{
  "schemaVersion": "1.0",
  "item": {
    "slug": "request-approval",
    "name": "Request Approval",
    "source": "tencent",
    "type": "skill",
    "category": "其他",
    "sourceUrl": "https://clawhub.ai/yconst/request-approval",
    "canonicalUrl": "https://clawhub.ai/yconst/request-approval",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/request-approval",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=request-approval",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "references/EXAMPLES.md",
      "references/TROUBLESHOOTING.md",
      "references/SETUP.md",
      "README.md",
      "SKILL.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "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/request-approval"
    },
    "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/request-approval",
    "agentPageUrl": "https://openagent3.xyz/skills/request-approval/agent",
    "manifestUrl": "https://openagent3.xyz/skills/request-approval/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/request-approval/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": "Request Approval Skill",
        "body": "Use Preloop's request_approval MCP tool to get human approval before executing risky operations. Preloop will notify the user (via Slack, email, mobile apps, etc.) and wait for their response."
      },
      {
        "title": "Setup",
        "body": "Preloop must be configured as an MCP server. See references/SETUP.md for configuration details."
      },
      {
        "title": "ALWAYS Request Approval For:",
        "body": "Deleting anything (files, directories, database records, cloud resources)\nProduction changes (deployments, config changes, environment variables)\nDatabase operations (schema changes, migrations, bulk deletions/updates)\nExternal modifications (creating/merging PRs, posting to APIs, sending emails)\nSecurity changes (permissions, access controls, API keys)\nFinancial operations (purchases, charges, refunds)\nSystem modifications (installing packages, changing system settings, CI/CD changes)"
      },
      {
        "title": "Usually Request Approval For:",
        "body": "Creating pull requests or issues (unless explicitly requested)\nPushing commits to main/master branches\nModifying critical files (package.json, requirements.txt, docker-compose.yml, etc.)\nRunning commands that modify system state\nMaking bulk changes (affecting many files/records)"
      },
      {
        "title": "DON'T Request Approval For:",
        "body": "Reading files or data\nSearching or querying\nCreating feature branches\nRunning tests (in isolated environments)\nMaking commits to feature branches"
      },
      {
        "title": "How to Use",
        "body": "Call the request_approval tool BEFORE executing the risky operation."
      },
      {
        "title": "Parameters",
        "body": "Required:\n\noperation (string): Clear, specific description of what you'll do\n\n✅ Good: \"Delete the logs/2024-01/ directory containing 1,234 log files (2.3GB)\"\n❌ Bad: \"Delete some logs\"\n\n\n\ncontext (string): Additional details about what will be affected\n\n✅ Good: \"This directory contains archived application logs from January 2024. The logs have been backed up to S3. Deleting will free up 2.3GB.\"\n❌ Bad: \"Old logs\"\n\n\n\nreasoning (string): Why this operation is necessary\n\n✅ Good: \"Disk usage is at 92% capacity. These logs are archived in S3 and no longer needed locally.\"\n❌ Bad: \"Need more space\"\n\nOptional:\n\ncaller (string): Auto-populated by Preloop\napproval_policy (string): Specific approval policy name (uses account default if omitted)"
      },
      {
        "title": "Response",
        "body": "The tool returns a string:\n\nApproved: Success message → proceed with the operation\nDenied: \"Approval denied\" or \"Approval denied: {reason}\" → STOP, don't execute\nError: Error message → check configuration or try again"
      },
      {
        "title": "Quick Example",
        "body": "Task: User asks to delete old cache files\n\nYour workflow:\n\nCheck what exists: 3,421 cache files, 1.8GB, from last week\nCall request_approval:\n\noperation: \"Delete the temp-cache/ directory\"\ncontext: \"Contains 3,421 cache files totaling 1.8GB from batch jobs that ran last week. All jobs completed successfully.\"\nreasoning: \"Cache is no longer needed and is consuming disk space. Results are in the database.\"\n\n\nWait for response\nIf \"denied\" in response → tell user it's cancelled, ask for alternatives\nIf approved → proceed with deletion\n\nSee references/EXAMPLES.md for more examples."
      },
      {
        "title": "Decision Framework",
        "body": "When unsure:\n\nCan this be undone easily? NO → Request approval\nCould this cause harm or data loss? YES → Request approval\nIs this modifying production or external systems? YES → Request approval\nWould a human want to review this first? YES → Request approval\nAm I uncertain about the safety? YES → Request approval\n\nGolden Rule: When in doubt, request approval. Better to ask unnecessarily than to cause harm."
      },
      {
        "title": "If Approval is Denied",
        "body": "Stop immediately - do NOT proceed\nCheck for comments - denial may include reasoning\nInform the user - explain why it was cancelled\nLook for alternatives - can you accomplish the goal differently?\nDon't retry - don't ask again unless circumstances change"
      },
      {
        "title": "Best Practices",
        "body": "DO:\n\n✅ Request approval BEFORE executing\n✅ Be specific and detailed\n✅ Include numbers (file count, size, affected records)\n✅ Explain the impact\n✅ Respect denials\n\nDON'T:\n\n❌ Execute first, then ask\n❌ Be vague\n❌ Bundle multiple operations\n❌ Proceed if denied\n❌ Skip approval because you think it's \"probably fine\""
      },
      {
        "title": "Additional Resources",
        "body": "references/SETUP.md - Configuration and MCP server setup\nreferences/EXAMPLES.md - Detailed examples and workflows\nreferences/TROUBLESHOOTING.md - Common errors and solutions\n\nRemember: Safety first! Trust is earned by being cautious and respectful of the user's systems and data."
      }
    ],
    "body": "Request Approval Skill\n\nUse Preloop's request_approval MCP tool to get human approval before executing risky operations. Preloop will notify the user (via Slack, email, mobile apps, etc.) and wait for their response.\n\nSetup\n\nPreloop must be configured as an MCP server. See references/SETUP.md for configuration details.\n\nWhen to Request Approval\nALWAYS Request Approval For:\nDeleting anything (files, directories, database records, cloud resources)\nProduction changes (deployments, config changes, environment variables)\nDatabase operations (schema changes, migrations, bulk deletions/updates)\nExternal modifications (creating/merging PRs, posting to APIs, sending emails)\nSecurity changes (permissions, access controls, API keys)\nFinancial operations (purchases, charges, refunds)\nSystem modifications (installing packages, changing system settings, CI/CD changes)\nUsually Request Approval For:\nCreating pull requests or issues (unless explicitly requested)\nPushing commits to main/master branches\nModifying critical files (package.json, requirements.txt, docker-compose.yml, etc.)\nRunning commands that modify system state\nMaking bulk changes (affecting many files/records)\nDON'T Request Approval For:\nReading files or data\nSearching or querying\nCreating feature branches\nRunning tests (in isolated environments)\nMaking commits to feature branches\nHow to Use\n\nCall the request_approval tool BEFORE executing the risky operation.\n\nParameters\n\nRequired:\n\noperation (string): Clear, specific description of what you'll do\n\n✅ Good: \"Delete the logs/2024-01/ directory containing 1,234 log files (2.3GB)\"\n❌ Bad: \"Delete some logs\"\n\ncontext (string): Additional details about what will be affected\n\n✅ Good: \"This directory contains archived application logs from January 2024. The logs have been backed up to S3. Deleting will free up 2.3GB.\"\n❌ Bad: \"Old logs\"\n\nreasoning (string): Why this operation is necessary\n\n✅ Good: \"Disk usage is at 92% capacity. These logs are archived in S3 and no longer needed locally.\"\n❌ Bad: \"Need more space\"\n\nOptional:\n\ncaller (string): Auto-populated by Preloop\napproval_policy (string): Specific approval policy name (uses account default if omitted)\nResponse\n\nThe tool returns a string:\n\nApproved: Success message → proceed with the operation\nDenied: \"Approval denied\" or \"Approval denied: {reason}\" → STOP, don't execute\nError: Error message → check configuration or try again\nQuick Example\n\nTask: User asks to delete old cache files\n\nYour workflow:\n\nCheck what exists: 3,421 cache files, 1.8GB, from last week\nCall request_approval:\noperation: \"Delete the temp-cache/ directory\"\ncontext: \"Contains 3,421 cache files totaling 1.8GB from batch jobs that ran last week. All jobs completed successfully.\"\nreasoning: \"Cache is no longer needed and is consuming disk space. Results are in the database.\"\nWait for response\nIf \"denied\" in response → tell user it's cancelled, ask for alternatives\nIf approved → proceed with deletion\n\nSee references/EXAMPLES.md for more examples.\n\nDecision Framework\n\nWhen unsure:\n\nCan this be undone easily? NO → Request approval\nCould this cause harm or data loss? YES → Request approval\nIs this modifying production or external systems? YES → Request approval\nWould a human want to review this first? YES → Request approval\nAm I uncertain about the safety? YES → Request approval\n\nGolden Rule: When in doubt, request approval. Better to ask unnecessarily than to cause harm.\n\nIf Approval is Denied\nStop immediately - do NOT proceed\nCheck for comments - denial may include reasoning\nInform the user - explain why it was cancelled\nLook for alternatives - can you accomplish the goal differently?\nDon't retry - don't ask again unless circumstances change\nBest Practices\n\nDO:\n\n✅ Request approval BEFORE executing\n✅ Be specific and detailed\n✅ Include numbers (file count, size, affected records)\n✅ Explain the impact\n✅ Respect denials\n\nDON'T:\n\n❌ Execute first, then ask\n❌ Be vague\n❌ Bundle multiple operations\n❌ Proceed if denied\n❌ Skip approval because you think it's \"probably fine\"\nAdditional Resources\nreferences/SETUP.md - Configuration and MCP server setup\nreferences/EXAMPLES.md - Detailed examples and workflows\nreferences/TROUBLESHOOTING.md - Common errors and solutions\n\nRemember: Safety first! Trust is earned by being cautious and respectful of the user's systems and data."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/yconst/request-approval",
    "publisherUrl": "https://clawhub.ai/yconst/request-approval",
    "owner": "yconst",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/request-approval",
    "downloadUrl": "https://openagent3.xyz/downloads/request-approval",
    "agentUrl": "https://openagent3.xyz/skills/request-approval/agent",
    "manifestUrl": "https://openagent3.xyz/skills/request-approval/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/request-approval/agent.md"
  }
}