{
  "schemaVersion": "1.0",
  "item": {
    "slug": "openclaw-marshal",
    "name": "Openclaw Marshal",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/AtlasPA/openclaw-marshal",
    "canonicalUrl": "https://clawhub.ai/AtlasPA/openclaw-marshal",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/openclaw-marshal",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-marshal",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "scripts/marshal.py",
      "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": "2026-04-30T16:55:25.780Z",
      "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/openclaw-marshal"
    },
    "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/openclaw-marshal",
    "agentPageUrl": "https://openagent3.xyz/skills/openclaw-marshal/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-marshal/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-marshal/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": "OpenClaw Marshal",
        "body": "Define security policies for your workspace and audit compliance. Check installed skills against command, network, and data handling rules. Generate audit-ready compliance reports."
      },
      {
        "title": "Why This Matters",
        "body": "Agent workspaces accumulate skills that execute commands, access the network, and handle data. Without a defined security policy, there is no way to know whether installed skills comply with your organization's requirements — or whether your workspace itself meets basic security hygiene standards.\n\nThis skill lets you define a policy once and audit everything against it."
      },
      {
        "title": "Initialize Policy",
        "body": "Create a default security policy file (.marshal-policy.json) with sensible defaults.\n\npython3 {baseDir}/scripts/marshal.py policy --init --workspace /path/to/workspace"
      },
      {
        "title": "Show Policy",
        "body": "Display the current active policy.\n\npython3 {baseDir}/scripts/marshal.py policy --show --workspace /path/to/workspace"
      },
      {
        "title": "Policy Summary",
        "body": "Quick overview of loaded policy rules.\n\npython3 {baseDir}/scripts/marshal.py policy --workspace /path/to/workspace"
      },
      {
        "title": "Full Compliance Audit",
        "body": "Audit all installed skills and workspace configuration against the active policy. Reports compliance score, violations, and recommendations.\n\npython3 {baseDir}/scripts/marshal.py audit --workspace /path/to/workspace"
      },
      {
        "title": "Check Specific Skill",
        "body": "Check a single skill against the policy. Reports pass/fail per rule.\n\npython3 {baseDir}/scripts/marshal.py check openclaw-warden --workspace /path/to/workspace"
      },
      {
        "title": "Generate Compliance Report",
        "body": "Produce a formatted, copy-pastable compliance report suitable for audit documentation.\n\npython3 {baseDir}/scripts/marshal.py report --workspace /path/to/workspace"
      },
      {
        "title": "Quick Status",
        "body": "One-line summary: policy loaded, compliance score, critical violations count.\n\npython3 {baseDir}/scripts/marshal.py status --workspace /path/to/workspace"
      },
      {
        "title": "Workspace Auto-Detection",
        "body": "If --workspace is omitted, the script tries:\n\nOPENCLAW_WORKSPACE environment variable\nCurrent directory (if AGENTS.md exists)\n~/.openclaw/workspace (default)"
      },
      {
        "title": "What Gets Checked",
        "body": "CategoryChecksSeverityCommand SafetyDangerous patterns (eval, exec, pipe-to-shell, rm -rf /)CRITICALCommand PolicyBlocked and review-required commands from policyHIGH/MEDIUMNetwork PolicyDomain allow/blocklists, suspicious TLD patternsCRITICAL/HIGHData HandlingSecret scanner installed, PII scanner configuredHIGH/MEDIUMWorkspace Hygiene.gitignore, audit trail (ledger), skill signing (signet)HIGH/MEDIUMConfigurationDebug modes, verbose logging left enabledLOW"
      },
      {
        "title": "Policy Format",
        "body": "The .marshal-policy.json file defines all rules:\n\ncommands.allow — Permitted binaries\ncommands.block — Blocked command patterns\ncommands.review — Commands requiring human review\nnetwork.allow_domains — Permitted network domains\nnetwork.block_domains — Blocked domains\nnetwork.block_patterns — Wildcard domain blocks (e.g., *.tk)\ndata_handling.pii_scan — Require PII scanning\ndata_handling.secret_scan — Require secret scanning\nworkspace.require_gitignore — Require .gitignore\nworkspace.require_audit_trail — Require ledger\nworkspace.require_skill_signing — Require signet"
      },
      {
        "title": "Exit Codes",
        "body": "0 — Compliant, no issues\n1 — Review needed (medium/high findings)\n2 — Critical violations detected"
      },
      {
        "title": "No External Dependencies",
        "body": "Python standard library only. No pip install. No network calls. Everything runs locally."
      },
      {
        "title": "Cross-Platform",
        "body": "Works with OpenClaw, Claude Code, Cursor, and any tool using the Agent Skills specification."
      }
    ],
    "body": "OpenClaw Marshal\n\nDefine security policies for your workspace and audit compliance. Check installed skills against command, network, and data handling rules. Generate audit-ready compliance reports.\n\nWhy This Matters\n\nAgent workspaces accumulate skills that execute commands, access the network, and handle data. Without a defined security policy, there is no way to know whether installed skills comply with your organization's requirements — or whether your workspace itself meets basic security hygiene standards.\n\nThis skill lets you define a policy once and audit everything against it.\n\nCommands\nInitialize Policy\n\nCreate a default security policy file (.marshal-policy.json) with sensible defaults.\n\npython3 {baseDir}/scripts/marshal.py policy --init --workspace /path/to/workspace\n\nShow Policy\n\nDisplay the current active policy.\n\npython3 {baseDir}/scripts/marshal.py policy --show --workspace /path/to/workspace\n\nPolicy Summary\n\nQuick overview of loaded policy rules.\n\npython3 {baseDir}/scripts/marshal.py policy --workspace /path/to/workspace\n\nFull Compliance Audit\n\nAudit all installed skills and workspace configuration against the active policy. Reports compliance score, violations, and recommendations.\n\npython3 {baseDir}/scripts/marshal.py audit --workspace /path/to/workspace\n\nCheck Specific Skill\n\nCheck a single skill against the policy. Reports pass/fail per rule.\n\npython3 {baseDir}/scripts/marshal.py check openclaw-warden --workspace /path/to/workspace\n\nGenerate Compliance Report\n\nProduce a formatted, copy-pastable compliance report suitable for audit documentation.\n\npython3 {baseDir}/scripts/marshal.py report --workspace /path/to/workspace\n\nQuick Status\n\nOne-line summary: policy loaded, compliance score, critical violations count.\n\npython3 {baseDir}/scripts/marshal.py status --workspace /path/to/workspace\n\nWorkspace Auto-Detection\n\nIf --workspace is omitted, the script tries:\n\nOPENCLAW_WORKSPACE environment variable\nCurrent directory (if AGENTS.md exists)\n~/.openclaw/workspace (default)\nWhat Gets Checked\nCategory\tChecks\tSeverity\nCommand Safety\tDangerous patterns (eval, exec, pipe-to-shell, rm -rf /)\tCRITICAL\nCommand Policy\tBlocked and review-required commands from policy\tHIGH/MEDIUM\nNetwork Policy\tDomain allow/blocklists, suspicious TLD patterns\tCRITICAL/HIGH\nData Handling\tSecret scanner installed, PII scanner configured\tHIGH/MEDIUM\nWorkspace Hygiene\t.gitignore, audit trail (ledger), skill signing (signet)\tHIGH/MEDIUM\nConfiguration\tDebug modes, verbose logging left enabled\tLOW\nPolicy Format\n\nThe .marshal-policy.json file defines all rules:\n\ncommands.allow — Permitted binaries\ncommands.block — Blocked command patterns\ncommands.review — Commands requiring human review\nnetwork.allow_domains — Permitted network domains\nnetwork.block_domains — Blocked domains\nnetwork.block_patterns — Wildcard domain blocks (e.g., *.tk)\ndata_handling.pii_scan — Require PII scanning\ndata_handling.secret_scan — Require secret scanning\nworkspace.require_gitignore — Require .gitignore\nworkspace.require_audit_trail — Require ledger\nworkspace.require_skill_signing — Require signet\nExit Codes\n0 — Compliant, no issues\n1 — Review needed (medium/high findings)\n2 — Critical violations detected\nNo External Dependencies\n\nPython standard library only. No pip install. No network calls. Everything runs locally.\n\nCross-Platform\n\nWorks with OpenClaw, Claude Code, Cursor, and any tool using the Agent Skills specification."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/AtlasPA/openclaw-marshal",
    "publisherUrl": "https://clawhub.ai/AtlasPA/openclaw-marshal",
    "owner": "AtlasPA",
    "version": "1.0.2",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/openclaw-marshal",
    "downloadUrl": "https://openagent3.xyz/downloads/openclaw-marshal",
    "agentUrl": "https://openagent3.xyz/skills/openclaw-marshal/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-marshal/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-marshal/agent.md"
  }
}