{
  "schemaVersion": "1.0",
  "item": {
    "slug": "clawwork",
    "name": "Clawwork",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/felipetruman/clawwork",
    "canonicalUrl": "https://clawhub.ai/felipetruman/clawwork",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/clawwork",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=clawwork",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "__init__.py",
      "clawwork.sh",
      "cli.py",
      "quick_task.py"
    ],
    "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": "clawwork",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T17:27:46.268Z",
      "expiresAt": "2026-05-07T17:27:46.268Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=clawwork",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=clawwork",
        "contentDisposition": "attachment; filename=\"clawwork-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "clawwork"
      },
      "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/clawwork"
    },
    "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/clawwork",
    "agentPageUrl": "https://openagent3.xyz/skills/clawwork/agent",
    "manifestUrl": "https://openagent3.xyz/skills/clawwork/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/clawwork/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": "ClawWork Skill",
        "body": "Integração com ClawWork para execução de tarefas profissionais com tracking econômico."
      },
      {
        "title": "O que é",
        "body": "ClawWork transforma o assistente em um \"coworker de IA\" que:\n\nExecuta tarefas profissionais reais (220 tarefas em 44 setores)\nPaga por tokens utilizados\nGanha \"dinheiro\" ao completar tarefas com qualidade\nMantém balance econômico (sobrevivência)"
      },
      {
        "title": "CLI",
        "body": "# Status dos agentes\nskill clawwork status\n\n# Comparar modelos\nskill clawwork compare\n\n# Executar tarefa (requer E2B_API_KEY)\nskill clawwork run -t \"Criar análise de mercado\"\nskill clawwork run -t \"Gerar plano de marketing\" -m kimi-coding/k2p5"
      },
      {
        "title": "Uso Direto",
        "body": "# Via script\n/home/freedom/.openclaw/workspace/skills/clawwork/clawwork.sh status\n\n# Via Python\npython /home/freedom/.openclaw/workspace/skills/clawwork/cli.py status"
      },
      {
        "title": "1. Configurar API Keys",
        "body": "Edite ~/.openclaw/workspace/ClawWork/.env:\n\n# OpenRouter (já configurado ✅)\nOPENAI_API_KEY=sk-or-v1-xxx\nOPENAI_API_BASE=https://openrouter.ai/api/v1\n\n# E2B - necessário para execução de código\n# Obtenha gratuitamente em: https://e2b.dev/\nE2B_API_KEY=e2b_xxx"
      },
      {
        "title": "2. Iniciar Dashboard (opcional)",
        "body": "cd ~/.openclaw/workspace/ClawWork\n./start_dashboard.sh\n\nAcesse: http://localhost:3000"
      },
      {
        "title": "3. Testar",
        "body": "skill clawwork status"
      },
      {
        "title": "Funcionamento",
        "body": "Usuário: /clawwork \"Criar análise de mercado para SaaS B2B\"\n\nZero → Classifica tarefa → [Technology / Software Engineer]\n     → Define valor → [$50 baseado em salário BLS]\n     → Executa via GLM-4.7 + ferramentas\n     → Avalia qualidade → [GPT-4o scoring]\n     → Calcula economics:\n       💸 Custo tokens: $2.50\n       💵 Pagamento: $45.00 (qualidade 90%)\n       📊 Lucro: $42.50\n     → Retorna resultado + métricas"
      },
      {
        "title": "Dados Existentes",
        "body": "Já temos testes anteriores:\n\nGLM-4.7: 157 dias de logs\nKimi K2.5: 220 dias de logs\nQwen3 Max: 220 dias de logs"
      },
      {
        "title": "Localização",
        "body": "ComponentePathClawWork~/.openclaw/workspace/ClawWork/Skill~/.openclaw/workspace/skills/clawwork/Config~/.openclaw/workspace/ClawWork/.envDados~/.openclaw/workspace/ClawWork/livebench/data/"
      },
      {
        "title": "Mais Informações",
        "body": "Repositório: https://github.com/HKUDS/ClawWork\nDataset: GDPVal\nLeaderboard: https://hkuds.github.io/ClawWork/"
      }
    ],
    "body": "ClawWork Skill\n\nIntegração com ClawWork para execução de tarefas profissionais com tracking econômico.\n\nO que é\n\nClawWork transforma o assistente em um \"coworker de IA\" que:\n\nExecuta tarefas profissionais reais (220 tarefas em 44 setores)\nPaga por tokens utilizados\nGanha \"dinheiro\" ao completar tarefas com qualidade\nMantém balance econômico (sobrevivência)\nComandos\nCLI\n# Status dos agentes\nskill clawwork status\n\n# Comparar modelos\nskill clawwork compare\n\n# Executar tarefa (requer E2B_API_KEY)\nskill clawwork run -t \"Criar análise de mercado\"\nskill clawwork run -t \"Gerar plano de marketing\" -m kimi-coding/k2p5\n\nUso Direto\n# Via script\n/home/freedom/.openclaw/workspace/skills/clawwork/clawwork.sh status\n\n# Via Python\npython /home/freedom/.openclaw/workspace/skills/clawwork/cli.py status\n\nSetup\n1. Configurar API Keys\n\nEdite ~/.openclaw/workspace/ClawWork/.env:\n\n# OpenRouter (já configurado ✅)\nOPENAI_API_KEY=sk-or-v1-xxx\nOPENAI_API_BASE=https://openrouter.ai/api/v1\n\n# E2B - necessário para execução de código\n# Obtenha gratuitamente em: https://e2b.dev/\nE2B_API_KEY=e2b_xxx\n\n2. Iniciar Dashboard (opcional)\ncd ~/.openclaw/workspace/ClawWork\n./start_dashboard.sh\n\n\nAcesse: http://localhost:3000\n\n3. Testar\nskill clawwork status\n\nFuncionamento\nUsuário: /clawwork \"Criar análise de mercado para SaaS B2B\"\n\nZero → Classifica tarefa → [Technology / Software Engineer]\n     → Define valor → [$50 baseado em salário BLS]\n     → Executa via GLM-4.7 + ferramentas\n     → Avalia qualidade → [GPT-4o scoring]\n     → Calcula economics:\n       💸 Custo tokens: $2.50\n       💵 Pagamento: $45.00 (qualidade 90%)\n       📊 Lucro: $42.50\n     → Retorna resultado + métricas\n\nDados Existentes\n\nJá temos testes anteriores:\n\nGLM-4.7: 157 dias de logs\nKimi K2.5: 220 dias de logs\nQwen3 Max: 220 dias de logs\nLocalização\nComponente\tPath\nClawWork\t~/.openclaw/workspace/ClawWork/\nSkill\t~/.openclaw/workspace/skills/clawwork/\nConfig\t~/.openclaw/workspace/ClawWork/.env\nDados\t~/.openclaw/workspace/ClawWork/livebench/data/\nMais Informações\nRepositório: https://github.com/HKUDS/ClawWork\nDataset: GDPVal\nLeaderboard: https://hkuds.github.io/ClawWork/"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/felipetruman/clawwork",
    "publisherUrl": "https://clawhub.ai/felipetruman/clawwork",
    "owner": "felipetruman",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/clawwork",
    "downloadUrl": "https://openagent3.xyz/downloads/clawwork",
    "agentUrl": "https://openagent3.xyz/skills/clawwork/agent",
    "manifestUrl": "https://openagent3.xyz/skills/clawwork/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/clawwork/agent.md"
  }
}