{
  "schemaVersion": "1.0",
  "item": {
    "slug": "openclaw-growth-pack",
    "name": "OpenClaw Growth Pack",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/Dalomeve/openclaw-growth-pack",
    "canonicalUrl": "https://clawhub.ai/Dalomeve/openclaw-growth-pack",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/openclaw-growth-pack",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-growth-pack",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "references/examples.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. 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/openclaw-growth-pack"
    },
    "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-growth-pack",
    "agentPageUrl": "https://openagent3.xyz/skills/openclaw-growth-pack/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-growth-pack/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-growth-pack/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": "OpenClaw Growth Pack",
        "body": "Apply this skill to bootstrap a new OpenClaw instance into a stable, task-completing setup.\n\nUse this workflow in order:\n\nAlign model routing and provider endpoint.\nAlign gateway token values across runtime surfaces.\nInstall anti-stall execution contract in AGENTS.md and HEARTBEAT.md.\nEnable lightweight periodic self-check.\nRun verification gates before calling setup complete.\n\nKeep changes minimal, auditable, and reversible."
      },
      {
        "title": "1) Model Routing Baseline",
        "body": "Use one source of truth in ~/.openclaw/openclaw.json:\n\n{\n  \"models\": {\n    \"mode\": \"merge\",\n    \"providers\": {\n      \"bailian\": {\n        \"baseUrl\": \"https://coding.dashscope.aliyuncs.com/v1\",\n        \"apiKey\": \"YOUR_CODING_PLAN_KEY\"\n      }\n    }\n  },\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"bailian/qwen3-coder-plus\"\n      }\n    }\n  }\n}\n\nRules:\n\nDo not keep coding-intl.dashscope.aliyuncs.com in active config.\nDo not duplicate provider definitions in multiple files unless strictly needed.\nIf ~/.openclaw/agents/main/agent/models.json exists, remove conflicting provider overrides."
      },
      {
        "title": "2) Gateway Token Consistency",
        "body": "Keep all token surfaces aligned:\n\ngateway.auth.token in openclaw.json\ngateway.remote.token in openclaw.json (if present)\nDashboard Control UI token (paste the same value)\n\nPowerShell audit:\n\n$cfg = Get-Content \"$HOME/.openclaw/openclaw.json\" -Raw | ConvertFrom-Json\n$auth = $cfg.gateway.auth.token\n$remote = $cfg.gateway.remote.token\n\"auth.token   = $auth\"\n\"remote.token = $remote\"\nif ($remote -and $auth -ne $remote) { Write-Warning \"Token mismatch in openclaw.json\" }\n\nAfter any token change:\n\nopenclaw gateway restart"
      },
      {
        "title": "3) Anti-Stall Contract",
        "body": "Write or update AGENTS.md with these mandatory constraints:\n\nOutput state on each substantial task: Goal, Progress, Next.\nDo not stop before completion except for explicit blocker or user stop.\nOn failure: retry, then fallback, then report minimal unblock input.\nMulti-step completion must include evidence artifact path or command result summary.\n\nWrite or update HEARTBEAT.md:\n\nEach cycle performs at most 1-2 checks.\nEither produce execution evidence or exactly HEARTBEAT_OK.\nIf queue item exists, execute one concrete step, then log evidence to memory/YYYY-MM-DD.md."
      },
      {
        "title": "4) Lightweight Autonomy Loop",
        "body": "If cron/system events are available, create conservative jobs:\n\nDaily: unfinished-task check.\nWeekly: memory review and friction pattern extraction.\n\nIf cron is unavailable, enforce manual equivalent:\n\nStart-of-day: review tasks/QUEUE.md, pick one actionable item.\nEnd-of-day: append one lesson to memory/YYYY-MM-DD.md."
      },
      {
        "title": "5) Verification Gates (Do Not Skip)",
        "body": "Setup is complete only when all pass:\n\nModel call succeeds with primary route.\nGateway access succeeds without token mismatch.\nA 3+ step task finishes with evidence.\nAt least one blocker path is documented in memory/blocked-items.md.\n\nRecommended evidence:\n\ncommand summary\nartifact path or URL\nfinal status (done or blocked with required input)"
      },
      {
        "title": "6) Rollback",
        "body": "Before edits, create backups:\n\nCopy-Item \"$HOME/.openclaw/openclaw.json\" \"$HOME/.openclaw/openclaw.json.bak\" -Force\n\nRollback:\n\nCopy-Item \"$HOME/.openclaw/openclaw.json.bak\" \"$HOME/.openclaw/openclaw.json\" -Force\nopenclaw gateway restart"
      },
      {
        "title": "References",
        "body": "For concrete command examples and troubleshooting playbooks, read:\n\nreferences/examples.md"
      }
    ],
    "body": "OpenClaw Growth Pack\n\nApply this skill to bootstrap a new OpenClaw instance into a stable, task-completing setup.\n\nUse this workflow in order:\n\nAlign model routing and provider endpoint.\nAlign gateway token values across runtime surfaces.\nInstall anti-stall execution contract in AGENTS.md and HEARTBEAT.md.\nEnable lightweight periodic self-check.\nRun verification gates before calling setup complete.\n\nKeep changes minimal, auditable, and reversible.\n\n1) Model Routing Baseline\n\nUse one source of truth in ~/.openclaw/openclaw.json:\n\n{\n  \"models\": {\n    \"mode\": \"merge\",\n    \"providers\": {\n      \"bailian\": {\n        \"baseUrl\": \"https://coding.dashscope.aliyuncs.com/v1\",\n        \"apiKey\": \"YOUR_CODING_PLAN_KEY\"\n      }\n    }\n  },\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"bailian/qwen3-coder-plus\"\n      }\n    }\n  }\n}\n\n\nRules:\n\nDo not keep coding-intl.dashscope.aliyuncs.com in active config.\nDo not duplicate provider definitions in multiple files unless strictly needed.\nIf ~/.openclaw/agents/main/agent/models.json exists, remove conflicting provider overrides.\n2) Gateway Token Consistency\n\nKeep all token surfaces aligned:\n\ngateway.auth.token in openclaw.json\ngateway.remote.token in openclaw.json (if present)\nDashboard Control UI token (paste the same value)\n\nPowerShell audit:\n\n$cfg = Get-Content \"$HOME/.openclaw/openclaw.json\" -Raw | ConvertFrom-Json\n$auth = $cfg.gateway.auth.token\n$remote = $cfg.gateway.remote.token\n\"auth.token   = $auth\"\n\"remote.token = $remote\"\nif ($remote -and $auth -ne $remote) { Write-Warning \"Token mismatch in openclaw.json\" }\n\n\nAfter any token change:\n\nopenclaw gateway restart\n\n3) Anti-Stall Contract\n\nWrite or update AGENTS.md with these mandatory constraints:\n\nOutput state on each substantial task: Goal, Progress, Next.\nDo not stop before completion except for explicit blocker or user stop.\nOn failure: retry, then fallback, then report minimal unblock input.\nMulti-step completion must include evidence artifact path or command result summary.\n\nWrite or update HEARTBEAT.md:\n\nEach cycle performs at most 1-2 checks.\nEither produce execution evidence or exactly HEARTBEAT_OK.\nIf queue item exists, execute one concrete step, then log evidence to memory/YYYY-MM-DD.md.\n4) Lightweight Autonomy Loop\n\nIf cron/system events are available, create conservative jobs:\n\nDaily: unfinished-task check.\nWeekly: memory review and friction pattern extraction.\n\nIf cron is unavailable, enforce manual equivalent:\n\nStart-of-day: review tasks/QUEUE.md, pick one actionable item.\nEnd-of-day: append one lesson to memory/YYYY-MM-DD.md.\n5) Verification Gates (Do Not Skip)\n\nSetup is complete only when all pass:\n\nModel call succeeds with primary route.\nGateway access succeeds without token mismatch.\nA 3+ step task finishes with evidence.\nAt least one blocker path is documented in memory/blocked-items.md.\n\nRecommended evidence:\n\ncommand summary\nartifact path or URL\nfinal status (done or blocked with required input)\n6) Rollback\n\nBefore edits, create backups:\n\nCopy-Item \"$HOME/.openclaw/openclaw.json\" \"$HOME/.openclaw/openclaw.json.bak\" -Force\n\n\nRollback:\n\nCopy-Item \"$HOME/.openclaw/openclaw.json.bak\" \"$HOME/.openclaw/openclaw.json\" -Force\nopenclaw gateway restart\n\nReferences\n\nFor concrete command examples and troubleshooting playbooks, read:\n\nreferences/examples.md"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Dalomeve/openclaw-growth-pack",
    "publisherUrl": "https://clawhub.ai/Dalomeve/openclaw-growth-pack",
    "owner": "Dalomeve",
    "version": "1.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/openclaw-growth-pack",
    "downloadUrl": "https://openagent3.xyz/downloads/openclaw-growth-pack",
    "agentUrl": "https://openagent3.xyz/skills/openclaw-growth-pack/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-growth-pack/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-growth-pack/agent.md"
  }
}