{
  "schemaVersion": "1.0",
  "item": {
    "slug": "claw-guardirails-skill",
    "name": "ClawGuardrails",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/eveiljuice/claw-guardirails-skill",
    "canonicalUrl": "https://clawhub.ai/eveiljuice/claw-guardirails-skill",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/claw-guardirails-skill",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=claw-guardirails-skill",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "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. 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. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.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/claw-guardirails-skill"
    },
    "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/claw-guardirails-skill",
    "agentPageUrl": "https://openagent3.xyz/skills/claw-guardirails-skill/agent",
    "manifestUrl": "https://openagent3.xyz/skills/claw-guardirails-skill/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/claw-guardirails-skill/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. 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. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "When to Use",
        "body": "Apply this skill whenever a request can:\n\nexecute shell/system commands;\nsend outbound messages/posts to channels;\ntrigger external actions (email, DB, gateways, automation)."
      },
      {
        "title": "Hard Rules",
        "body": "Use safe_exec instead of raw exec.\nUse safe_send instead of direct channel-post tools.\nUse safe_action for generic external/API side effects.\nNever bypass the guardrails resolver with direct destructive tools.\nIf decision is require_approval, stop and wait for explicit approval flow."
      },
      {
        "title": "Input Hygiene",
        "body": "Always provide the narrowest cwd for safe_exec.\nInclude sender/channel/agent context when available.\nKeep command args explicit; do not hide risky flags in shell expansions.\nFor safe_action, include explicit resources where possible."
      },
      {
        "title": "safe_exec",
        "body": "Use for shell commands only after permission resolution.\n\nExpected input shape:\n\n{\n  \"command\": \"git\",\n  \"args\": [\"status\"],\n  \"cwd\": \"/workspace/project\"\n}"
      },
      {
        "title": "safe_send",
        "body": "Use for outbound channel messages.\n\nExpected input shape:\n\n{\n  \"channel\": \"telegram:ops-room\",\n  \"message\": \"Deployment done\",\n  \"channelType\": \"telegram\"\n}"
      },
      {
        "title": "safe_action",
        "body": "Use for side-effect actions that are not plain shell or plain chat send.\n\nExpected input shape:\n\n{\n  \"action\": \"gmail.delete_message\",\n  \"payload\": { \"messageId\": \"...\" },\n  \"resources\": [\n    { \"kind\": \"unknown\", \"value\": \"email-api\", \"operation\": \"delete\" }\n  ]\n}"
      },
      {
        "title": "Decision Handling",
        "body": "allow: continue and return runtime result.\ndeny: return denial with reason code; do not retry with alternate dangerous tools.\nrequire_approval: surface approval id/reason and wait for /approve <id> or RPC approval."
      },
      {
        "title": "Good Defaults",
        "body": "Prefer read-only commands (git status, rg, ls) before mutable ones.\nPropose reversible operations first.\nAsk for confirmation before destructive intent, even if technically allowed."
      }
    ],
    "body": "Guardrails Safe Tools\nWhen to Use\n\nApply this skill whenever a request can:\n\nexecute shell/system commands;\nsend outbound messages/posts to channels;\ntrigger external actions (email, DB, gateways, automation).\nHard Rules\nUse safe_exec instead of raw exec.\nUse safe_send instead of direct channel-post tools.\nUse safe_action for generic external/API side effects.\nNever bypass the guardrails resolver with direct destructive tools.\nIf decision is require_approval, stop and wait for explicit approval flow.\nInput Hygiene\nAlways provide the narrowest cwd for safe_exec.\nInclude sender/channel/agent context when available.\nKeep command args explicit; do not hide risky flags in shell expansions.\nFor safe_action, include explicit resources where possible.\nTool Contracts\nsafe_exec\n\nUse for shell commands only after permission resolution.\n\nExpected input shape:\n\n{\n  \"command\": \"git\",\n  \"args\": [\"status\"],\n  \"cwd\": \"/workspace/project\"\n}\n\nsafe_send\n\nUse for outbound channel messages.\n\nExpected input shape:\n\n{\n  \"channel\": \"telegram:ops-room\",\n  \"message\": \"Deployment done\",\n  \"channelType\": \"telegram\"\n}\n\nsafe_action\n\nUse for side-effect actions that are not plain shell or plain chat send.\n\nExpected input shape:\n\n{\n  \"action\": \"gmail.delete_message\",\n  \"payload\": { \"messageId\": \"...\" },\n  \"resources\": [\n    { \"kind\": \"unknown\", \"value\": \"email-api\", \"operation\": \"delete\" }\n  ]\n}\n\nDecision Handling\nallow: continue and return runtime result.\ndeny: return denial with reason code; do not retry with alternate dangerous tools.\nrequire_approval: surface approval id/reason and wait for /approve <id> or RPC approval.\nGood Defaults\nPrefer read-only commands (git status, rg, ls) before mutable ones.\nPropose reversible operations first.\nAsk for confirmation before destructive intent, even if technically allowed."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/eveiljuice/claw-guardirails-skill",
    "publisherUrl": "https://clawhub.ai/eveiljuice/claw-guardirails-skill",
    "owner": "eveiljuice",
    "version": "0.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/claw-guardirails-skill",
    "downloadUrl": "https://openagent3.xyz/downloads/claw-guardirails-skill",
    "agentUrl": "https://openagent3.xyz/skills/claw-guardirails-skill/agent",
    "manifestUrl": "https://openagent3.xyz/skills/claw-guardirails-skill/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/claw-guardirails-skill/agent.md"
  }
}