{"id":"16561b8c-8ba0-4a59-a5a3-ed6bda5b9632","slug":"clawhub-gechengling-financial-engineer-digital-employee","name":"Financial Engineer Digital Employee","description":"覆盖数据探查、单变量分析、特征工程、LR评分卡、XGBoost/DNN建模、超参数调优、模型解释、多模型对比、分群建模、DeepModel集成全流程。从数据到模型上线的一站式机器学习建模能力。","canonicalUrl":"https://www.xpersona.co/agent/clawhub-gechengling-financial-engineer-digital-employee","sourceUrl":"https://clawhub.ai/gechengling/financial-engineer-digital-employee","homepage":"https://clawhub.ai/gechengling/skills/financial-engineer-digital-employee","source":"CLAWHUB","vendor":{"slug":"clawhub","label":"Clawhub","url":"https://clawhub.ai/gechengling/skills/financial-engineer-digital-employee"},"protocols":["OPENCLEW"],"capabilities":[],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":"2.0.4","freshnessAt":"2026-10-11T15:30:19.955Z","freshnessLabel":"Oct 11, 2026","securityReviewed":true,"openapiReady":false,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"OpenClaw"},{"label":"Freshness","value":"Oct 11, 2026"},{"label":"Vendor","value":"Clawhub"},{"label":"Artifacts","value":"0"},{"label":"Benchmarks","value":"0"},{"label":"Last release","value":"2.0.4"}],"factsPreview":[{"factKey":"vendor","category":"vendor","label":"Vendor","value":"Clawhub","href":"https://clawhub.ai/gechengling/skills/financial-engineer-digital-employee","sourceUrl":"https://clawhub.ai/gechengling/skills/financial-engineer-digital-employee","sourceType":"profile","confidence":"medium","observedAt":"2026-10-11T15:30:20.029Z","isPublic":true},{"factKey":"protocols","category":"compatibility","label":"Protocol compatibility","value":"OpenClaw","href":"https://www.xpersona.co/api/v1/agents/clawhub-gechengling-financial-engineer-digital-employee/contract","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-gechengling-financial-engineer-digital-employee/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-10-11T15:30:20.029Z","isPublic":true},{"factKey":"traction","category":"adoption","label":"Adoption signal","value":"1K downloads","href":"https://clawhub.ai/gechengling/financial-engineer-digital-employee","sourceUrl":"https://clawhub.ai/gechengling/financial-engineer-digital-employee","sourceType":"profile","confidence":"medium","observedAt":"2026-10-11T15:30:20.029Z","isPublic":true},{"factKey":"latest_release","category":"release","label":"Latest release","value":"2.0.4","href":"https://clawhub.ai/gechengling/financial-engineer-digital-employee","sourceUrl":"https://clawhub.ai/gechengling/financial-engineer-digital-employee","sourceType":"release","confidence":"medium","observedAt":"2026-09-21T05:45:48.007Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://www.xpersona.co/api/v1/agents/clawhub-gechengling-financial-engineer-digital-employee/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-gechengling-financial-engineer-digital-employee/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["1K downloads","Trust evidence available"],"agentCard":{"name":"Financial Engineer Digital Employee","description":"覆盖数据探查、单变量分析、特征工程、LR评分卡、XGBoost/DNN建模、超参数调优、模型解释、多模型对比、分群建模、DeepModel集成全流程。从数据到模型上线的一站式机器学习建模能力。","source":"CLAWHUB","sourceId":"clawhub:s17ewqc4f2s6gpcbm88hy7fgvn85kg1g:financial-engineer-digital-employee","homepage":"https://clawhub.ai/gechengling/skills/financial-engineer-digital-employee","repository":"https://clawhub.ai/gechengling/financial-engineer-digital-employee","documentation":"https://www.xpersona.co/agent/clawhub-gechengling-financial-engineer-digital-employee","protocols":["OPENCLEW"],"examples":[{"kind":"example","language":"json","snippet":"{\n  \"skill\": \"data-profiling\",\n  \"status\": \"success\",\n  \"files\": [\n    {\"path\": \".../report.md\", \"role\": \"report\"}\n  ],\n  \"metrics\": {\"n_rows\": 10000, \"n_cols\": 28, \"n_missing_cols\": 5},\n  \"summary\": \"中等规模数据集（10,000行），28 个字段，数值型为主，发现 2 个高缺失字段\"\n}"},{"kind":"example","language":"text","snippet":"特征: age | 分箱方式: 等频 | 分箱数: 10\n\n| 区间          | 样本数  | 占比    | 累计占比 |\n|---------------|---------|---------|----------|\n| Missing       | 156     | 1.56%   | 1.56%    |\n| [18, 23)      | 984     | 9.84%   | 11.40%   |\n| [23, 28)      | 1,012   | 10.12%  | 21.52%   |\n| ...           | ...     | ...     | ...      |"}]}}