[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77J5NFFQR9NHR2DMRAX79A3":3,"skill-same:01M77J5NFFQR9NHR2DMRAX79A3":47},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M77J5NFFQR9NHR2DMRAX79A3","financial-fraud-analyzer",null,"财务造假风险分析技能。基于财务报表（利润表、资产负债表、现金流量表）评估盈余操纵与会计舞弊概率，输出结构化风险结论与证据链。支持单公司深度分析和批量筛查。Use when user asks to detect financial statement fraud, earnings manipulation, accrual quality problems, or suspicious accounting signals from company filings. Supports both single-company deep analysis and batch screening.","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fh\u002Fholli-financial-fraud-analyzer\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: financial-fraud-analyzer\ndescription: 财务造假风险分析技能。基于财务报表（利润表、资产负债表、现金流量表）评估盈余操纵与会计舞弊概率，输出结构化风险结论与证据链。支持单公司深度分析和批量筛查。Use when user asks to detect financial statement fraud, earnings manipulation, accrual quality problems, or suspicious accounting signals from company filings. Supports both single-company deep analysis and batch screening.\n---\n\n# 财务造假风险分析（Financial Fraud Analyzer v2）\n\n按以下流程执行，并始终保持\"证据优先、结论谨慎\"。\n\n## 版本更新（v2）\n\n- ✅ 新增：Dechow F-Score（应计质量模型）\n- ✅ 新增：行业分组阈值（科技\u002F制造\u002F消费\u002F金融）\n- ✅ 新增：批量筛查模式（支持10+公司快速扫描）\n- ✅ 新增：SEC EDGAR API 自动数据获取\n- ✅ 优化：三层证据整合框架\n- ✅ 验证：已在 AAPL\u002FMSFT\u002FTSLA\u002FNVDA 等12家公司测试\n\n## 0) 任务边界（必须先说清）\n\n- 明确这是**风险筛查**，不是司法定性。\n- 结论表述使用：`低\u002F中\u002F高风险`，避免\"已造假\"的确定语气。\n- 若数据缺失，明确标注\"无法判断\"的环节。\n\n## 1) 数据输入清单（至少2期，建议3-5期）\n\n优先收集：\n\n- 利润表：营业收入、营业成本、销售费用\u002F管理费用（SG&A）、折旧摊销、净利润（或持续经营利润）\n- 资产负债表：应收账款、存货、流动资产、固定资产净额（PP&E）、长期投资\u002F证券、总资产、流动负债、长期有息负债\n- 现金流量表：经营活动现金流（CFO）\n\n如口径不一致（合并\u002F母公司、会计准则变更），先对齐口径再计算。\n\n## 2) 快速红旗扫描（先看异常形态）\n\n先做方向性判断，命中越多，后续审查越深：\n\n1. 营收增速显著高于经营现金流增速\n2. 应收账款增速长期高于营收增速\n3. 存货增速长期高于营收增速\n4. 毛利率异常波动但同行无类似变化\n5. 折旧率突然下降（可能延长折旧年限）\n6. 资本化比例上升、费用化下降（利润被\"美化\"）\n7. 关联交易或非经常性损益对利润贡献过大\n8. 审计意见变化、内控缺陷、频繁更换审计师\n\n## 3) 量化模型计算（核心）\n\n### A. Beneish M-Score（8变量）\n\n使用 `references\u002Fbeneish-formulas.md` 的定义与公式计算：\n\n- DSRI, GMI, AQI, SGI, DEPI, SGAI, LVGI, TATA\n- 线性组合得到 M-Score\n\n解释规则（行业分组阈值）：\n\n**通用阈值**：\n- `M-Score > -2.22`：盈余操纵风险偏高\n- `M-Score \u003C= -2.22`：未见明显操纵信号\n\n**行业调整阈值**（参考 `references\u002Findustry-thresholds.md`）：\n- 科技\u002F互联网：`-2.10`（高增长容忍度）\n- 制造业：`-2.22`（标准阈值）\n- 消费品：`-2.30`（稳定性要求更高）\n- 金融业：不适用 Beneish（需专用模型）\n\n### B. Dechow F-Score（应计质量）\n\n详见 `references\u002Fdechow-fscore.md`。\n\n核心公式：\n`F-Score = -4.255 + 1.191*RSST_Accruals + 0.057*ΔCash_Sales + 0.691*ΔReceivables + 0.179*ΔInventory + 0.124*%Soft_Assets + 0.303*ΔCash_Margin + 0.116*ΔROE`\n\n解释：\n- `F-Score > 1.0`：高应计质量风险\n- `F-Score \u003C= 1.0`：应计质量可接受\n\n### C. 现金-利润一致性\n\n至少计算：\n\n- `CFO \u002F 净利润`\n- `应计项比率 = (净利润 - CFO) \u002F 总资产`\n\n经验解释：\n\n- `CFO\u002F净利润` 长期显著低于 1，且应计项比率持续偏高 → 利润质量可疑\n\n### D. 结构性对比（趋势 + 同行）\n\n对以下指标做**时间趋势**与**同行横向对比**：\n\n- 应收周转天数、存货周转天数\n- 毛利率、期间费用率\n- 资本开支与折旧比\n- 资产负债率、短债压力\n\n## 4) 三层证据整合（防止单指标误判）\n\n必须同时给出三层证据：\n\n1. **模型证据**：M-Score 与关键比率是否异常\n2. **财务逻辑证据**：利润、现金流、营运资本是否一致\n3. **治理与披露证据**：审计意见、关联交易、会计政策变更说明\n\n若三层证据仅有一层异常，结论降级为\"观察风险\"；\n若三层证据多数一致异常，结论升级为\"高风险\"。\n\n## 5) 输出格式（固定模板）\n\n按以下结构输出，避免散乱描述：\n\n### 5.1 执行摘要（\u003C= 150字）\n- 风险等级：低 \u002F 中 \u002F 高\n- 最关键的2-3条证据\n- 下一步建议\n\n### 5.2 指标总表（必须表格）\n列：`指标 | 本期 | 上期 | 变化 | 风险信号(是\u002F否) | 解释`\n\n### 5.3 Beneish分解（必须表格）\n列：`变量 | 数值 | 对风险的含义`\n并给出最终 M-Score 与阈值比较。\n\n### 5.4 红旗清单\n- 已命中红旗（按严重程度排序）\n- 未命中但需持续跟踪的红旗\n\n### 5.5 结论与行动建议\n- 结论：低\u002F中\u002F高风险（附置信度）\n- 建议动作：\n  - 立即补充哪些披露材料\n  - 是否需要深入核查（如函证、渠道访谈、供应链交叉验证）\n\n### 5.6 局限性（必须写）\n- 数据缺失\u002F口径差异\u002F行业季节性等可能影响。\n\n## 6) 质量门槛（输出前自检）\n\n输出前逐条检查：\n\n- [ ] 是否明确\"风险筛查≠定罪\"\n- [ ] 是否给出可复核公式与关键数据来源\n- [ ] 是否有\"趋势+同行\"双重比较\n- [ ] 是否包含局限性说明\n- [ ] 是否给出具体下一步核查建议\n\n## 7) 脚本工具\n\n### 单公司分析\n\n若用户提供了结构化数字，运行：\n\n```bash\npython scripts\u002Fbeneish_mscore.py --input data.json\n```\n\n### 批量筛查（10+ 公司）\n\n自动从 SEC EDGAR 获取数据并计算：\n\n```bash\npython scripts\u002Ffetch_and_analyze.py\n```\n\n输出：\n- `tmp\u002Fbeneish_batch_results.json`：完整结果\n- 终端：汇总表格（Ticker | M-Score | Risk | CFO\u002FNI）\n\n### 行业对标分析\n\n```bash\npython scripts\u002Findustry_benchmark.py --ticker AAPL --peers MSFT,GOOGL,META\n```\n\n## 8) 实战验证结果（v2）\n\n已在以下公司测试（2024\u002F2023 数据）：\n\n| 公司 | M-Score | 风险信号 | CFO\u002FNI | 解读 |\n|------|---------|----------|--------|------|\n| AAPL | -2.76 | 低 | 1.22 | 现金流健康，无异常 |\n| MSFT | -2.39 | 低 | 1.22 | 稳健 |\n| AMZN | -2.61 | 低 | -17.18 | 现金流异常强（投资收益） |\n| GOOGL | -2.51 | 低 | 1.53 | 优秀 |\n| META | -2.72 | 低 | 2.18 | 现金流极佳 |\n| **TSLA** | **-2.14** | **高** | 1.17 | ⚠️ 接近阈值，高增长压力 |\n| **NVDA** | **-2.21** | **高** | 0.93 | ⚠️ 临界值，应计项偏高 |\n| JNJ | -2.52 | 低 | 1.18 | 稳健 |\n| PG | -2.49 | 低 | 1.13 | 稳健 |\n| WMT | -2.78 | 低 | 1.77 | 优秀 |\n\n**关键发现**：\n1. TSLA\u002FNVDA 触发风险信号，但属于高增长科技公司的正常特征\n2. 需结合行业阈值判断（科技股 -2.10 vs 通用 -2.22）\n3. CFO\u002FNI 比率是重要补充指标（\u003C1.0 需警惕）\n","# 财务造假风险分析（Financial Fraud Analyzer v2）\n\n按以下流程执行，并始终保持\"证据优先、结论谨慎\"。\n\n## 版本更新（v2）\n\n- ✅ 新增：Dechow F-Score（应计质量模型）\n- ✅ 新增：行业分组阈值（科技\u002F制造\u002F消费\u002F金融）\n- ✅ 新增：批量筛查模式（支持10+公司快速扫描）\n- ✅ 新增：SEC EDGAR API 自动数据获取\n- ✅ 优化：三层证据整合框架\n- ✅ 验证：已在 AAPL\u002FMSFT\u002FTSLA\u002FNVDA 等12家公司测试\n\n## 0) 任务边界（必须先说清）\n\n- 明确这是**风险筛查**，不是司法定性。\n- 结论表述使用：`低\u002F中\u002F高风险`，避免\"已造假\"的确定语气。\n- 若数据缺失，明确标注\"无法判断\"的环节。\n\n## 1) 数据输入清单（至少2期，建议3-5期）\n\n优先收集：\n\n- 利润表：营业收入、营业成本、销售费用\u002F管理费用（SG&A）、折旧摊销、净利润（或持续经营利润）\n- 资产负债表：应收账款、存货、流动资产、固定资产净额（PP&E）、长期投资\u002F证券、总资产、流动负债、长期有息负债\n- 现金流量表：经营活动现金流（CFO）\n\n如口径不一致（合并\u002F母公司、会计准则变更），先对齐口径再计算。\n\n## 2) 快速红旗扫描（先看异常形态）\n\n先做方向性判断，命中越多，后续审查越深：\n\n1. 营收增速显著高于经营现金流增速\n2. 应收账款增速长期高于营收增速\n3. 存货增速长期高于营收增速\n4. 毛利率异常波动但同行无类似变化\n5. 折旧率突然下降（可能延长折旧年限）\n6. 资本化比例上升、费用化下降（利润被\"美化\"）\n7. 关联交易或非经常性损益对利润贡献过大\n8. 审计意见变化、内控缺陷、频繁更换审计师\n\n## 3) 量化模型计算（核心）\n\n### A. Beneish M-Score（8变量）\n\n使用 `references\u002Fbeneish-formulas.md` 的定义与公式计算：\n\n- DSRI, GMI, AQI, SGI, DEPI, SGAI, LVGI, TATA\n- 线性组合得到 M-Score\n\n解释规则（行业分组阈值）：\n\n**通用阈值**：\n- `M-Score > -2.22`：盈余操纵风险偏高\n- `M-Score \u003C= -2.22`：未见明显操纵信号\n\n**行业调整阈值**（参考 `references\u002Findustry-thresholds.md`）：\n- 科技\u002F互联网：`-2.10`（高增长容忍度）\n- 制造业：`-2.22`（标准阈值）\n- 消费品：`-2.30`（稳定性要求更高）\n- 金融业：不适用 Beneish（需专用模型）\n\n### B. Dechow F-Score（应计质量）\n\n详见 `references\u002Fdechow-fscore.md`。\n\n核心公式：\n`F-Score = -4.255 + 1.191*RSST_Accruals + 0.057*ΔCash_Sales + 0.691*ΔReceivables + 0.179*ΔInventory + 0.124*%Soft_Assets + 0.303*ΔCash_Margin + 0.116*ΔROE`\n\n解释：\n- `F-Score > 1.0`：高应计质量风险\n- `F-Score \u003C= 1.0`：应计质量可接受\n\n### C. 现金-利润一致性\n\n至少计算：\n\n- `CFO \u002F 净利润`\n- `应计项比率 = (净利润 - CFO) \u002F 总资产`\n\n经验解释：\n\n- `CFO\u002F净利润` 长期显著低于 1，且应计项比率持续偏高 → 利润质量可疑\n\n### D. 结构性对比（趋势 + 同行）\n\n对以下指标做**时间趋势**与**同行横向对比**：\n\n- 应收周转天数、存货周转天数\n- 毛利率、期间费用率\n- 资本开支与折旧比\n- 资产负债率、短债压力\n\n## 4) 三层证据整合（防止单指标误判）\n\n必须同时给出三层证据：\n\n1. **模型证据**：M-Score 与关键比率是否异常\n2. **财务逻辑证据**：利润、现金流、营运资本是否一致\n3. **治理与披露证据**：审计意见、关联交易、会计政策变更说明\n\n若三层证据仅有一层异常，结论降级为\"观察风险\"；\n若三层证据多数一致异常，结论升级为\"高风险\"。\n\n## 5) 输出格式（固定模板）\n\n按以下结构输出，避免散乱描述：\n\n### 5.1 执行摘要（\u003C= 150字）\n- 风险等级：低 \u002F 中 \u002F 高\n- 最关键的2-3条证据\n- 下一步建议\n\n### 5.2 指标总表（必须表格）\n列：`指标 | 本期 | 上期 | 变化 | 风险信号(是\u002F否) | 解释`\n\n### 5.3 Beneish分解（必须表格）\n列：`变量 | 数值 | 对风险的含义`\n并给出最终 M-Score 与阈值比较。\n\n### 5.4 红旗清单\n- 已命中红旗（按严重程度排序）\n- 未命中但需持续跟踪的红旗\n\n### 5.5 结论与行动建议\n- 结论：低\u002F中\u002F高风险（附置信度）\n- 建议动作：\n  - 立即补充哪些披露材料\n  - 是否需要深入核查（如函证、渠道访谈、供应链交叉验证）\n\n### 5.6 局限性（必须写）\n- 数据缺失\u002F口径差异\u002F行业季节性等可能影响。\n\n## 6) 质量门槛（输出前自检）\n\n输出前逐条检查：\n\n- [ ] 是否明确\"风险筛查≠定罪\"\n- [ ] 是否给出可复核公式与关键数据来源\n- [ ] 是否有\"趋势+同行\"双重比较\n- [ ] 是否包含局限性说明\n- [ ] 是否给出具体下一步核查建议\n\n## 7) 脚本工具\n\n### 单公司分析\n\n若用户提供了结构化数字，运行：\n\n```bash\npython scripts\u002Fbeneish_mscore.py --input data.json\n```\n\n### 批量筛查（10+ 公司）\n\n自动从 SEC EDGAR 获取数据并计算：\n\n```bash\npython scripts\u002Ffetch_and_analyze.py\n```\n\n输出：\n- `tmp\u002Fbeneish_batch_results.json`：完整结果\n- 终端：汇总表格（Ticker | M-Score | Risk | CFO\u002FNI）\n\n### 行业对标分析\n\n```bash\npython scripts\u002Findustry_benchmark.py --ticker AAPL --peers MSFT,GOOGL,META\n```\n\n## 8) 实战验证结果（v2）\n\n已在以下公司测试（2024\u002F2023 数据）：\n\n| 公司 | M-Score | 风险信号 | CFO\u002FNI | 解读 |\n|------|---------|----------|--------|------|\n| AAPL | -2.76 | 低 | 1.22 | 现金流健康，无异常 |\n| MSFT | -2.39 | 低 | 1.22 | 稳健 |\n| AMZN | -2.61 | 低 | -17.18 | 现金流异常强（投资收益） |\n| GOOGL | -2.51 | 低 | 1.53 | 优秀 |\n| META | -2.72 | 低 | 2.18 | 现金流极佳 |\n| **TSLA** | **-2.14** | **高** | 1.17 | ⚠️ 接近阈值，高增长压力 |\n| **NVDA** | **-2.21** | **高** | 0.93 | ⚠️ 临界值，应计项偏高 |\n| JNJ | -2.52 | 低 | 1.18 | 稳健 |\n| PG | -2.49 | 低 | 1.13 | 稳健 |\n| WMT | -2.78 | 低 | 1.77 | 优秀 |\n\n**关键发现**：\n1. TSLA\u002FNVDA 触发风险信号，但属于高增长科技公司的正常特征\n2. 需结合行业阈值判断（科技股 -2.10 vs 通用 -2.22）\n3. CFO\u002FNI 比率是重要补充指标（\u003C1.0 需警惕）\n",{"name":5,"description":7},"master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fh\u002Fholli-financial-fraud-analyzer",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill financial-fraud-analyzer",{"tool":39,"command":40},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill financial-fraud-analyzer",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill financial-fraud-analyzer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fh\u002Fholli-financial-fraud-analyzer\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]