{
  "schemaVersion": "1.0",
  "item": {
    "slug": "automate",
    "name": "Automate",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/ivangdavila/automate",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/automate",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/automate",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=automate",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "signals.md",
      "templates.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": "2026-04-23T16:43:11.935Z",
      "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/automate"
    },
    "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/automate",
    "agentPageUrl": "https://openagent3.xyz/skills/automate/agent",
    "manifestUrl": "https://openagent3.xyz/skills/automate/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/automate/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": "Core Principle",
        "body": "LLMs are expensive, slow, and probabilistic. Scripts are free, fast, and deterministic.\n\nEvery time you do something twice that could be scripted, you're wasting:\n\nTokens — money burned on solved problems\nTime — seconds/minutes vs milliseconds\nReliability — LLMs fail randomly, scripts fail predictably\n\nCheck signals.md for detection patterns. Check templates.md for common script patterns."
      },
      {
        "title": "The Automation Test",
        "body": "Before doing any task, ask:\n\nIs this deterministic? Same input → same output every time?\nIs this repetitive? Will this happen again?\nIs this rule-based? Can I write down the exact steps?\n\nIf yes to all three → script it, don't LLM it."
      },
      {
        "title": "Script vs LLM Decision Matrix",
        "body": "Task typeScriptLLMFormat conversion (JSON↔YAML)✅❌Text transformation (regex)✅❌File operations (rename, move)✅❌Data validation✅❌API calls with fixed logic✅❌Git workflows✅❌Judgement calls❌✅Creative content❌✅Ambiguous inputs❌✅One-time unique tasks❌✅"
      },
      {
        "title": "Automation Triggers",
        "body": "When you notice yourself:\n\nDoing the same task twice → script it\nWriting similar prompts repeatedly → script the pattern\nFormatting output the same way → script the formatter\nValidating data with same rules → script the validator\nCalling APIs with predictable logic → script the integration"
      },
      {
        "title": "Automation Proposal Format",
        "body": "When you spot an opportunity:\n\n🔧 Automation opportunity\n\nTask: [what you keep doing]\nFrequency: [how often]\nCurrent cost: [tokens/time per run]\n\nProposed script:\n- Language: [bash/python/node]\n- Input: [what it takes]\n- Output: [what it produces]\n- Location: [where to save it]\n\nEstimated savings: [tokens/time saved per month]\n\nShould I write it?"
      },
      {
        "title": "Script Standards",
        "body": "When writing automation:\n\nSingle purpose — one script, one job\nIdempotent — safe to run multiple times\nDocumented — usage in comments at top\nLogged — output what you're doing\nFail loud — exit codes, error messages\nNo secrets hardcoded — env vars or keychain"
      },
      {
        "title": "Tracking Automations",
        "body": "Document what you've built:\n\n### Active Scripts\n- scripts/format-json.sh — JSON prettifier [saved ~2k tokens/week]\n- scripts/deploy-staging.sh — one-command deploy [saved 5min/deploy]\n- scripts/sync-env.sh — env file sync [eliminated manual errors]\n\n### Candidates\n- Weekly report generation — repetitive formatting\n- Log parsing — same grep patterns every time"
      },
      {
        "title": "The 3x Rule",
        "body": "If you do something 3 times, it must become a script.\n\n1st time: Do it, note that it might repeat\n2nd time: Do it, flag as automation candidate\n3rd time: Stop. Write the script first, then run it."
      },
      {
        "title": "Anti-Patterns",
        "body": "Don'tDo insteadRe-prompt for same transformationWrite a script onceUse LLM for data validationWrite validation rulesBurn tokens on formattingUse formatters (prettier, jq, etc.)Ask LLM to remember proceduresDocument in scriptsSolve same problem differently each timeStandardize with automation\n\nEvery script written = permanent token savings. Compound your efficiency."
      }
    ],
    "body": "Core Principle\n\nLLMs are expensive, slow, and probabilistic. Scripts are free, fast, and deterministic.\n\nEvery time you do something twice that could be scripted, you're wasting:\n\nTokens — money burned on solved problems\nTime — seconds/minutes vs milliseconds\nReliability — LLMs fail randomly, scripts fail predictably\n\nCheck signals.md for detection patterns. Check templates.md for common script patterns.\n\nThe Automation Test\n\nBefore doing any task, ask:\n\nIs this deterministic? Same input → same output every time?\nIs this repetitive? Will this happen again?\nIs this rule-based? Can I write down the exact steps?\n\nIf yes to all three → script it, don't LLM it.\n\nScript vs LLM Decision Matrix\nTask type\tScript\tLLM\nFormat conversion (JSON↔YAML)\t✅\t❌\nText transformation (regex)\t✅\t❌\nFile operations (rename, move)\t✅\t❌\nData validation\t✅\t❌\nAPI calls with fixed logic\t✅\t❌\nGit workflows\t✅\t❌\nJudgement calls\t❌\t✅\nCreative content\t❌\t✅\nAmbiguous inputs\t❌\t✅\nOne-time unique tasks\t❌\t✅\nAutomation Triggers\n\nWhen you notice yourself:\n\nDoing the same task twice → script it\nWriting similar prompts repeatedly → script the pattern\nFormatting output the same way → script the formatter\nValidating data with same rules → script the validator\nCalling APIs with predictable logic → script the integration\nAutomation Proposal Format\n\nWhen you spot an opportunity:\n\n🔧 Automation opportunity\n\nTask: [what you keep doing]\nFrequency: [how often]\nCurrent cost: [tokens/time per run]\n\nProposed script:\n- Language: [bash/python/node]\n- Input: [what it takes]\n- Output: [what it produces]\n- Location: [where to save it]\n\nEstimated savings: [tokens/time saved per month]\n\nShould I write it?\n\nScript Standards\n\nWhen writing automation:\n\nSingle purpose — one script, one job\nIdempotent — safe to run multiple times\nDocumented — usage in comments at top\nLogged — output what you're doing\nFail loud — exit codes, error messages\nNo secrets hardcoded — env vars or keychain\nTracking Automations\n\nDocument what you've built:\n\n### Active Scripts\n- scripts/format-json.sh — JSON prettifier [saved ~2k tokens/week]\n- scripts/deploy-staging.sh — one-command deploy [saved 5min/deploy]\n- scripts/sync-env.sh — env file sync [eliminated manual errors]\n\n### Candidates\n- Weekly report generation — repetitive formatting\n- Log parsing — same grep patterns every time\n\nThe 3x Rule\n\nIf you do something 3 times, it must become a script.\n\n1st time: Do it, note that it might repeat\n2nd time: Do it, flag as automation candidate\n3rd time: Stop. Write the script first, then run it.\nAnti-Patterns\nDon't\tDo instead\nRe-prompt for same transformation\tWrite a script once\nUse LLM for data validation\tWrite validation rules\nBurn tokens on formatting\tUse formatters (prettier, jq, etc.)\nAsk LLM to remember procedures\tDocument in scripts\nSolve same problem differently each time\tStandardize with automation\n\nEvery script written = permanent token savings. Compound your efficiency."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ivangdavila/automate",
    "publisherUrl": "https://clawhub.ai/ivangdavila/automate",
    "owner": "ivangdavila",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/automate",
    "downloadUrl": "https://openagent3.xyz/downloads/automate",
    "agentUrl": "https://openagent3.xyz/skills/automate/agent",
    "manifestUrl": "https://openagent3.xyz/skills/automate/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/automate/agent.md"
  }
}