{
  "schemaVersion": "1.0",
  "item": {
    "slug": "autonomous-agent",
    "name": "Autonomous Agent Skills",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/Josephrp/autonomous-agent",
    "canonicalUrl": "https://clawhub.ai/Josephrp/autonomous-agent",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/autonomous-agent",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=autonomous-agent",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "LICENSE.md",
      "package-lock.json",
      "package.json",
      "README.md",
      "SKILL.md",
      "src/attest-aptos-wallet.js"
    ],
    "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/autonomous-agent"
    },
    "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/autonomous-agent",
    "agentPageUrl": "https://openagent3.xyz/skills/autonomous-agent/agent",
    "manifestUrl": "https://openagent3.xyz/skills/autonomous-agent/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/autonomous-agent/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": "CornerStone MCP x402 Skill (for Agents)",
        "body": "This skill gives you (the agent) a set of tools to: create and manage Aptos and EVM wallets, check balances, and call x402-paid MCP tools (stock prediction, backtest, bank linking, agent/borrower scores). Payment is automatic — when a paid tool returns 402, the skill signs, verifies, settles, and retries transparently. You just call the tool; the result comes back."
      },
      {
        "title": "Quick-start workflow",
        "body": "Follow this sequence on first use, then skip to the tool you need:\n\nCheck wallets → call get_wallet_addresses (no args).\nIf empty → call create_aptos_wallet then create_evm_wallet.\nFund → call credit_aptos_wallet (Aptos faucet) and fund_evm_wallet (EVM faucet instructions).\nTell the user to whitelist the returned addresses at https://arnstein.ch/flow.html.\nCheck balance → call balance_aptos (must have USDC for predictions/backtests) and/or balance_evm (must have ETH for bank linking).\nUse paid tools → run_prediction, run_backtest, link_bank_account, or score tools.\n\nImportant: Paid tools will fail with a wallet/whitelist error if the address has not been funded and whitelisted. Always verify wallets and balances first."
      },
      {
        "title": "Wallet management tools (local)",
        "body": "get_wallet_addresses\n\nArgs: none\nReturns: { aptos: [{ address, network }], evm: [{ address, network }] } — may be empty arrays.\nWhen to use: Always call first before any wallet or paid tool action. Determines what exists.\nDecision: If both arrays are empty → create wallets. If only one is empty → create the missing one. If both have entries → proceed to balance check or paid tools.\n\ncreate_aptos_wallet\n\nArgs: { force?: boolean, network?: \"testnet\" | \"mainnet\" } — defaults: force=false, network=testnet.\nReturns: { success, address, network, message } or { success: false, message, addresses } if wallet exists and force=false.\nWhen to use: When get_wallet_addresses returns empty aptos array, or user requests a new wallet.\nError handling: If success: false and wallet already exists, either use the existing wallet or retry with force: true to add another.\n\ncreate_evm_wallet\n\nArgs: { force?: boolean, network?: \"testnet\" | \"mainnet\" } — defaults: force=false, network=testnet.\nReturns: { success, address, network, message } or { success: false, message, addresses }.\nSame pattern as create_aptos_wallet.\n\ncredit_aptos_wallet\n\nArgs: { amount_octas?: number } — default 100,000,000 (= 1 APT).\nReturns on devnet: { success: true, address } (programmatic faucet funded).\nReturns on testnet: { success: true, address, faucet_url } (instructions only; no programmatic faucet).\nPrerequisite: Aptos wallet must exist (create_aptos_wallet first).\nNote: Funded APT is for gas; tools pay in USDC (~6¢). The user may need to acquire testnet USDC separately.\n\nfund_evm_wallet\n\nArgs: none\nReturns: { success: true, address, faucet_url, message } (manual funding instructions).\nPrerequisite: EVM wallet must exist (create_evm_wallet first).\nNote: Returns a Base Sepolia faucet URL. The user must fund manually; there is no programmatic faucet."
      },
      {
        "title": "Balance tools (local)",
        "body": "balance_aptos\n\nArgs: none\nReturns: { address, balances: { usdc, apt } } or { error }.\nWhen to use: Before calling run_prediction, run_backtest, or score tools to confirm sufficient USDC.\n\nbalance_evm\n\nArgs: { chain?: string } — default \"base\". Supported: base, baseSepolia, ethereum, polygon, arbitrum, optimism.\nReturns: { address, chain, balance, symbol } or { error }.\nWhen to use: Before calling link_bank_account to confirm sufficient ETH on Base Sepolia.\nNote: For testnet tools, use chain: \"baseSepolia\"."
      },
      {
        "title": "Paid MCP tools (x402 — payment handled automatically)",
        "body": "All paid tools accept both Aptos and EVM payment. The skill picks the best option or follows PREFERRED_PAYMENT_ORDER. You never see 402 errors — just call the tool and get the result or an error message.\n\nrun_prediction\n\nArgs: { symbol: string, horizon?: number } — symbol is a stock ticker (e.g. \"AAPL\"), horizon is days (default 30).\nReturns: Prediction result object (forecast data, confidence intervals, etc.) or { error }.\nCost: ~6¢ USDC (Aptos or EVM).\nPrerequisite: Funded + whitelisted Aptos or EVM wallet.\nExample call: run_prediction({ symbol: \"AAPL\", horizon: 30 })\n\nrun_backtest\n\nArgs: { symbol: string, startDate?: string, endDate?: string, strategy?: string } — dates in \"YYYY-MM-DD\", strategy defaults to \"chronos\".\nReturns: Backtest result (returns, drawdown, sharpe, etc.) or { error }.\nCost: ~6¢ USDC.\nExample call: run_backtest({ symbol: \"TSLA\", startDate: \"2024-01-01\", endDate: \"2024-12-31\", strategy: \"chronos\" })\n\nlink_bank_account\n\nArgs: none\nReturns: { link_token } or account ID for Plaid bank linking, or { error }.\nCost: ~5¢ (EVM/Base).\nPrerequisite: Funded + whitelisted EVM wallet (Base Sepolia for testnet).\n\nget_agent_reputation_score\n\nArgs: { agent_address?: string, payer_wallet?: string } — both optional; uses the configured wallet if omitted.\nReturns: { reputation_score: number } (e.g. 100) or 403 if not allowlisted, or { error }.\nCost: ~6¢ via x402, or free with lender credits (pass payer_wallet).\n\nget_borrower_score\n\nArgs: { agent_address?: string, payer_wallet?: string } — same pattern.\nReturns: { score: number } (100 base; higher with bank linked) or { error }.\nCost: ~6¢ via x402, or free with lender credits.\n\nget_agent_reputation_score_by_email\n\nArgs: { email: string, payer_wallet?: string } — resolves email to allowlisted agent.\nReturns: { reputation_score: number } or { error }.\nPrerequisite: SCORE_BY_EMAIL_ENABLED must be set on the server. Higher fee.\n\nget_borrower_score_by_email\n\nArgs: { email: string, payer_wallet?: string } — same pattern.\nReturns: { score: number } or { error }.\nPrerequisite: SCORE_BY_EMAIL_ENABLED must be set on the server. Higher fee."
      },
      {
        "title": "\"Run a prediction for X\"",
        "body": "get_wallet_addresses\n  → aptos empty? → create_aptos_wallet → credit_aptos_wallet → tell user to whitelist\n  → aptos exists? → balance_aptos\n    → has USDC? → run_prediction({ symbol: \"X\", horizon: 30 })\n    → no USDC? → tell user to fund USDC, provide address"
      },
      {
        "title": "\"Link a bank account\"",
        "body": "get_wallet_addresses\n  → evm empty? → create_evm_wallet → fund_evm_wallet → tell user to whitelist\n  → evm exists? → balance_evm({ chain: \"baseSepolia\" })\n    → has ETH? → link_bank_account\n    → no ETH? → fund_evm_wallet (returns faucet URL)"
      },
      {
        "title": "\"Get my scores\"",
        "body": "get_wallet_addresses\n  → has aptos or evm? → get_agent_reputation_score + get_borrower_score\n  → neither? → create wallets first, whitelist, then query"
      },
      {
        "title": "Error handling",
        "body": "Error patternMeaningWhat to do\"No Aptos wallet\"Wallet file missingCall create_aptos_wallet\"No EVM wallet\"Wallet file missingCall create_evm_wallet\"already exist. Use force: true\"Wallet exists, not overwritingUse existing wallet, or pass force: true to add another\"Payment verification failed\"Insufficient funds or wrong assetCheck balance; tell user to fund the wallet\"No Aptos wallet configured\" / \"No EVM wallet configured\"Paid tool needs wallet that doesn't existCreate the missing wallet type\"Unsupported chain\"Invalid chain name for balance_evmUse one of: base, baseSepolia, ethereum, polygon, arbitrum, optimism\"timed out after 300s\"MCP call took too longRetry once; the server may be under load\"403\" or \"not allowlisted\"Wallet not whitelistedTell user to whitelist address at https://arnstein.ch/flow.html"
      },
      {
        "title": "Setup (for the human installing this skill)",
        "body": "Install: npm install from repo root. Copy .env.example to .env.\nConfigure: Set wallet paths (APTOS_WALLET_PATH, EVM_WALLET_PATH or EVM_PRIVATE_KEY).\nWallets: Create via tools (create_aptos_wallet, create_evm_wallet) or CLI (node src/setup-aptos.js, node src/setup.js). Fund and whitelist all addresses at https://arnstein.ch/flow.html."
      },
      {
        "title": "CLI commands (from repo root)",
        "body": "TaskCommandGenerate Aptos walletnpm run setup:aptosGenerate EVM walletnpm run setupShow addresses for whitelistnpm run addressesCredit Aptos (devnet)npm run credit:aptos (set APTOS_FAUCET_NETWORK=devnet)EVM balancenpm run balance -- <chain>Transfer ETH/tokensnpm run transfer -- <chain> <to> <amount> [tokenAddress]Swap tokens (Odos)npm run swap -- <chain> <fromToken> <toToken> <amount>Run skill demonpx cornerstone-agent \"Run a 30-day prediction for AAPL\"Attest Aptos walletnpm run attest:aptosAttest EVM walletnpm run attest:evm\n\nSource: FinTechTonic/autonomous-agent"
      }
    ],
    "body": "CornerStone MCP x402 Skill (for Agents)\n\nThis skill gives you (the agent) a set of tools to: create and manage Aptos and EVM wallets, check balances, and call x402-paid MCP tools (stock prediction, backtest, bank linking, agent/borrower scores). Payment is automatic — when a paid tool returns 402, the skill signs, verifies, settles, and retries transparently. You just call the tool; the result comes back.\n\nQuick-start workflow\n\nFollow this sequence on first use, then skip to the tool you need:\n\nCheck wallets → call get_wallet_addresses (no args).\nIf empty → call create_aptos_wallet then create_evm_wallet.\nFund → call credit_aptos_wallet (Aptos faucet) and fund_evm_wallet (EVM faucet instructions).\nTell the user to whitelist the returned addresses at https://arnstein.ch/flow.html.\nCheck balance → call balance_aptos (must have USDC for predictions/backtests) and/or balance_evm (must have ETH for bank linking).\nUse paid tools → run_prediction, run_backtest, link_bank_account, or score tools.\n\nImportant: Paid tools will fail with a wallet/whitelist error if the address has not been funded and whitelisted. Always verify wallets and balances first.\n\nTool reference\nWallet management tools (local)\nget_wallet_addresses\nArgs: none\nReturns: { aptos: [{ address, network }], evm: [{ address, network }] } — may be empty arrays.\nWhen to use: Always call first before any wallet or paid tool action. Determines what exists.\nDecision: If both arrays are empty → create wallets. If only one is empty → create the missing one. If both have entries → proceed to balance check or paid tools.\ncreate_aptos_wallet\nArgs: { force?: boolean, network?: \"testnet\" | \"mainnet\" } — defaults: force=false, network=testnet.\nReturns: { success, address, network, message } or { success: false, message, addresses } if wallet exists and force=false.\nWhen to use: When get_wallet_addresses returns empty aptos array, or user requests a new wallet.\nError handling: If success: false and wallet already exists, either use the existing wallet or retry with force: true to add another.\ncreate_evm_wallet\nArgs: { force?: boolean, network?: \"testnet\" | \"mainnet\" } — defaults: force=false, network=testnet.\nReturns: { success, address, network, message } or { success: false, message, addresses }.\nSame pattern as create_aptos_wallet.\ncredit_aptos_wallet\nArgs: { amount_octas?: number } — default 100,000,000 (= 1 APT).\nReturns on devnet: { success: true, address } (programmatic faucet funded).\nReturns on testnet: { success: true, address, faucet_url } (instructions only; no programmatic faucet).\nPrerequisite: Aptos wallet must exist (create_aptos_wallet first).\nNote: Funded APT is for gas; tools pay in USDC (~6¢). The user may need to acquire testnet USDC separately.\nfund_evm_wallet\nArgs: none\nReturns: { success: true, address, faucet_url, message } (manual funding instructions).\nPrerequisite: EVM wallet must exist (create_evm_wallet first).\nNote: Returns a Base Sepolia faucet URL. The user must fund manually; there is no programmatic faucet.\nBalance tools (local)\nbalance_aptos\nArgs: none\nReturns: { address, balances: { usdc, apt } } or { error }.\nWhen to use: Before calling run_prediction, run_backtest, or score tools to confirm sufficient USDC.\nbalance_evm\nArgs: { chain?: string } — default \"base\". Supported: base, baseSepolia, ethereum, polygon, arbitrum, optimism.\nReturns: { address, chain, balance, symbol } or { error }.\nWhen to use: Before calling link_bank_account to confirm sufficient ETH on Base Sepolia.\nNote: For testnet tools, use chain: \"baseSepolia\".\nPaid MCP tools (x402 — payment handled automatically)\n\nAll paid tools accept both Aptos and EVM payment. The skill picks the best option or follows PREFERRED_PAYMENT_ORDER. You never see 402 errors — just call the tool and get the result or an error message.\n\nrun_prediction\nArgs: { symbol: string, horizon?: number } — symbol is a stock ticker (e.g. \"AAPL\"), horizon is days (default 30).\nReturns: Prediction result object (forecast data, confidence intervals, etc.) or { error }.\nCost: ~6¢ USDC (Aptos or EVM).\nPrerequisite: Funded + whitelisted Aptos or EVM wallet.\nExample call: run_prediction({ symbol: \"AAPL\", horizon: 30 })\nrun_backtest\nArgs: { symbol: string, startDate?: string, endDate?: string, strategy?: string } — dates in \"YYYY-MM-DD\", strategy defaults to \"chronos\".\nReturns: Backtest result (returns, drawdown, sharpe, etc.) or { error }.\nCost: ~6¢ USDC.\nExample call: run_backtest({ symbol: \"TSLA\", startDate: \"2024-01-01\", endDate: \"2024-12-31\", strategy: \"chronos\" })\nlink_bank_account\nArgs: none\nReturns: { link_token } or account ID for Plaid bank linking, or { error }.\nCost: ~5¢ (EVM/Base).\nPrerequisite: Funded + whitelisted EVM wallet (Base Sepolia for testnet).\nget_agent_reputation_score\nArgs: { agent_address?: string, payer_wallet?: string } — both optional; uses the configured wallet if omitted.\nReturns: { reputation_score: number } (e.g. 100) or 403 if not allowlisted, or { error }.\nCost: ~6¢ via x402, or free with lender credits (pass payer_wallet).\nget_borrower_score\nArgs: { agent_address?: string, payer_wallet?: string } — same pattern.\nReturns: { score: number } (100 base; higher with bank linked) or { error }.\nCost: ~6¢ via x402, or free with lender credits.\nget_agent_reputation_score_by_email\nArgs: { email: string, payer_wallet?: string } — resolves email to allowlisted agent.\nReturns: { reputation_score: number } or { error }.\nPrerequisite: SCORE_BY_EMAIL_ENABLED must be set on the server. Higher fee.\nget_borrower_score_by_email\nArgs: { email: string, payer_wallet?: string } — same pattern.\nReturns: { score: number } or { error }.\nPrerequisite: SCORE_BY_EMAIL_ENABLED must be set on the server. Higher fee.\nDecision tree for common tasks\n\"Run a prediction for X\"\nget_wallet_addresses\n  → aptos empty? → create_aptos_wallet → credit_aptos_wallet → tell user to whitelist\n  → aptos exists? → balance_aptos\n    → has USDC? → run_prediction({ symbol: \"X\", horizon: 30 })\n    → no USDC? → tell user to fund USDC, provide address\n\n\"Link a bank account\"\nget_wallet_addresses\n  → evm empty? → create_evm_wallet → fund_evm_wallet → tell user to whitelist\n  → evm exists? → balance_evm({ chain: \"baseSepolia\" })\n    → has ETH? → link_bank_account\n    → no ETH? → fund_evm_wallet (returns faucet URL)\n\n\"Get my scores\"\nget_wallet_addresses\n  → has aptos or evm? → get_agent_reputation_score + get_borrower_score\n  → neither? → create wallets first, whitelist, then query\n\nError handling\nError pattern\tMeaning\tWhat to do\n\"No Aptos wallet\"\tWallet file missing\tCall create_aptos_wallet\n\"No EVM wallet\"\tWallet file missing\tCall create_evm_wallet\n\"already exist. Use force: true\"\tWallet exists, not overwriting\tUse existing wallet, or pass force: true to add another\n\"Payment verification failed\"\tInsufficient funds or wrong asset\tCheck balance; tell user to fund the wallet\n\"No Aptos wallet configured\" / \"No EVM wallet configured\"\tPaid tool needs wallet that doesn't exist\tCreate the missing wallet type\n\"Unsupported chain\"\tInvalid chain name for balance_evm\tUse one of: base, baseSepolia, ethereum, polygon, arbitrum, optimism\n\"timed out after 300s\"\tMCP call took too long\tRetry once; the server may be under load\n\"403\" or \"not allowlisted\"\tWallet not whitelisted\tTell user to whitelist address at https://arnstein.ch/flow.html\nSetup (for the human installing this skill)\nInstall: npm install from repo root. Copy .env.example to .env.\nConfigure: Set wallet paths (APTOS_WALLET_PATH, EVM_WALLET_PATH or EVM_PRIVATE_KEY).\nWallets: Create via tools (create_aptos_wallet, create_evm_wallet) or CLI (node src/setup-aptos.js, node src/setup.js). Fund and whitelist all addresses at https://arnstein.ch/flow.html.\nCLI commands (from repo root)\nTask\tCommand\nGenerate Aptos wallet\tnpm run setup:aptos\nGenerate EVM wallet\tnpm run setup\nShow addresses for whitelist\tnpm run addresses\nCredit Aptos (devnet)\tnpm run credit:aptos (set APTOS_FAUCET_NETWORK=devnet)\nEVM balance\tnpm run balance -- <chain>\nTransfer ETH/tokens\tnpm run transfer -- <chain> <to> <amount> [tokenAddress]\nSwap tokens (Odos)\tnpm run swap -- <chain> <fromToken> <toToken> <amount>\nRun skill demo\tnpx cornerstone-agent \"Run a 30-day prediction for AAPL\"\nAttest Aptos wallet\tnpm run attest:aptos\nAttest EVM wallet\tnpm run attest:evm\n\nSource: FinTechTonic/autonomous-agent"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Josephrp/autonomous-agent",
    "publisherUrl": "https://clawhub.ai/Josephrp/autonomous-agent",
    "owner": "Josephrp",
    "version": "2.1.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/autonomous-agent",
    "downloadUrl": "https://openagent3.xyz/downloads/autonomous-agent",
    "agentUrl": "https://openagent3.xyz/skills/autonomous-agent/agent",
    "manifestUrl": "https://openagent3.xyz/skills/autonomous-agent/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/autonomous-agent/agent.md"
  }
}