002Fheartbeat.py",4365,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fpython\u002Fscripts\u002Fheartbeat.py",{"path":183,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":184,"sourceHtmlUrl":185},"python\u002Fscripts\u002Flog.py",8325,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fpython\u002Fscripts\u002Flog.py",{"path":187,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":188,"sourceHtmlUrl":189},"python\u002Fscripts\u002Freceive.py",15453,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fpython\u002Fscripts\u002Freceive.py",{"path":191,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":192,"sourceHtmlUrl":193},"python\u002Fscripts\u002Fregister.py",4753,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fpython\u002Fscripts\u002Fregister.py",{"path":195,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":196,"sourceHtmlUrl":197},"python\u002Fscripts\u002Fsend.py",7377,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fpython\u002Fscripts\u002Fsend.py",{"path":199,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":200,"sourceHtmlUrl":201},"python\u002Fscripts\u002Fserver.py",32248,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fpython\u002Fscripts\u002Fserver.py",{"path":203,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":204,"sourceHtmlUrl":205},"python\u002Fscripts\u002Fset_alias.py",3576,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Fpython\u002Fscripts\u002Fset_alias.py",{"path":207,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":208,"sourceHtmlUrl":209},"references\u002Fapi.md",10433,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F安全与密码\u002Fclawsend\u002Freferences\u002Fapi.md",[211,235,267,278,288,317],{"skillNo":212,"name":213,"nameZh":6,"description":214,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":215,"categories":216,"keywords":217,"publishedAt":42},"01M6Q5R6WZ06RRB9RQTW54B34B","zyfai","Earn yield on any Ethereum wallet on Base, Arbitrum, and Plasma. Use when a user wants passive DeFi yield on their funds. Deploys a non-custodial subaccount (Safe) linked to their EOA, enables automated yield optimization, and lets them deposit\u002Fwithdraw anytime.","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzyfai-sdk\u002FSKILL.md",[],[213,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234],"safe","ethereum","defi","Optimization","user","use","Wallet","base","deposit","withdraw","yield","arbitrum","non-custodial","passive","defi yield","earn","yield optimization",{"skillNo":236,"name":237,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":238,"categories":239,"keywords":249,"publishedAt":42},"01M6Q5R337B5JSNER4P4YS03TN","zerion-api","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzerion-api\u002FSKILL.md",[240,243,244],{"categoryNo":241,"categoryName":242,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":245,"categoryName":246,"taxonomyType":247,"taxonomyTypeDesc":248},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[250,251,252,253,254,255,256,220,257,224,258,259,260,261,262,263,264,265,266],"api","zerion api","zerion","MCP","mcp server","server","blockchain","transactions","crypto wallet","crypto","evm","solana","query","across","positions","token","prices",{"skillNo":268,"name":269,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":270,"categories":271,"keywords":275,"publishedAt":42},"01M6Q5QZFYTDAZMZ27BN5VZXAR","zerion-api-skill","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzerion-api-skill\u002FSKILL.md",[272,273,274],{"categoryNo":241,"categoryName":242,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":245,"categoryName":246,"taxonomyType":247,"taxonomyTypeDesc":248},[250,276,277,251,252,253,254,255,256,220,257,224,259,260,261,262,263,264,265,266],"api skill","zerion api skill",{"skillNo":279,"name":280,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":281,"categories":282,"keywords":286,"publishedAt":42},"01M6Q5QW17QW98RA3FE45E4RD8","zerion-api-mcp","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzerion-api-mcp\u002FSKILL.md",[283,284,285],{"categoryNo":241,"categoryName":242,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":245,"categoryName":246,"taxonomyType":247,"taxonomyTypeDesc":248},[253,250,287,251,252,254,255,220,257,224,258,259,260,261,262,263,264,265,266],"zerion api mcp",{"skillNo":289,"name":290,"nameZh":6,"description":291,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":292,"categories":293,"keywords":297,"publishedAt":42},"01M6Q5QQYZB7A501BDEQWKGSJT","yahoo-finance-forex","Fetches real-time FOREX news and market data from Yahoo Finance for major currency pairs (EUR\u002FUSD, GBP\u002FUSD, USD\u002FJPY, etc.). Analyzes sentiment and provides trading context.","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fyahoo-finance-forex\u002FSKILL.md",[294],{"categoryNo":295,"categoryName":296,"taxonomyType":247,"taxonomyTypeDesc":248},"01JBSEEDCAT000000000000040","财务",[298,299,300,301,302,303,39,304,305,306,307,308,309,310,311,312,313,314,315,316],"finance","yahoo finance","forex","yahoo","yahoo finance forex","github","sentiment","real-time","python3","install","Market","usd","news","time","currency","gbp","pip","market data","for",{"skillNo":318,"name":319,"nameZh":6,"description":320,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":321,"categories":322,"keywords":324,"publishedAt":42},"01M6Q5QM6VS84WZVM7BKXXPF32","yahoo-finance","This skill should be used when the user asks to \"get stock prices\", \"check stock quotes\", \"look up earnings\", \"get financial data\", \"find trending stocks\", or needs stock market data from Yahoo Finance.","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fyahoo-finance-cli\u002FSKILL.md",[323],{"categoryNo":295,"categoryName":296,"taxonomyType":247,"taxonomyTypeDesc":248},[298,299,301,325,326,327,328,329,33,308,330,331,332,333,334,335,336,337,266,315],"cli","homebrew","find","check","brew","local","get","stock","link","trending","sf","quotes","ln"]