{
  "schemaVersion": "1.0",
  "item": {
    "slug": "erpclaw-setup",
    "name": "ERPClaw-Setup",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/ivangdavila/setup",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/setup",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/erpclaw-setup",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=setup",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "agents.md",
      "automation.md",
      "channels.md",
      "gateway.md",
      "memory.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",
      "slug": "erpclaw-setup",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-02T19:36:16.036Z",
      "expiresAt": "2026-05-09T19:36:16.036Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=setup",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=setup",
        "contentDisposition": "attachment; filename=\"setup-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "erpclaw-setup"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/erpclaw-setup"
    },
    "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/erpclaw-setup",
    "agentPageUrl": "https://openagent3.xyz/skills/erpclaw-setup/agent",
    "manifestUrl": "https://openagent3.xyz/skills/erpclaw-setup/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/erpclaw-setup/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": "Quick Reference",
        "body": "TaskLoadMessaging channels (Telegram, WhatsApp, Discord, etc.)channels.mdAgent settings, models, workspacesagents.mdSecurity, auth, DM policies, allowlistssecurity.mdTools: exec, browser, web, mediatools.mdCron, hooks, heartbeats, automationautomation.mdRecommendations by use caserecommendations.mdMemory search, embeddings, QMDmemory.mdGateway: port, TLS, Tailscale, remotegateway.md"
      },
      {
        "title": "First Setup Checklist",
        "body": "Before any config, run:\n\nopenclaw onboard --install-daemon  # Full wizard\nopenclaw doctor                    # Check issues\n\nMinimum viable config:\n\nAt least one channel connected (Telegram recommended for testing)\n Model configured (Anthropic Claude or OpenAI)\n Workspace path set (agents.defaults.workspace)\n Owner allowlist configured (your user ID in channels.*.allowFrom)"
      },
      {
        "title": "Config Locations",
        "body": "FilePurpose~/.openclaw/openclaw.jsonMain config~/.openclaw/.envEnvironment variables~/.openclaw/workspace/Default workspace~/.openclaw/sessions/Session storage\n\nHot reload: Most settings apply instantly. Gateway settings (port, TLS) require restart."
      },
      {
        "title": "Common Mistakes to Avoid",
        "body": "Open DM policy without allowlist → Anyone can message your bot\nNo auth token on remote gateway → Exposed to internet\nModel without fallbacks → Single point of failure\nHeartbeat without delivery target → Lost proactive messages\nexec.security: \"full\" in groups → Dangerous command access"
      },
      {
        "title": "When You're Done",
        "body": "openclaw doctor       # Verify config\nopenclaw status       # Check runtime\nopenclaw health       # Gateway health"
      }
    ],
    "body": "Quick Reference\nTask\tLoad\nMessaging channels (Telegram, WhatsApp, Discord, etc.)\tchannels.md\nAgent settings, models, workspaces\tagents.md\nSecurity, auth, DM policies, allowlists\tsecurity.md\nTools: exec, browser, web, media\ttools.md\nCron, hooks, heartbeats, automation\tautomation.md\nRecommendations by use case\trecommendations.md\nMemory search, embeddings, QMD\tmemory.md\nGateway: port, TLS, Tailscale, remote\tgateway.md\nFirst Setup Checklist\n\nBefore any config, run:\n\nopenclaw onboard --install-daemon  # Full wizard\nopenclaw doctor                    # Check issues\n\n\nMinimum viable config:\n\n At least one channel connected (Telegram recommended for testing)\n Model configured (Anthropic Claude or OpenAI)\n Workspace path set (agents.defaults.workspace)\n Owner allowlist configured (your user ID in channels.*.allowFrom)\nConfig Locations\nFile\tPurpose\n~/.openclaw/openclaw.json\tMain config\n~/.openclaw/.env\tEnvironment variables\n~/.openclaw/workspace/\tDefault workspace\n~/.openclaw/sessions/\tSession storage\n\nHot reload: Most settings apply instantly. Gateway settings (port, TLS) require restart.\n\nCommon Mistakes to Avoid\nOpen DM policy without allowlist → Anyone can message your bot\nNo auth token on remote gateway → Exposed to internet\nModel without fallbacks → Single point of failure\nHeartbeat without delivery target → Lost proactive messages\nexec.security: \"full\" in groups → Dangerous command access\nWhen You're Done\nopenclaw doctor       # Verify config\nopenclaw status       # Check runtime\nopenclaw health       # Gateway health"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ivangdavila/setup",
    "publisherUrl": "https://clawhub.ai/ivangdavila/setup",
    "owner": "ivangdavila",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/erpclaw-setup",
    "downloadUrl": "https://openagent3.xyz/downloads/erpclaw-setup",
    "agentUrl": "https://openagent3.xyz/skills/erpclaw-setup/agent",
    "manifestUrl": "https://openagent3.xyz/skills/erpclaw-setup/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/erpclaw-setup/agent.md"
  }
}