{
  "schemaVersion": "1.0",
  "item": {
    "slug": "jz-roundtable",
    "name": "Roundtable by JZ",
    "source": "tencent",
    "type": "skill",
    "category": "数据分析",
    "sourceUrl": "https://clawhub.ai/jzOcb/jz-roundtable",
    "canonicalUrl": "https://clawhub.ai/jzOcb/jz-roundtable",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/jz-roundtable",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=jz-roundtable",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.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. 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": "2026-04-23T16:43:11.935Z",
      "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/jz-roundtable"
    },
    "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/jz-roundtable",
    "agentPageUrl": "https://openagent3.xyz/skills/jz-roundtable/agent",
    "manifestUrl": "https://openagent3.xyz/skills/jz-roundtable/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/jz-roundtable/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": "⚠️ 执行方式",
        "body": "直接在主 session 执行，不要用 sessions_spawn。\n\n原因：\n\nRoundtable 是 prompt 技巧，不是长任务\n主 Agent 需要保持对话控制\n避免 subagent announce 路由问题\n更快（省去 spawn 开销）"
      },
      {
        "title": "When to Use",
        "body": "触发词（任一）：\n\nroundtable / roundtable this\n圆桌 / 圆桌会议 / 圆桌讨论\n帮我跑一个 roundtable\n\n场景：\n\nImportant decisions that benefit from multiple viewpoints\nBefore high-risk operations (trading, public posts, major changes)"
      },
      {
        "title": "Default Prompt (动态选角)",
        "body": "针对以下决策进行 roundtable 讨论：\n\n[决策描述]\n\n请：\n1. 评估决策风险级别，选择合适人数（3-8人）\n2. 选择最相关的视角/角色\n3. 每个角色进行两轮讨论（每轮 2-3 句话）\n4. 给出 Consensus（最终建议 + action items）\n\n输出格式：\n## 🗣️ 第一轮\n### [角色1 emoji] [角色名]\n> \"观点...\"\n\n### [角色2 emoji] [角色名]\n> \"观点...\"\n\n## 🗣️ 第二轮\n...\n\n## 📊 Consensus\n- 最终建议\n\n### Action Items (checkbox 格式，便于追踪)\n- [ ] 第一个行动项\n- [ ] 第二个行动项\n- [ ] 第三个行动项"
      },
      {
        "title": "角色参考池",
        "body": "根据任务类型，从以下角色中选择：\n\n角色Emoji擅长领域GrowthStrategist📈增长、scale、ROI、机会RiskGuardian⚠️风险、downside、防御SkepticalOperator🤔执行现实、过度工程检测QualityArchitect🏛️质量、可维护性、长期影响FinanceAnalyst💰成本、现金流、ROI 计算TechEngineer🔧技术可行性、架构、实现ProductManager🎯用户价值、优先级、MVPDataScientist📊数据验证、A/B测试、统计SecurityAuditor🛡️安全、合规、隐私CreativeDirector🎨创意、差异化、品牌MarketAnalyst📉市场情绪、趋势、交易时机DevilsAdvocate😈专门唱反调、找漏洞、压力测试UserAdvocate👤用户视角、体验优先、同理心LegalCounsel⚖️合规、法律风险、条款细节HistorianAnalyst📚历史类比、\"上次怎样\"、模式识别\n\n不需要背这个列表 — 根据任务自然选择合适视角即可。"
      },
      {
        "title": "参与人数指南",
        "body": "决策类型人数说明快速判断3日常决策，不需要太多视角标准决策4-5默认配置，平衡深度和效率高风险决策6-7真钱交易、公开发布、不可逆操作战略级决策8+重大方向调整、年度规划\n\n判断标准：\n\n涉及金额 >$500 → 至少 5 人\n不可逆操作 → 至少 6 人\n公开发布 → 至少 5 人（含 DevilsAdvocate）\n有历史教训的领域 → 必须含 HistorianAnalyst"
      },
      {
        "title": "pre_trade (真钱交易前)",
        "body": "必须包含：\n\n⚠️ RiskGuardian — 风险评估\n💰 FinanceAnalyst — 成本/收益\n🤔 SkepticalOperator — 质疑假设"
      },
      {
        "title": "think_tank_review (高风险操作前)",
        "body": "用于：真钱交易、对外发消息、删除重要文件、修改系统配置\n\n智库只提问题，不做最终决策。"
      },
      {
        "title": "优先级评分（可选）",
        "body": "如果需要对建议排序：\n\npriority = (impact × 0.4) + (confidence × 0.35) + ((100 - effort) × 0.25)\n\nimpact: 预期影响 0-100\nconfidence: 把握程度 0-100\neffort: 工作量 0-100"
      },
      {
        "title": "示例任务 → 角色选择",
        "body": "任务推荐角色人数交易决策RiskGuardian, FinanceAnalyst, MarketAnalyst, SkepticalOperator, HistorianAnalyst5X 帖子内容GrowthStrategist, CreativeDirector, DevilsAdvocate, UserAdvocate4系统架构TechEngineer, SecurityAuditor, SkepticalOperator, QualityArchitect4产品定价FinanceAnalyst, GrowthStrategist, ProductManager, UserAdvocate4内容发布GrowthStrategist, QualityArchitect, RiskGuardian, DevilsAdvocate4合同/协议LegalCounsel, RiskGuardian, FinanceAnalyst, SkepticalOperator4大额交易 (>$1k)RiskGuardian, FinanceAnalyst, MarketAnalyst, HistorianAnalyst, DevilsAdvocate, SkepticalOperator6"
      },
      {
        "title": "注意事项",
        "body": "每个角色 2-3 句话，不要长篇大论\n角色之间要有真正的分歧，不是和稀泥\nConsensus 要有明确的行动建议\n如果所有角色都同意，可能说明问题太简单不需要 roundtable"
      },
      {
        "title": "何时用 Subagent（不是 Roundtable）",
        "body": "以下场景应该用 sessions_spawn：\n\n场景原因长任务 (>3min)不阻塞主对话并行研究多个目标同时跑，结果汇总代码重构/大改动隔离环境批量处理比如扫描 20 个市场\n\nRoundtable 不属于以上任何一种 — 它只是一个 prompt 技巧。"
      }
    ],
    "body": "Roundtable: Multi-Perspective Decision Analysis\n⚠️ 执行方式\n\n直接在主 session 执行，不要用 sessions_spawn。\n\n原因：\n\nRoundtable 是 prompt 技巧，不是长任务\n主 Agent 需要保持对话控制\n避免 subagent announce 路由问题\n更快（省去 spawn 开销）\nWhen to Use\n\n触发词（任一）：\n\nroundtable / roundtable this\n圆桌 / 圆桌会议 / 圆桌讨论\n帮我跑一个 roundtable\n\n场景：\n\nImportant decisions that benefit from multiple viewpoints\nBefore high-risk operations (trading, public posts, major changes)\nDefault Prompt (动态选角)\n针对以下决策进行 roundtable 讨论：\n\n[决策描述]\n\n请：\n1. 评估决策风险级别，选择合适人数（3-8人）\n2. 选择最相关的视角/角色\n3. 每个角色进行两轮讨论（每轮 2-3 句话）\n4. 给出 Consensus（最终建议 + action items）\n\n输出格式：\n## 🗣️ 第一轮\n### [角色1 emoji] [角色名]\n> \"观点...\"\n\n### [角色2 emoji] [角色名]\n> \"观点...\"\n\n## 🗣️ 第二轮\n...\n\n## 📊 Consensus\n- 最终建议\n\n### Action Items (checkbox 格式，便于追踪)\n- [ ] 第一个行动项\n- [ ] 第二个行动项\n- [ ] 第三个行动项\n\n角色参考池\n\n根据任务类型，从以下角色中选择：\n\n角色\tEmoji\t擅长领域\nGrowthStrategist\t📈\t增长、scale、ROI、机会\nRiskGuardian\t⚠️\t风险、downside、防御\nSkepticalOperator\t🤔\t执行现实、过度工程检测\nQualityArchitect\t🏛️\t质量、可维护性、长期影响\nFinanceAnalyst\t💰\t成本、现金流、ROI 计算\nTechEngineer\t🔧\t技术可行性、架构、实现\nProductManager\t🎯\t用户价值、优先级、MVP\nDataScientist\t📊\t数据验证、A/B测试、统计\nSecurityAuditor\t🛡️\t安全、合规、隐私\nCreativeDirector\t🎨\t创意、差异化、品牌\nMarketAnalyst\t📉\t市场情绪、趋势、交易时机\nDevilsAdvocate\t😈\t专门唱反调、找漏洞、压力测试\nUserAdvocate\t👤\t用户视角、体验优先、同理心\nLegalCounsel\t⚖️\t合规、法律风险、条款细节\nHistorianAnalyst\t📚\t历史类比、\"上次怎样\"、模式识别\n\n不需要背这个列表 — 根据任务自然选择合适视角即可。\n\n参与人数指南\n决策类型\t人数\t说明\n快速判断\t3\t日常决策，不需要太多视角\n标准决策\t4-5\t默认配置，平衡深度和效率\n高风险决策\t6-7\t真钱交易、公开发布、不可逆操作\n战略级决策\t8+\t重大方向调整、年度规划\n\n判断标准：\n\n涉及金额 >$500 → 至少 5 人\n不可逆操作 → 至少 6 人\n公开发布 → 至少 5 人（含 DevilsAdvocate）\n有历史教训的领域 → 必须含 HistorianAnalyst\n特殊格式\npre_trade (真钱交易前)\n\n必须包含：\n\n⚠️ RiskGuardian — 风险评估\n💰 FinanceAnalyst — 成本/收益\n🤔 SkepticalOperator — 质疑假设\nthink_tank_review (高风险操作前)\n\n用于：真钱交易、对外发消息、删除重要文件、修改系统配置\n\n智库只提问题，不做最终决策。\n\n优先级评分（可选）\n\n如果需要对建议排序：\n\npriority = (impact × 0.4) + (confidence × 0.35) + ((100 - effort) × 0.25)\n\nimpact: 预期影响 0-100\nconfidence: 把握程度 0-100\neffort: 工作量 0-100\n示例任务 → 角色选择\n任务\t推荐角色\t人数\n交易决策\tRiskGuardian, FinanceAnalyst, MarketAnalyst, SkepticalOperator, HistorianAnalyst\t5\nX 帖子内容\tGrowthStrategist, CreativeDirector, DevilsAdvocate, UserAdvocate\t4\n系统架构\tTechEngineer, SecurityAuditor, SkepticalOperator, QualityArchitect\t4\n产品定价\tFinanceAnalyst, GrowthStrategist, ProductManager, UserAdvocate\t4\n内容发布\tGrowthStrategist, QualityArchitect, RiskGuardian, DevilsAdvocate\t4\n合同/协议\tLegalCounsel, RiskGuardian, FinanceAnalyst, SkepticalOperator\t4\n大额交易 (>$1k)\tRiskGuardian, FinanceAnalyst, MarketAnalyst, HistorianAnalyst, DevilsAdvocate, SkepticalOperator\t6\n注意事项\n每个角色 2-3 句话，不要长篇大论\n角色之间要有真正的分歧，不是和稀泥\nConsensus 要有明确的行动建议\n如果所有角色都同意，可能说明问题太简单不需要 roundtable\n何时用 Subagent（不是 Roundtable）\n\n以下场景应该用 sessions_spawn：\n\n场景\t原因\n长任务 (>3min)\t不阻塞主对话\n并行研究多个目标\t同时跑，结果汇总\n代码重构/大改动\t隔离环境\n批量处理\t比如扫描 20 个市场\n\nRoundtable 不属于以上任何一种 — 它只是一个 prompt 技巧。"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/jzOcb/jz-roundtable",
    "publisherUrl": "https://clawhub.ai/jzOcb/jz-roundtable",
    "owner": "jzOcb",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/jz-roundtable",
    "downloadUrl": "https://openagent3.xyz/downloads/jz-roundtable",
    "agentUrl": "https://openagent3.xyz/skills/jz-roundtable/agent",
    "manifestUrl": "https://openagent3.xyz/skills/jz-roundtable/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/jz-roundtable/agent.md"
  }
}