{"id":"5ed958a0-1b3a-4d08-9812-f08316397549","entityType":"agent","slug":"clawhub-gechengling-finance-data-analysis","name":"Finance Data Analysis","canonicalUrl":"https://www.xpersona.co/agent/clawhub-gechengling-finance-data-analysis","canonicalPath":"/agent/clawhub-gechengling-finance-data-analysis","generatedAt":"2026-10-10T21:47:43.039Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-10T19:03:00.579Z","emptyReason":null},"description":"Provides AI-driven financial data analysis including KPI tracking, financial statement evaluation, data visualization, and automated reporting for decision s... Skill: Finance Data Analysis Owner: gechengling Summary: Provides AI-driven financial data analysis including KPI tracking, financial statement evaluation, data visualization, and automated reporting for decision s... Tags: banking:5.0.0, dianjin:5.0.0, finance:5.0.0, finance-data-analysis:5.0.3, insurance:5.0.0, latest:5.0.3 Version history: v5.0.3 | 2026-09-15T14:22:39.395Z | user 内容增强与修正（4235→8761字符）：修复 frontmatte","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.3K downloads reported by the source. Last updated 10/10/2026.","installCommand":"clawhub skill install s17ewqc4f2s6gpcbm88hy7fgvn85kg1g:finance-data-analysis","sourceUrl":"https://clawhub.ai/gechengling/finance-data-analysis","homepage":"https://clawhub.ai/gechengling/skills/finance-data-analysis","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/gechengling/finance-data-analysis","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/gechengling/skills/finance-data-analysis","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":62,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Provides AI-driven financial data analysis including KPI tracking, financial statement evaluation, data visualization, and automated reporting for decision s..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-10T19:03:00.579Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T19:03:00.579Z","emptyReason":null},"stars":null,"forks":null,"downloads":1286,"packageName":null,"latestVersion":"5.0.3","tractionLabel":"1.3K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T19:03:00.579Z","emptyReason":null},"lastUpdatedAt":"2026-10-10T19:03:00.579Z","lastCrawledAt":"2026-10-10T19:03:00.579Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-11T19:03:00.579Z","lastVerifiedAt":null,"highlights":[{"version":"5.0.3","createdAt":"2026-09-15T14:22:39.395Z","changelog":"内容增强与修正（4235→8761字符）：修复 frontmatter slug 与实际 slug 不一致（finance-data-analytics→finance-data-analysis）；修复示例代码逻辑错误（ratio_analysis 方法体使用未定义的 data，参数名为 financial_data）；消除安全声明中的重复条目；监管与行业动态更新至 2026-09-15 并扩充至8项；新增指标体系与口径矩阵、数据质量校验六维度表、归因分析三层下钻框架与量价拆解口径、可视化选型对照表、三条参考工作流、常见误用与纠偏表、数据使用纪律（合规底线）；版本号 5.0.2→5.0.3","fileCount":3,"zipByteSize":8817},{"version":"5.0.2","createdAt":"2026-06-04T15:14:37.251Z","changelog":"finance-data-analysis v5.0.2 - Clarified security and data handling policies in SKILL.md, emphasizing no code execution or real data processing; all code is strictly for educational reference. - Updated capabilities: replaced \"no-executable-code\" with \"code-examples-reference\" and added explicit \"allowed-tools: []\" declaration. - Improved and expanded security notice and data privacy disclosures, especially for Python examples and data analysis frameworks. - Removed the \"skill-card.md\" file for consistency and simplification.","fileCount":3,"zipByteSize":4120},{"version":"5.0.1","createdAt":"2026-06-01T15:11:04.342Z","changelog":"Security compliance update: added capability declarations and advisory-only disclaimers to meet ClawHub security scan requirements","fileCount":3,"zipByteSize":7294},{"version":"5.0.0","createdAt":"2026-05-31T02:12:49.420Z","changelog":"融合阿里点金（Dianjin）金融数字员工精髓，版本升级至5.0.0","fileCount":3,"zipByteSize":6970},{"version":"3.0.1","createdAt":"2026-05-25T05:23:43.898Z","changelog":"- Enhanced skill description to clearly outline key features and target users in both English and Chinese. - Added latest financial regulatory updates (as of 2026-05-25), emphasizing new compliance and disclosure standards impacting data analysis. - Explicitly listed industry pain points and mapped each to skill-specific solutions. - Defined and expanded English and Chinese trigger keywords for easier access. - Detailed core capabilities with ready-to-use financial analysis and dashboard Python templates. - Included a disclaimer clarifying the tool’s educational purpose.","fileCount":3,"zipByteSize":3592}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17ewqc4f2s6gpcbm88hy7fgvn85kg1g:finance-data-analysis","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-gechengling-finance-data-analysis/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-gechengling-finance-data-analysis/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-gechengling-finance-data-analysis/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-gechengling-finance-data-analysis/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-gechengling-finance-data-analysis/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-gechengling-finance-data-analysis/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T21:47:43.038Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-gechengling-finance-data-analysis/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-gechengling-finance-data-analysis/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-gechengling-finance-data-analysis/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-gechengling-finance-data-analysis/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-10T19:03:00.579Z","emptyReason":null},"readme":"Skill: Finance Data Analysis\n\nOwner: gechengling\n\nSummary: Provides AI-driven financial data analysis including KPI tracking, financial statement evaluation, data visualization, and automated reporting for decision s...\n\nTags: banking:5.0.0, dianjin:5.0.0, finance:5.0.0, finance-data-analysis:5.0.3, insurance:5.0.0, latest:5.0.3\n\nVersion history:\n\nv5.0.3 | 2026-09-15T14:22:39.395Z | user\n\n内容增强与修正（4235→8761字符）：修复 frontmatter slug 与实际 slug 不一致（finance-data-analytics→finance-data-analysis）；修复示例代码逻辑错误（ratio_analysis 方法体使用未定义的 data，参数名为 financial_data）；消除安全声明中的重复条目；监管与行业动态更新至 2026-09-15 并扩充至8项；新增指标体系与口径矩阵、数据质量校验六维度表、归因分析三层下钻框架与量价拆解口径、可视化选型对照表、三条参考工作流、常见误用与纠偏表、数据使用纪律（合规底线）；版本号 5.0.2→5.0.3\n\nv5.0.2 | 2026-06-04T15:14:37.251Z | auto\n\nfinance-data-analysis v5.0.2\n\n- Clarified security and data handling policies in SKILL.md, emphasizing no code execution or real data processing; all code is strictly for educational reference.\n- Updated capabilities: replaced \"no-executable-code\" with \"code-examples-reference\" and added explicit \"allowed-tools: []\" declaration.\n- Improved and expanded security notice and data privacy disclosures, especially for Python examples and data analysis frameworks.\n- Removed the \"skill-card.md\" file for consistency and simplification.\n\nv5.0.1 | 2026-06-01T15:11:04.342Z | user\n\nSecurity compliance update: added capability declarations and advisory-only disclaimers to meet ClawHub security scan requirements\n\nv5.0.0 | 2026-05-31T02:12:49.420Z | user\n\n融合阿里点金（Dianjin）金融数字员工精髓，版本升级至5.0.0\n\nv3.0.1 | 2026-05-25T05:23:43.898Z | auto\n\n- Enhanced skill description to clearly outline key features and target users in both English and Chinese.\n- Added latest financial regulatory updates (as of 2026-05-25), emphasizing new compliance and disclosure standards impacting data analysis.\n- Explicitly listed industry pain points and mapped each to skill-specific solutions.\n- Defined and expanded English and Chinese trigger keywords for easier access.\n- Detailed core capabilities with ready-to-use financial analysis and dashboard Python templates.\n- Included a disclaimer clarifying the tool’s educational purpose.\n\nArchive index:\n\nArchive v5.0.3: 3 files, 8817 bytes\n\nFiles: skill-card.md (2202b), SKILL.md (15399b), _meta.json (140b)\n\nFile v5.0.3:SKILL.md\n\n---\nname: Financial Industry Data Analysis Expert\nslug: finance-data-analysis\ndescription: AI-powered financial data analysis expert — covers financial statement analysis, KPI tracking, trend analysis, data visualization, and automated reporting. Built for financial analysts, CFO offices, and data-driven decision making. Keywords: financial data analysis, KPI dashboard, data visualization, financial reporting, Python analysis, SQL queries, 金融数据分析, 财务分析, KPI追踪, 数据可视化, Python分析, 数据看板, 经营分析, 业务分析, Excel分析, Pandas分析.\nversion: \"5.0.3\"\nallowed-tools: []\ncapabilities:\n  - educational-reference\n  - advisory-only\n  - requires-human-review\n  - code-examples-reference\n---\n\n# Financial Industry Data Analysis Expert / 金融数据分析专家\n\n> **⚠️ SECURITY NOTICE**\n> - **Type:** Educational reference / analytical framework ONLY\n> - **技能本身不包含可执行代码**，文中 Python / SQL 片段均为**教学示例**，不会被本技能自动运行\n> - **No persistent storage and no background execution** — 本技能不创建、不写入、不读取任何文件\n> - **No credential collection, no PII processing, no system access** — 不接触数据库连接串、账号口令或生产数据\n> - **All outputs require human review before real-world application**\n> - **NOT financial, legal, or insurance advice**\n>\n> **⚠️ 数据安全警告**\n> - 本技能仅提供金融数据分析的方法论参考框架，**不执行任何代码或脚本**\n> - 文中提到的市场数据查询、资金流向分析为**教学方法论展示**，不涉及实际的 API 调用或数据采集\n> - 使用者如将示例代码落地，须自行完成**数据脱敏、权限审批与留痕**，不得将客户身份信息、账户信息带入分析环境\n> - 所有分析结果仅供参考，不构成投资建议或审计意见\n\n> **English:** AI-powered financial data analysis — covers financial statements, KPIs, visualization, and automated reporting.\n>\n> **中文:** 金融数据分析——覆盖财务报表、KPI、可视化、自动化报告。\n\n---\n\n## 金融监管与行业动态（截至 2026-09-15）\n\n| 动态类型 | 内容摘要 | 对分析工作的影响 |\n|---------|---------|----------------|\n| 监管合规 | 数据安全与个人信息保护要求在金融业持续压实，\"最小必要\"原则成为分析取数的默认前提 | 取数环节须可溯源、可解释；分析底稿需记录数据来源与使用范围 |\n| 监管合规 | 金融\"五篇大文章\"（科技、绿色、普惠、养老、数字金融）统计口径逐步细化 | KPI 体系需与监管口径对齐，避免同一指标多口径并存 |\n| 监管合规 | 反洗钱与可疑交易监控的数据要求持续加强 | 客户维度分析需区分\"分析用\"与\"报送用\"两套口径与授权 |\n| 监管合规 | 理财与保险产品信息披露透明度要求提高 | 产品类经营分析需同时满足内部分析与对外披露两类口径 |\n| 行业趋势 | 经营分析从\"报表解读\"转向\"指标归因 + 前瞻预测\" | 分析交付物需包含归因链条与情景假设，而非仅同比环比 |\n| 行业趋势 | 数据中台与指标体系治理成为金融机构标准动作 | 指标定义、口径、责任人需成体系管理，避免\"同名不同义\" |\n| 行业趋势 | 大模型辅助取数、解读与报告生成进入实用阶段 | 生成结果必须人工复核，数字与结论不得直接对外使用 |\n| 技术演进 | 湖仓一体与流批一体降低\"日终批量\"分析的时延 | 日频分析可向准实时演进，但对账与口径一致性要求同步提高 |\n\n> **数据截止**: 2026-09-15 | 来源：国家金融监督管理总局、中国人民银行、中国证监会、中国证券业协会、行业公开研究\n> **声明**: 以上动态供参考，政策与口径以官方最新发布为准\n\n---\n\n## Industry Pain Points / 行业痛点\n\n| Pain Point / 痛点 | Impact / 影响 | Solution / 本Skill解决方案 |\n|------------------|-------------|------------------------|\n| **数据分散** | 数据源多、系统异构，整合耗时且口径不一 | 统一数据模型与指标字典 |\n| **手工报表多** | 月报/季报重复劳动，易出错、难追溯 | 报告模板化 + 生成流程标准化 |\n| **分析浅** | 只看表面数字，缺归因与前瞻 | 三层归因分析框架 |\n| **可视化差** | 图表不直观，管理层读不出结论 | 图表选型对照表 |\n| **口径打架** | 同一指标各部门定义不同 | 指标口径与责任人矩阵 |\n| **合规风险** | 取数越界、留痕缺失 | 数据使用纪律与留痕清单 |\n\n---\n\n## Trigger Keywords / 触发关键词\n\n**English Triggers:** financial data analysis, KPI dashboard, data visualization, financial reporting, Python analysis\n\n**中文触发词：** 数据分析 / 财务分析 / KPI追踪 / 数据可视化 / 自动化报告 / Python分析 / SQL查询 / 数据看板 / 经营分析 / 业绩分析 / 同比环比 / 指标归因 / 报表搭建 / 口径对齐\n\n---\n\n## Core Capabilities / 核心能力\n\n### 1. Financial Analysis Templates / 财务分析模板\n\n> **示例代码（仅供学习参考，非本技能自动执行）**：\n\n```python\nclass FinancialAnalyzer:\n    \"\"\"财务分析引擎（教学示例骨架）\"\"\"\n\n    def income_statement_analysis(self, data: dict) -> dict:\n        \"\"\"损益表分析：趋势 + 结构 + 质量\"\"\"\n        return {\n            \"收入趋势\": self._trend_analysis(data[\"revenue\"]),\n            \"毛利率分析\": self._gross_margin_analysis(data),\n            \"费用结构\": self._expense_breakdown(data),\n            \"利润质量\": self._profit_quality_analysis(data),\n        }\n\n    def ratio_analysis(self, financial_data: dict) -> dict:\n        \"\"\"比率分析：三大类核心比率\"\"\"\n        return {\n            \"盈利能力\": {\n                \"毛利率\": financial_data[\"gross_profit\"] / financial_data[\"revenue\"],\n                \"净利率\": financial_data[\"net_profit\"] / financial_data[\"revenue\"],\n                \"ROE\": financial_data[\"net_profit\"] / financial_data[\"equity\"],\n            },\n            \"运营效率\": {\n                \"存货周转\": financial_data[\"cogs\"] / financial_data[\"inventory\"],\n                \"应收账款周转\": financial_data[\"revenue\"] / financial_data[\"ar\"],\n            },\n            \"偿债能力\": {\n                \"流动比率\": financial_data[\"current_assets\"] / financial_data[\"current_liabilities\"],\n                \"资产负债率\": financial_data[\"total_liabilities\"] / financial_data[\"total_assets\"],\n            },\n        }\n```\n\n```sql\n-- 示例：月度经营指标口径对齐查询（教学示例，未连接任何真实库）\nSELECT 月份,\n       业务线,\n       SUM(保费收入)                     AS 保费收入,\n       SUM(已赚保费)                     AS 已赚保费,\n       SUM(赔付支出)                     AS 赔付支出,\n       ROUND(SUM(赔付支出) / NULLIF(SUM(已赚保费), 0), 4) AS 综合赔付率\nFROM   dwd_经营明细\nWHERE  月份 BETWEEN '2026-06' AND '2026-08'\n  AND  数据版本 = '月结最终版'          -- 口径冻结标记，避免\"月中数\"混入\nGROUP  BY 月份, 业务线\nORDER  BY 月份, 业务线;\n```\n\n**要点三条（实操最常踩）**：\n1. **先锁口径再取数**——同一个\"保费收入\"可能是签单口径、承保口径或已赚口径，务必在取数前书面确认。\n2. **区分时点表与时期表**——资产负债表项目是时点值（期末），损益表项目是时期值（区间），混算必错。\n3. **比率分母不得为零或负**——用 `NULLIF` 或显式判断兜底，否则报表会出现 `inf` 或符号颠倒。\n\n### 2. Dashboard Templates / 数据看板模板\n\n```python\nDASHBOARD_TEMPLATES = {\n    \"CFO驾驶舱\": {\n        \"audience\": \"董事会 / 经营班子\",\n        \"refresh\": \"月度为主，关键指标日频\",\n        \"widgets\": [\n            {\"type\": \"kpi_card\",  \"metrics\": [\"营收\", \"利润\", \"ROE\"]},\n            {\"type\": \"line_chart\", \"data\": \"收入趋势\"},\n            {\"type\": \"bar_chart\", \"data\": \"各业务线收入\"},\n            {\"type\": \"waterfall\", \"data\": \"利润变动归因\"},\n            {\"type\": \"gauge\",     \"data\": \"KPI完成率\"},\n        ],\n    },\n    \"业务分析看板\": {\n        \"audience\": \"业务条线负责人\",\n        \"refresh\": \"周度 / 日频\",\n        \"widgets\": [\n            {\"type\": \"funnel\",    \"data\": \"转化漏斗\"},\n            {\"type\": \"heat_map\",  \"data\": \"客户活跃度\"},\n            {\"type\": \"pie_chart\", \"data\": \"客户分布\"},\n            {\"type\": \"trend\",     \"data\": \"关键指标趋势\"},\n        ],\n    },\n}\n```\n\n### 3. 指标体系与口径矩阵\n\n| 分析层级 | 典型指标 | 口径要点 | 责任部门 |\n|---------|---------|---------|---------|\n| 规模 | 保费收入、资产总额、客户数 | 时点 vs 时期；含税 vs 不含税 | 财务 / 业务 |\n| 效益 | 综合成本率、费用率、ROE | 分子分母同口径、同期间 | 财务 / 精算 |\n| 质量 | 退保率、继续率、赔付率 | 分母统一为已赚口径 | 精算 / 业务 |\n| 效率 | 人均产能、单均成本、周转天数 | 人力口径需与 HR 系统一致 | 人力资源 / 财务 |\n| 结构 | 产品结构、渠道结构、区域结构 | 占比之和须为 100%（含\"其他\"） | 业务 / 战略 |\n| 前瞻 | 准备金、剩余边际、隐含价值 | 需注明精算假设版本 | 精算 |\n\n**口径管理三条铁律**：\n1. 每个指标有且只有一个**口径定义书**，含公式、数据源、更新频率、责任人。\n2. 口径变更必须**版本化**并在报表脚注标注生效月份，避免前后不可比。\n3. 同名不同义的指标**必须改名**（如\"新单保费（签单口径）\"），不得靠口头解释。\n\n### 4. 数据质量校验维度\n\n| 维度 | 检查内容 | 典型校验规则 | 处理动作 |\n|-----|---------|-------------|---------|\n| 完整性 | 是否有缺失记录/空值 | 主键非空、日切分区齐全 | 回溯补数或标注\"数据不全\" |\n| 唯一性 | 是否有重复 | 主键唯一、去重前后行数比对 | 定位重复源，去重留痕 |\n| 准确性 | 数值是否落在合理区间 | 比率在 0–1、金额非负 | 异常值单独列出，不静默剔除 |\n| 一致性 | 跨表/跨系统是否一致 | 总分核对、明细汇总对总账 | 差异挂账，注明待查 |\n| 及时性 | 是否在约定时间到位 | 分区更新时间戳检查 | 标注数据版本与截止时点 |\n| 有效性 | 是否符合业务约束 | 日期不外溢、枚举值在字典内 | 剔除或映射，并记录映射表 |\n\n### 5. 归因分析框架（三层下钻）\n\n| 层级 | 问题 | 方法 | 输出 |\n|-----|-----|-----|-----|\n| 第一层：是什么 | 指标变了多少？ | 同比 / 环比 / 预算差异 | 差异金额与差异率 |\n| 第二层：为什么 | 变化由哪些因素构成？ | 量价拆解、结构拆解、贡献度分析 | 各因素贡献额与贡献占比 |\n| 第三层：怎么办 | 哪些因素可控？ | 可控/不可控分离、敏感性测算 | 建议动作与预期影响区间 |\n\n**量价拆解示例（教学口径）**：\n- 收入变动 = 量变动贡献 + 价变动贡献 + 结构变动贡献 + 交叉项\n- 量价交叉项必须**单独列示**，不得并入任一项，否则贡献度之和会失真。\n\n### 6. 可视化选型对照表\n\n| 分析目的 | 推荐图表 | 不推荐 | 原因 |\n|---------|---------|-------|-----|\n| 看趋势 | 折线图、面积图 | 饼图 | 饼图无法表达时间维度 |\n| 看结构 | 堆叠柱、条形图 | 3D 饼图 | 3D 扭曲比例感知 |\n| 看对比 | 分组柱、子弹图 | 雷达图（超 5 维） | 维度多则不可读 |\n| 看归因 | 瀑布图、桥图 | 折线图 | 折线无法表达加减关系 |\n| 看分布 | 箱线图、直方图 | 均值单点 | 均值掩盖分布与长尾 |\n| 看相关性 | 散点图、气泡图 | 双轴折线（量纲差异大时） | 双轴易造成虚假相关 |\n| 看达成 | 仪表盘、进度条 | 纯数字 | 缺少目标参照 |\n\n---\n\n## Reference Workflows / 参考工作流\n\n### Workflow A：月度经营分析报告（标准路径）\n\n1. **明确问题**——本次要回答哪 3 个问题？避免\"什么都写\"。\n2. **锁定口径与数据版本**——书面确认指标定义、数据截止时点、版本标记。\n3. **数据校验**——按第 4 节六维度过一遍，输出校验清单。\n4. **分析**——先第一层差异，再第二层归因，最后第三层建议。\n5. **成文**——结论先行，图表附后，口径与数据源在脚注写明。\n6. **复核**——由业务方与财务方各复核一次，留存复核记录。\n\n### Workflow B：指标体系搭建（从零开始）\n\n| 步骤 | 动作 | 交付物 |\n|-----|-----|-------|\n| 1 | 梳理管理层最常问的 10 个问题 | 问题清单 |\n| 2 | 把问题翻译成指标 | 候选指标池 |\n| 3 | 为每个指标写口径定义书 | 指标字典 |\n| 4 | 指定数据源与责任人 | 数据源映射表 |\n| 5 | 试跑并核对历史数据 | 历史回溯验证报告 |\n| 6 | 上线并建立变更流程 | 口径变更登记机制 |\n\n### Workflow C：临时取数请求处理\n\n1. 确认请求方**权限与用途**（是否涉及客户信息）。\n2. 确认**口径与时间范围**，避免反复返工。\n3. 优先复用既有指标，不新建口径。\n4. 交付时附**数据说明**（口径、截止时点、已知局限）。\n5. 涉及敏感字段时**脱敏或聚合**，必要时走审批流程。\n\n---\n\n## 常见误用与纠偏\n\n| 误用 | 后果 | 正确做法 |\n|-----|-----|---------|\n| 拿\"月中数\"当\"月结数\" | 结论反复推翻 | 明确数据版本，只用冻结版本出结论 |\n| 用同比解释结构性变化 | 误判为经营波动 | 结构变化优先做结构拆解 |\n| 比率分母为零未兜底 | 报表出现 `inf` / 符号颠倒 | 分母加 `NULLIF` 或显式判断 |\n| 时点值与时期值混算 | 逻辑错误且难发现 | 明确标注时点/时期，分别处理 |\n| 异常值直接剔除 | 掩盖真实问题 | 单独列示并说明处置理由 |\n| 只报均值不报分布 | 管理层误判风险 | 关键指标给均值 + 分位数 |\n| 图表追求美观牺牲准确 | 误导决策 | 坐标轴从零起（柱图），标注口径 |\n| 把模型输出当结论 | 合规与准确性风险 | 人工复核后方可对外使用 |\n\n---\n\n## 数据使用纪律（合规底线）\n\n- **最小必要**：只取完成分析所必需的字段，不\"顺手\"拉全表。\n- **可溯源**：每次交付附数据来源、口径、截止时点与版本。\n- **不落地敏感数据**：客户身份、账户、联系方式等不得导出至非受控环境。\n- **脱敏优先**：能聚合不取明细，能脱敏不取原始。\n- **留痕**：取数请求、审批、交付物留存记录，以备审计回溯。\n- **不用于非申报用途**：分析结果不得用于未经授权的营销外呼、二次加工或对外发布。\n\n> 本节为方法学提示，具体授权范围、审批层级与留存要求以所在机构制度为准。\n\n---\n\n## Disclaimer\n\nThis skill provides data analysis methodology for educational purposes. 文中代码与查询均为教学示例，不含任何真实数据源、连接信息或执行能力；所有分析结论在用于决策前须经人工复核。\n\nFile v5.0.3:_meta.json\n\n{\n  \"ownerId\": \"kn74e704j3ygjcygnpf02rdvd185js13\",\n  \"slug\": \"finance-data-analysis\",\n  \"version\": \"5.0.3\",\n  \"publishedAt\": 1789482159395\n}\n\nFile v5.0.3:skill-card.md\n\n## Description:\n\nProvides financial analysts and finance teams with reference frameworks for financial statement analysis, KPI tracking, trend analysis, data visualization, and reporting.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[gechengling](https://clawhub.ai/user/gechengling)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nFinancial analysts, CFO office teams, and data-driven finance users use this skill to structure KPI dashboards, financial statement reviews, trend analysis, visualization choices, and reporting workflows. The skill is advisory and its outputs should be reviewed before business, investment, audit, legal, or regulatory use.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Financial analysis outputs may be incorrect, incomplete, or mistaken for financial, legal, insurance, audit, or investment advice.\n\nMitigation: Require qualified human review before using outputs for decisions, reporting, disclosure, audit, or regulatory work.\n\nRisk: Users may include customer, account, credential, or production financial data in uncontrolled prompts or downstream examples.\n\nMitigation: Keep real customer and account data out of uncontrolled prompts; use approved, minimized, aggregated, or desensitized data only.\n\nRisk: Broad finance and Chinese trigger terms may activate the skill in conversations where the reference framework is not intended.\n\nMitigation: Narrow trigger terms during deployment if unintended activation would disrupt agent behavior.\n\n## Reference(s):\n\n\n## Skill Output:\n\n**Output Type(s):** [Analysis, Code, Guidance]\n\n**Output Format:** [Markdown with Python and SQL example code blocks]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Advisory reference output requiring human review; no tool execution or data access.]\n\n## Skill Version(s):\n\n5.0.3 (source: frontmatter and server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v5.0.2: 3 files, 4120 bytes\n\nFiles: skill-card.md (2294b), SKILL.md (5593b), _meta.json (140b)\n\nFile v5.0.2:SKILL.md\n\n---\nname: Financial Industry Data Analysis Expert\nslug: finance-data-analytics\ndescription: AI-powered financial data analysis expert — covers financial statement analysis, KPI tracking, trend analysis, data visualization, and automated reporting. Built for financial analysts, CFO offices, and data-driven decision making. Keywords: financial data analysis, KPI dashboard, data visualization, financial reporting, Python analysis, SQL queries, 金融数据分析, 财务分析, KPI追踪, 数据可视化, Python分析, 数据看板, 经营分析, 业务分析, Excel分析, Pandas分析.\nversion: \"5.0.2\"\nallowed-tools: []\ncapabilities:\n  - educational-reference\n  - advisory-only\n  - requires-human-review\n  - code-examples-reference\n---\n\n# Financial Industry Data Analysis Expert / 金融数据分析专家\n> **⚠️ SECURITY NOTICE**\n> - **Type:** Educational reference / analytical framework ONLY\n> - **技能本身不包含可执行代码**，文中Python代码为教学示例\n> - **No persistent storage, background execution, or credential collection**\n> - **No credential collection, PII processing, or system access**\n> - **All outputs require human review before real-world application**\n> - **NOT financial, legal, or insurance advice**\n>\n> **⚠️ 数据安全警告**\n> - 本技能仅提供金融数据分析的方法论参考框架，**不执行任何代码或脚本**\n> - 文中提到的市场数据查询、资金流向分析为**教学方法论展示**，不涉及实际的API调用或数据采集\n> - 不会自动访问、存储或处理用户的任何数据或个人信息\n> - 所有分析结果仅供参考，不构成投资建议\n\n\n\n> **English:** AI-powered financial data analysis — covers financial statements, KPIs, visualization, and automated reporting.\n>\n> **中文:** 金融数据分析——覆盖财务报表、KPI、可视化、自动化报告。\n\n---\n\n\n### 金融监管最新动态 [2026-05-25更新]\n\n| 动态类型 | 内容摘要 | 影响范围 |\n|---------|---------|---------|\n| 金融监管 | 2026年Q1：金融数据合规要求提升 | 数据分析框架需纳入合规和信披新标准 |\n| 金融监管 | 理财信息披露'三清'推进，数据分析需关注新标准 | 数据分析框架需纳入合规和信披新标准 |\n| 金融监管 | 反洗钱数据监控要求加强 | 数据分析框架需纳入合规和信披新标准 |\n\n> **数据截止**: 2026-05-25 | 来源：证监会、NFRA、中证协、安永Q1分析\n> **声明**: 以上动态供参考，具体以官方最新发布为准\n\n## Industry Pain Points / 行业痛点\n\n| Pain Point / 痛点 | Impact / 影响 | Solution / 本Skill解决方案 |\n|------------------|-------------|------------------------|\n| **数据分散** | 数据源多，整合耗时 | 统一数据模型 |\n| **手工报表多** | 月报/季报重复劳动 | 自动报告生成 |\n| **分析浅** | 只看表面数字 | 深度归因分析 |\n| **可视化差** | 图表不直观 | 专业可视化模板 |\n\n---\n\n## Trigger Keywords / 触发关键词\n\n**English Triggers:** financial data analysis, KPI dashboard, data visualization, financial reporting, Python analysis\n\n**中文触发词：** 数据分析 / 财务分析 / KPI追踪 / 数据可视化 / 自动化报告 / Python分析 / SQL查询 / 数据看板 / 经营分析 / 业绩分析 / 同比环比\n\n---\n\n## Core Capabilities / 核心能力\n\n### 1. Financial Analysis Templates / 财务分析模板\n\n> **示例代码（仅供学习参考，非本技能自动执行）**：\n```python\nclass FinancialAnalyzer:\n    \"\"\"财务分析引擎\"\"\"\n    \n    def income_statement_analysis(self, data: dict) -> dict:\n        \"\"\"损益表分析\"\"\"\n        return {\n            \"收入趋势\": self._trend_analysis(data[\"revenue\"]),\n            \"毛利率分析\": self._gross_margin_analysis(data),\n            \"费用结构\": self._expense_breakdown(data),\n            \"利润质量\": self._profit_quality_analysis(data)\n        }\n    \n    def ratio_analysis(self, financial_data: dict) -> dict:\n        \"\"\"比率分析\"\"\"\n        ratios = {\n            \"盈利能力\": {\n                \"毛利率\": data[\"gross_profit\"] / data[\"revenue\"],\n                \"净利率\": data[\"net_profit\"] / data[\"revenue\"],\n                \"ROE\": data[\"net_profit\"] / data[\"equity\"]\n            },\n            \"运营效率\": {\n                \"存货周转\": data[\"cogs\"] / data[\"inventory\"],\n                \"应收账款周转\": data[\"revenue\"] / data[\"ar\"]\n            },\n            \"偿债能力\": {\n                \"流动比率\": data[\"current_assets\"] / data[\"current_liabilities\"],\n                \"资产负债率\": data[\"total_liabilities\"] / data[\"total_assets\"]\n            }\n        }\n        return ratios\n```\n\n### 2. Dashboard Templates / 数据看板模板\n\n```python\nDASHBOARD_TEMPLATES = {\n    \"CFO驾驶舱\": {\n        \"widgets\": [\n            {\"type\": \"kpi_card\", \"metrics\": [\"营收\", \"利润\", \"ROE\"]},\n            {\"type\": \"line_chart\", \"data\": \"收入趋势\"},\n            {\"type\": \"bar_chart\", \"data\": \"各业务线收入\"},\n            {\"type\": \"waterfall\", \"data\": \"利润变动归因\"},\n            {\"type\": \"gauge\", \"data\": \"KPI完成率\"}\n        ]\n    },\n    \"业务分析看板\": {\n        \"widgets\": [\n            {\"type\": \"funnel\", \"data\": \"转化漏斗\"},\n            {\"type\": \"heat_map\", \"data\": \"客户活跃度\"},\n            {\"type\": \"pie_chart\", \"data\": \"客户分布\"},\n            {\"type\": \"trend\", \"data\": \"关键指标趋势\"}\n        ]\n    }\n}\n```\n\n---\n\n## Disclaimer\n\nThis skill provides data analysis tools for educational purposes.\n\nFile v5.0.2:_meta.json\n\n{\n  \"ownerId\": \"kn74e704j3ygjcygnpf02rdvd185js13\",\n  \"slug\": \"finance-data-analysis\",\n  \"version\": \"5.0.2\",\n  \"publishedAt\": 1780586077251\n}\n\nFile v5.0.2:skill-card.md\n\n## Description: <br>\nProvides educational financial data analysis guidance for financial statements, KPI tracking, trend analysis, data visualization, and automated reporting. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[gechengling](https://clawhub.ai/user/gechengling) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nExternal users, financial analysts, CFO offices, and data practitioners can use this skill for educational frameworks and templates for financial reporting, KPI analysis, dashboard design, and trend analysis. Outputs require qualified human review before real-world business, financial, legal, insurance, or compliance use. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Financial or regulatory conclusions may be incorrect, outdated, or unsuitable for a specific real-world context. <br>\nMitigation: Treat outputs as educational guidance and verify conclusions with current official sources and a qualified human reviewer. <br>\nRisk: Broad trigger terms may activate the skill for non-finance data analysis tasks. <br>\nMitigation: Confirm that the requested task is finance-related before applying the skill's templates or conclusions. <br>\nRisk: Illustrative Python examples could be mistaken for automatically executed or production-ready code. <br>\nMitigation: Use the examples only as reference material; review, test, and adapt any code before execution in a controlled environment. <br>\n\n\n## Reference(s): <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Text, Markdown, Code, Guidance] <br>\n**Output Format:** [Markdown guidance with illustrative Python code examples] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Documentation-only; no executable files, tools, persistence, credential handling, hidden data access, or automatic data processing.] <br>\n\n## Skill Version(s): <br>\n5.0.2 (source: frontmatter and server release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v5.0.1: 3 files, 7294 bytes\n\nFiles: skill-card.md (2215b), SKILL.md (12610b), _meta.json (140b)\n\nFile v5.0.1:SKILL.md\n\n---\nname: Financial Industry Data Analysis Expert\nslug: finance-data-analytics\ndescription: AI-powered financial data analysis expert — covers financial statement analysis, KPI tracking, trend analysis, data visualization, and automated reporting. Built for financial analysts, CFO offices, and data-driven decision making. Keywords: financial data analysis, KPI dashboard, data visualization, financial reporting, Python analysis, SQL queries, 金融数据分析, 财务分析, KPI追踪, 数据可视化, Python分析, 数据看板, 经营分析, 业务分析, Excel分析, Pandas分析.\nversion: \"5.0.0\"\n\ncapabilities:\n  - educational-reference\n  - advisory-only\n  - requires-human-review\n  - no-executable-code\n---\n\n# Financial Industry Data Analysis Expert / 金融数据分析专家\n> **⚠️ SECURITY NOTICE**\n> - **Type:** Educational reference / analytical framework ONLY\n> - **No executable code, scripts, or binaries included**\n> - **No persistent storage, network calls, or background execution**\n> - **No credential collection, PII processing, or system access**\n> - **All outputs require human review before real-world application**\n> - **NOT financial, legal, or insurance advice**\n\n\n\n> **English:** AI-powered financial data analysis — covers financial statements, KPIs, visualization, and automated reporting.\n>\n> **中文:** 金融数据分析——覆盖财务报表、KPI、可视化、自动化报告。\n\n---\n\n\n### 金融监管最新动态 [2026-05-25更新]\n\n| 动态类型 | 内容摘要 | 影响范围 |\n|---------|---------|---------|\n| 金融监管 | 2026年Q1：金融数据合规要求提升 | 数据分析框架需纳入合规和信披新标准 |\n| 金融监管 | 理财信息披露'三清'推进，数据分析需关注新标准 | 数据分析框架需纳入合规和信披新标准 |\n| 金融监管 | 反洗钱数据监控要求加强 | 数据分析框架需纳入合规和信披新标准 |\n\n> **数据截止**: 2026-05-25 | 来源：证监会、NFRA、中证协、安永Q1分析\n> **声明**: 以上动态供参考，具体以官方最新发布为准\n\n## Industry Pain Points / 行业痛点\n\n| Pain Point / 痛点 | Impact / 影响 | Solution / 本Skill解决方案 |\n|------------------|-------------|------------------------|\n| **数据分散** | 数据源多，整合耗时 | 统一数据模型 |\n| **手工报表多** | 月报/季报重复劳动 | 自动报告生成 |\n| **分析浅** | 只看表面数字 | 深度归因分析 |\n| **可视化差** | 图表不直观 | 专业可视化模板 |\n\n---\n\n## Trigger Keywords / 触发关键词\n\n**English Triggers:** financial data analysis, KPI dashboard, data visualization, financial reporting, Python analysis\n\n**中文触发词（优先）：** 数据分析 / 财务分析 / KPI追踪 / 数据可视化 / 自动化报告 / Python分析 / SQL查询 / 数据看板 / 经营分析 / 业绩分析 / 同比环比\n\n---\n\n## Core Capabilities / 核心能力\n\n### 1. Financial Analysis Templates / 财务分析模板\n\n```python\nclass FinancialAnalyzer:\n    \"\"\"财务分析引擎\"\"\"\n    \n    def income_statement_analysis(self, data: dict) -> dict:\n        \"\"\"损益表分析\"\"\"\n        return {\n            \"收入趋势\": self._trend_analysis(data[\"revenue\"]),\n            \"毛利率分析\": self._gross_margin_analysis(data),\n            \"费用结构\": self._expense_breakdown(data),\n            \"利润质量\": self._profit_quality_analysis(data)\n        }\n    \n    def ratio_analysis(self, financial_data: dict) -> dict:\n        \"\"\"比率分析\"\"\"\n        ratios = {\n            \"盈利能力\": {\n                \"毛利率\": data[\"gross_profit\"] / data[\"revenue\"],\n                \"净利率\": data[\"net_profit\"] / data[\"revenue\"],\n                \"ROE\": data[\"net_profit\"] / data[\"equity\"]\n            },\n            \"运营效率\": {\n                \"存货周转\": data[\"cogs\"] / data[\"inventory\"],\n                \"应收账款周转\": data[\"revenue\"] / data[\"ar\"]\n            },\n            \"偿债能力\": {\n                \"流动比率\": data[\"current_assets\"] / data[\"current_liabilities\"],\n                \"资产负债率\": data[\"total_liabilities\"] / data[\"total_assets\"]\n            }\n        }\n        return ratios\n```\n\n### 2. Dashboard Templates / 数据看板模板\n\n```python\nDASHBOARD_TEMPLATES = {\n    \"CFO驾驶舱\": {\n        \"widgets\": [\n            {\"type\": \"kpi_card\", \"metrics\": [\"营收\", \"利润\", \"ROE\"]},\n            {\"type\": \"line_chart\", \"data\": \"收入趋势\"},\n            {\"type\": \"bar_chart\", \"data\": \"各业务线收入\"},\n            {\"type\": \"waterfall\", \"data\": \"利润变动归因\"},\n            {\"type\": \"gauge\", \"data\": \"KPI完成率\"}\n        ]\n    },\n    \"业务分析看板\": {\n        \"widgets\": [\n            {\"type\": \"funnel\", \"data\": \"转化漏斗\"},\n            {\"type\": \"heat_map\", \"data\": \"客户活跃度\"},\n            {\"type\": \"pie_chart\", \"data\": \"客户分布\"},\n            {\"type\": \"trend\", \"data\": \"关键指标趋势\"}\n        ]\n    }\n}\n```\n\n---\n\n## Disclaimer\n\nThis skill provides data analysis tools for educational purposes.\n## Appendix G. Alibaba Dianjin Fusion — finance-data-analysis v5.0.0\n\n> **Source**: Alibaba Dianjin Digital Employee — `investment-advisor` (AI投资顾问) & `researcher` (AI研究员)  \n> **Essence**: 股票市场分析、板块轮动、资金流向监控、技术指标综合研判  \n> **Integrated**: 2026-05-31\n\n---\n\n### G.1 Core Workflow (Dianjin essence)\n\n```\n用户请求 → 股票/板块筛选 → 多维度数据分析 → 投资建议生成 → 风险提示\n   ↓\nData sources:\n  - 实时行情 (westock-data / neodata)\n  - 资金流向 (主力净流入/流出)\n  - 技术指标 (MACD, KDJ, RSI, BOLL)\n  - 板块轮动 (行业涨跌排行)\n  - 新闻舆情 (finance-news-aggregator)\n   ↓\nAnalysis dimensions:\n  1. 趋势判断 (日线/周线/月线)\n  2. 资金面 (北向资金, 融资余额)\n  3. 基本面 (PE/PB, 业绩增速)\n  4. 技术面 (突破/回调, 支撑位/压力位)\n  5. 风险面 (减持, ST, 质押)\n   ↓\nOutput:\n  - 投资建议 (买入/持有/卖出)\n  - 目标价位 (止盈/止损)\n  - 风险提示 (仓位控制)\n```\n\n---\n\n### G.2 Stock Screening & Ranking (Dianjin method)\n\n**筛选逻辑（投资顾问精髓）**：\n\n```\nStep 1: 板块筛选\n  - 今日涨幅榜 TOP 10 板块\n  - 资金净流入 TOP 10 板块\n  - 政策利好板块 (国务院/央行/证监会)\n   ↓\nStep 2: 个股筛选\n  - 板块内龙头股 (市值TOP3)\n  - 资金流入强度 (主力净流入 > 1000万)\n  - 技术形态 (突破/金叉)\n  - 基本面 (ROE > 10%, 业绩正增长)\n   ↓\nStep 3: 风险过滤\n  - 排除ST/*ST\n  - 排除近期大额减持\n  - 排除高质押率 (>50%)\n   ↓\nOutput: 推荐股票清单 (TOP 5-10)\n```\n\n**评分模型（Dianjin风格）**：\n\n| 维度 | 权重 | 评分标准 |\n|------|------|---------|\n| 趋势强度 | 30% | 均线多头排列 + 突破压力位 |\n| 资金面 | 25% | 主力净流入 + 北向资金增持 |\n| 基本面 | 20% | ROE + 业绩增速 + 估值合理 |\n| 技术面 | 15% | MACD金叉 + KDJ低位 |\n| 风险面 | 10% | 无重大风险事件 |\n\n---\n\n### G.3 Capital Flow Monitoring (Dianjin essence)\n\n**资金流向分析框架**：\n\n```\n监控指标：\n1. 主力资金净流入 (supermoney_in)\n   - 定义：超大单 + 大单净流入\n   - 阈值：> 1000万 = 强流入\n   - 持续天数：3日累计 > 3000万 = 趋势确认\n\n2. 北向资金 (north_money)\n   - 沪股通 + 深股通\n   - 单日流入 > 50亿 = 市场强势\n   - 连续5日流入 = 外资看多\n\n3. 融资余额 (margin_balance)\n   - 融资买入额 / 总成交额\n   - 占比 > 10% = 杠杆资金活跃\n   - 余额增长 > 5% = 市场风险偏好提升\n\n4. 板块轮动 (sector_rotation)\n   - 今日强势板块 vs 昨日强势板块\n   - 轮动规律：周期 → 金融 → 科技 → 消费\n   - 异常：同一板块连续3日领涨 = 可能见顶\n```\n\n**实战案例（Dianjin风格）**：\n\n```\n【资金流向日报】\n日期：2026-05-31\n\n【大盘】\n- 上证指数：+0.8%，成交额5200亿\n- 北向资金：+68亿（连续3日净流入）\n- 融资余额：+120亿（杠杆资金活跃）\n\n【板块资金流向 TOP 5】\n1. AI芯片：+52亿（新易盛 +12亿, 中际旭创 +10亿）\n2. 新能源车：+38亿（宁德时代 +15亿, 比亚迪 +12亿）\n3. 半导体：+31亿（北方华创 +8亿, 韦尔股份 +6亿）\n4. 银行：+25亿（招商银行 +7亿, 兴业银行 +5亿）\n5. 电力设备：+22亿（特变电工 +6亿, 国电南瑞 +5亿）\n\n【主力出逃 TOP 5】\n1. 房地产：-28亿（万科A -8亿, 保利发展 -6亿）\n2. 传媒：-18亿（分众传媒 -5亿, 东方明珠 -4亿）\n3. 钢铁：-15亿（宝钢股份 -4亿, 包钢股份 -3亿）\n4. 煤炭：-12亿（中国神华 -4亿, 陕西煤业 -3亿）\n5. 农业：-10亿（牧原股份 -3亿, 温氏股份 -2亿）\n\n【投资建议】\n- 激进型：关注AI芯片（新易盛, 中际旭创），短期强势\n- 稳健型：配置银行（招商银行），防御+股息\n- 风险提示：房地产资金持续出逃，规避相关板块\n```\n\n---\n\n### G.4 Technical Indicator Synthesis (Dianjin method)\n\n**多技术指标综合研判**：\n\n```\n买入信号（多指标共振）：\n  ✅ MACD金叉 + KDJ < 20 + RSI < 30\n  ✅ 突破20日均线 + 成交量放大 > 5日均量\n  ✅ BOLL下轨反弹 + 上轨空间 > 20%\n\n卖出信号（多指标共振）：\n  ❌ MACD死叉 + KDJ > 80 + RSI > 70\n  ❌ 跌破20日均线 + 成交量萎缩\n  ❌ BOLL上轨回落 + 下轨空间 > 15%\n\n观望信号：\n  ⚠️ 单一指标信号（需等待共振）\n  ⚠️ 横盘震荡（方向不明）\n```\n\n**实战模板（Dianjin风格）**：\n\n```\n【技术分析报告】\n标的：新易盛 (sz300502)\n\n【趋势判断】\n- 日线：多头排列（MA5 > MA10 > MA20 > MA60）\n- 周线：突破前高 85元，下一压力位 95元\n- 月线：长期上升趋势，MACD红柱放大\n\n【技术指标】\n- MACD：DIF=2.5, DEA=1.8, 金叉状态\n- KDJ：K=65, D=58, J=79（强势区域）\n- RSI：RSI1=68, RSI2=62（偏强，未超买）\n- BOLL：价格 88.5元，上轨 92元，下轨 78元\n\n【量价关系】\n- 今日成交量：5200万股（5日均量 3800万股，放量 +37%）\n- 换手率：4.2%（活跃）\n- 资金流向：主力净流入 +8.2亿\n\n【综合研判】\n✅ 买入信号（3个共振）\n  - MACD金叉 + 突破20日线 + 主力净流入\n⚠️ 风险提示：\n  - 短期涨幅 +35%（近10日），注意回调风险\n  - 下一压力位 92元（BOLL上轨）\n\n【操作建议】\n- 激进型：回调至 85元附近买入，止损 82元\n- 稳健型：等待回踩 83-85元区间，分批建仓\n- 目标价：第一目标 95元（+7%），第二目标 105元（+19%）\n```\n\n---\n\n### G.5 Compliance & Risk Constraints (Dianjin standards)\n\n**合规要求（投资顾问精髓）**：\n\n1. **风险提示必须**：\n   - 每份分析报告必须包含\"股市有风险，投资需谨慎\"\n   - 明确标注\"本报告仅供参考，不构成投资建议\"\n   - 推荐股票必须说明风险等级（高/中/低）\n\n2. **数据来源标注**：\n   - 实时行情：标注\"数据来源：腾讯自选股\"\n   - 历史数据：标注\"数据来源：聚源数据\"\n   - 新闻舆情：标注\"数据来源：公开市场信息\"\n\n3. **禁止行为**：\n   - ❌ 不允许承诺收益（\"必涨\", \"稳赚\"）\n   - ❌ 不允许推荐ST股票（除非风险充分提示）\n   - ❌ 不允许煽动性语言（\"暴涨\", \"千载难逢\"）\n\n---\n\n### G.6 Test Case (Dianjin quality)\n\n**Test Case 1: 板块轮动分析**\n\n```\nInput: \"帮我分析今天A股板块轮动情况，哪些板块值得关注？\"\n\nExpected Output:\n1. 今日涨幅榜 TOP 5 板块\n2. 资金净流入 TOP 5 板块\n3. 板块轮动规律分析（是否健康）\n4. 推荐关注板块（TOP 3）+ 理由\n5. 风险提示（规避板块）\n\nQuality Check:\n- ✅ 数据实时性（今日数据）\n- ✅ 逻辑合理性（板块轮动规律）\n- ✅ 风险提示（规避板块）\n- ✅ 合规性（不承诺收益）\n```\n\n**Test Case 2: 个股技术分析**\n\n```\nInput: \"分析新易盛 (300502) 的技术走势，现在能买吗？\"\n\nExpected Output:\n1. 趋势判断（日线/周线/月线）\n2. 技术指标（MACD, KDJ, RSI, BOLL）\n3. 量价关系（成交量, 换手率, 资金流向）\n4. 综合研判（买入/观望/卖出）\n5. 操作建议（入场价, 止损价, 目标价）\n\nQuality Check:\n- ✅ 多指标共振（不是单一指标）\n- ✅ 风险提示（短期涨幅过大）\n- ✅ 操作建议具体（价格区间）\n- ✅ 合规性（标注\"仅供参考\"）\n```\n\n---\n\n**End of Dianjin Fusion Content — finance-data-analysis v5.0.0**\n\nFile v5.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn74e704j3ygjcygnpf02rdvd185js13\",\n  \"slug\": \"finance-data-analysis\",\n  \"version\": \"5.0.1\",\n  \"publishedAt\": 1780326664342\n}\n\nFile v5.0.1:skill-card.md\n\n## Description: <br>\nProvides AI-powered financial data analysis for financial statements, KPI tracking, trend analysis, data visualization, and automated reporting. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[gechengling](https://clawhub.ai/user/gechengling) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nFinancial analysts, CFO offices, and business or data teams use this skill to structure financial statement analysis, KPI dashboards, trend analysis, visualizations, and report drafts. Outputs are advisory and require current data verification and human review before business or investment use. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill may steer an agent toward investment analysis, stock recommendations, target prices, or buy/sell guidance while presenting itself as educational-only. <br>\nMitigation: Treat market outputs as high-risk financial content requiring human review, current source verification, and compliance checks before use. <br>\nRisk: The artifact's no-network and no-advice notices may under-describe the behavior available in the skill text. <br>\nMitigation: Review generated market analysis against the full skill behavior and do not rely on the notices alone when approving deployment. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/gechengling/finance-data-analysis) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, code, guidance] <br>\n**Output Format:** [Markdown with tabular analysis templates and illustrative code blocks] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Advisory financial analysis output; requires current source verification, compliance checks, and human review.] <br>\n\n## Skill Version(s): <br>\n5.0.1 (source: server release metadata; artifact frontmatter reports 5.0.0) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v5.0.0: 3 files, 6970 bytes\n\nFiles: skill-card.md (2249b), SKILL.md (12091b), _meta.json (140b)\n\nFile v5.0.0:SKILL.md\n\n---\nname: Financial Industry Data Analysis Expert\nslug: finance-data-analytics\ndescription: AI-powered financial data analysis expert — covers financial statement analysis, KPI tracking, trend analysis, data visualization, and automated reporting. Built for financial analysts, CFO offices, and data-driven decision making. Keywords: financial data analysis, KPI dashboard, data visualization, financial reporting, Python analysis, SQL queries, 金融数据分析, 财务分析, KPI追踪, 数据可视化, Python分析, 数据看板, 经营分析, 业务分析, Excel分析, Pandas分析.\nversion: \"5.0.0\"\n---\n\n# Financial Industry Data Analysis Expert / 金融数据分析专家\n\n> **English:** AI-powered financial data analysis — covers financial statements, KPIs, visualization, and automated reporting.\n>\n> **中文:** 金融数据分析——覆盖财务报表、KPI、可视化、自动化报告。\n\n---\n\n\n### 金融监管最新动态 [2026-05-25更新]\n\n| 动态类型 | 内容摘要 | 影响范围 |\n|---------|---------|---------|\n| 金融监管 | 2026年Q1：金融数据合规要求提升 | 数据分析框架需纳入合规和信披新标准 |\n| 金融监管 | 理财信息披露'三清'推进，数据分析需关注新标准 | 数据分析框架需纳入合规和信披新标准 |\n| 金融监管 | 反洗钱数据监控要求加强 | 数据分析框架需纳入合规和信披新标准 |\n\n> **数据截止**: 2026-05-25 | 来源：证监会、NFRA、中证协、安永Q1分析\n> **声明**: 以上动态供参考，具体以官方最新发布为准\n\n## Industry Pain Points / 行业痛点\n\n| Pain Point / 痛点 | Impact / 影响 | Solution / 本Skill解决方案 |\n|------------------|-------------|------------------------|\n| **数据分散** | 数据源多，整合耗时 | 统一数据模型 |\n| **手工报表多** | 月报/季报重复劳动 | 自动报告生成 |\n| **分析浅** | 只看表面数字 | 深度归因分析 |\n| **可视化差** | 图表不直观 | 专业可视化模板 |\n\n---\n\n## Trigger Keywords / 触发关键词\n\n**English Triggers:** financial data analysis, KPI dashboard, data visualization, financial reporting, Python analysis\n\n**中文触发词（优先）：** 数据分析 / 财务分析 / KPI追踪 / 数据可视化 / 自动化报告 / Python分析 / SQL查询 / 数据看板 / 经营分析 / 业绩分析 / 同比环比\n\n---\n\n## Core Capabilities / 核心能力\n\n### 1. Financial Analysis Templates / 财务分析模板\n\n```python\nclass FinancialAnalyzer:\n    \"\"\"财务分析引擎\"\"\"\n    \n    def income_statement_analysis(self, data: dict) -> dict:\n        \"\"\"损益表分析\"\"\"\n        return {\n            \"收入趋势\": self._trend_analysis(data[\"revenue\"]),\n            \"毛利率分析\": self._gross_margin_analysis(data),\n            \"费用结构\": self._expense_breakdown(data),\n            \"利润质量\": self._profit_quality_analysis(data)\n        }\n    \n    def ratio_analysis(self, financial_data: dict) -> dict:\n        \"\"\"比率分析\"\"\"\n        ratios = {\n            \"盈利能力\": {\n                \"毛利率\": data[\"gross_profit\"] / data[\"revenue\"],\n                \"净利率\": data[\"net_profit\"] / data[\"revenue\"],\n                \"ROE\": data[\"net_profit\"] / data[\"equity\"]\n            },\n            \"运营效率\": {\n                \"存货周转\": data[\"cogs\"] / data[\"inventory\"],\n                \"应收账款周转\": data[\"revenue\"] / data[\"ar\"]\n            },\n            \"偿债能力\": {\n                \"流动比率\": data[\"current_assets\"] / data[\"current_liabilities\"],\n                \"资产负债率\": data[\"total_liabilities\"] / data[\"total_assets\"]\n            }\n        }\n        return ratios\n```\n\n### 2. Dashboard Templates / 数据看板模板\n\n```python\nDASHBOARD_TEMPLATES = {\n    \"CFO驾驶舱\": {\n        \"widgets\": [\n            {\"type\": \"kpi_card\", \"metrics\": [\"营收\", \"利润\", \"ROE\"]},\n            {\"type\": \"line_chart\", \"data\": \"收入趋势\"},\n            {\"type\": \"bar_chart\", \"data\": \"各业务线收入\"},\n            {\"type\": \"waterfall\", \"data\": \"利润变动归因\"},\n            {\"type\": \"gauge\", \"data\": \"KPI完成率\"}\n        ]\n    },\n    \"业务分析看板\": {\n        \"widgets\": [\n            {\"type\": \"funnel\", \"data\": \"转化漏斗\"},\n            {\"type\": \"heat_map\", \"data\": \"客户活跃度\"},\n            {\"type\": \"pie_chart\", \"data\": \"客户分布\"},\n            {\"type\": \"trend\", \"data\": \"关键指标趋势\"}\n        ]\n    }\n}\n```\n\n---\n\n## Disclaimer\n\nThis skill provides data analysis tools for educational purposes.\n## Appendix G. Alibaba Dianjin Fusion — finance-data-analysis v5.0.0\n\n> **Source**: Alibaba Dianjin Digital Employee — `investment-advisor` (AI投资顾问) & `researcher` (AI研究员)  \n> **Essence**: 股票市场分析、板块轮动、资金流向监控、技术指标综合研判  \n> **Integrated**: 2026-05-31\n\n---\n\n### G.1 Core Workflow (Dianjin essence)\n\n```\n用户请求 → 股票/板块筛选 → 多维度数据分析 → 投资建议生成 → 风险提示\n   ↓\nData sources:\n  - 实时行情 (westock-data / neodata)\n  - 资金流向 (主力净流入/流出)\n  - 技术指标 (MACD, KDJ, RSI, BOLL)\n  - 板块轮动 (行业涨跌排行)\n  - 新闻舆情 (finance-news-aggregator)\n   ↓\nAnalysis dimensions:\n  1. 趋势判断 (日线/周线/月线)\n  2. 资金面 (北向资金, 融资余额)\n  3. 基本面 (PE/PB, 业绩增速)\n  4. 技术面 (突破/回调, 支撑位/压力位)\n  5. 风险面 (减持, ST, 质押)\n   ↓\nOutput:\n  - 投资建议 (买入/持有/卖出)\n  - 目标价位 (止盈/止损)\n  - 风险提示 (仓位控制)\n```\n\n---\n\n### G.2 Stock Screening & Ranking (Dianjin method)\n\n**筛选逻辑（投资顾问精髓）**：\n\n```\nStep 1: 板块筛选\n  - 今日涨幅榜 TOP 10 板块\n  - 资金净流入 TOP 10 板块\n  - 政策利好板块 (国务院/央行/证监会)\n   ↓\nStep 2: 个股筛选\n  - 板块内龙头股 (市值TOP3)\n  - 资金流入强度 (主力净流入 > 1000万)\n  - 技术形态 (突破/金叉)\n  - 基本面 (ROE > 10%, 业绩正增长)\n   ↓\nStep 3: 风险过滤\n  - 排除ST/*ST\n  - 排除近期大额减持\n  - 排除高质押率 (>50%)\n   ↓\nOutput: 推荐股票清单 (TOP 5-10)\n```\n\n**评分模型（Dianjin风格）**：\n\n| 维度 | 权重 | 评分标准 |\n|------|------|---------|\n| 趋势强度 | 30% | 均线多头排列 + 突破压力位 |\n| 资金面 | 25% | 主力净流入 + 北向资金增持 |\n| 基本面 | 20% | ROE + 业绩增速 + 估值合理 |\n| 技术面 | 15% | MACD金叉 + KDJ低位 |\n| 风险面 | 10% | 无重大风险事件 |\n\n---\n\n### G.3 Capital Flow Monitoring (Dianjin essence)\n\n**资金流向分析框架**：\n\n```\n监控指标：\n1. 主力资金净流入 (supermoney_in)\n   - 定义：超大单 + 大单净流入\n   - 阈值：> 1000万 = 强流入\n   - 持续天数：3日累计 > 3000万 = 趋势确认\n\n2. 北向资金 (north_money)\n   - 沪股通 + 深股通\n   - 单日流入 > 50亿 = 市场强势\n   - 连续5日流入 = 外资看多\n\n3. 融资余额 (margin_balance)\n   - 融资买入额 / 总成交额\n   - 占比 > 10% = 杠杆资金活跃\n   - 余额增长 > 5% = 市场风险偏好提升\n\n4. 板块轮动 (sector_rotation)\n   - 今日强势板块 vs 昨日强势板块\n   - 轮动规律：周期 → 金融 → 科技 → 消费\n   - 异常：同一板块连续3日领涨 = 可能见顶\n```\n\n**实战案例（Dianjin风格）**：\n\n```\n【资金流向日报】\n日期：2026-05-31\n\n【大盘】\n- 上证指数：+0.8%，成交额5200亿\n- 北向资金：+68亿（连续3日净流入）\n- 融资余额：+120亿（杠杆资金活跃）\n\n【板块资金流向 TOP 5】\n1. AI芯片：+52亿（新易盛 +12亿, 中际旭创 +10亿）\n2. 新能源车：+38亿（宁德时代 +15亿, 比亚迪 +12亿）\n3. 半导体：+31亿（北方华创 +8亿, 韦尔股份 +6亿）\n4. 银行：+25亿（招商银行 +7亿, 兴业银行 +5亿）\n5. 电力设备：+22亿（特变电工 +6亿, 国电南瑞 +5亿）\n\n【主力出逃 TOP 5】\n1. 房地产：-28亿（万科A -8亿, 保利发展 -6亿）\n2. 传媒：-18亿（分众传媒 -5亿, 东方明珠 -4亿）\n3. 钢铁：-15亿（宝钢股份 -4亿, 包钢股份 -3亿）\n4. 煤炭：-12亿（中国神华 -4亿, 陕西煤业 -3亿）\n5. 农业：-10亿（牧原股份 -3亿, 温氏股份 -2亿）\n\n【投资建议】\n- 激进型：关注AI芯片（新易盛, 中际旭创），短期强势\n- 稳健型：配置银行（招商银行），防御+股息\n- 风险提示：房地产资金持续出逃，规避相关板块\n```\n\n---\n\n### G.4 Technical Indicator Synthesis (Dianjin method)\n\n**多技术指标综合研判**：\n\n```\n买入信号（多指标共振）：\n  ✅ MACD金叉 + KDJ < 20 + RSI < 30\n  ✅ 突破20日均线 + 成交量放大 > 5日均量\n  ✅ BOLL下轨反弹 + 上轨空间 > 20%\n\n卖出信号（多指标共振）：\n  ❌ MACD死叉 + KDJ > 80 + RSI > 70\n  ❌ 跌破20日均线 + 成交量萎缩\n  ❌ BOLL上轨回落 + 下轨空间 > 15%\n\n观望信号：\n  ⚠️ 单一指标信号（需等待共振）\n  ⚠️ 横盘震荡（方向不明）\n```\n\n**实战模板（Dianjin风格）**：\n\n```\n【技术分析报告】\n标的：新易盛 (sz300502)\n\n【趋势判断】\n- 日线：多头排列（MA5 > MA10 > MA20 > MA60）\n- 周线：突破前高 85元，下一压力位 95元\n- 月线：长期上升趋势，MACD红柱放大\n\n【技术指标】\n- MACD：DIF=2.5, DEA=1.8, 金叉状态\n- KDJ：K=65, D=58, J=79（强势区域）\n- RSI：RSI1=68, RSI2=62（偏强，未超买）\n- BOLL：价格 88.5元，上轨 92元，下轨 78元\n\n【量价关系】\n- 今日成交量：5200万股（5日均量 3800万股，放量 +37%）\n- 换手率：4.2%（活跃）\n- 资金流向：主力净流入 +8.2亿\n\n【综合研判】\n✅ 买入信号（3个共振）\n  - MACD金叉 + 突破20日线 + 主力净流入\n⚠️ 风险提示：\n  - 短期涨幅 +35%（近10日），注意回调风险\n  - 下一压力位 92元（BOLL上轨）\n\n【操作建议】\n- 激进型：回调至 85元附近买入，止损 82元\n- 稳健型：等待回踩 83-85元区间，分批建仓\n- 目标价：第一目标 95元（+7%），第二目标 105元（+19%）\n```\n\n---\n\n### G.5 Compliance & Risk Constraints (Dianjin standards)\n\n**合规要求（投资顾问精髓）**：\n\n1. **风险提示必须**：\n   - 每份分析报告必须包含\"股市有风险，投资需谨慎\"\n   - 明确标注\"本报告仅供参考，不构成投资建议\"\n   - 推荐股票必须说明风险等级（高/中/低）\n\n2. **数据来源标注**：\n   - 实时行情：标注\"数据来源：腾讯自选股\"\n   - 历史数据：标注\"数据来源：聚源数据\"\n   - 新闻舆情：标注\"数据来源：公开市场信息\"\n\n3. **禁止行为**：\n   - ❌ 不允许承诺收益（\"必涨\", \"稳赚\"）\n   - ❌ 不允许推荐ST股票（除非风险充分提示）\n   - ❌ 不允许煽动性语言（\"暴涨\", \"千载难逢\"）\n\n---\n\n### G.6 Test Case (Dianjin quality)\n\n**Test Case 1: 板块轮动分析**\n\n```\nInput: \"帮我分析今天A股板块轮动情况，哪些板块值得关注？\"\n\nExpected Output:\n1. 今日涨幅榜 TOP 5 板块\n2. 资金净流入 TOP 5 板块\n3. 板块轮动规律分析（是否健康）\n4. 推荐关注板块（TOP 3）+ 理由\n5. 风险提示（规避板块）\n\nQuality Check:\n- ✅ 数据实时性（今日数据）\n- ✅ 逻辑合理性（板块轮动规律）\n- ✅ 风险提示（规避板块）\n- ✅ 合规性（不承诺收益）\n```\n\n**Test Case 2: 个股技术分析**\n\n```\nInput: \"分析新易盛 (300502) 的技术走势，现在能买吗？\"\n\nExpected Output:\n1. 趋势判断（日线/周线/月线）\n2. 技术指标（MACD, KDJ, RSI, BOLL）\n3. 量价关系（成交量, 换手率, 资金流向）\n4. 综合研判（买入/观望/卖出）\n5. 操作建议（入场价, 止损价, 目标价）\n\nQuality Check:\n- ✅ 多指标共振（不是单一指标）\n- ✅ 风险提示（短期涨幅过大）\n- ✅ 操作建议具体（价格区间）\n- ✅ 合规性（标注\"仅供参考\"）\n```\n\n---\n\n**End of Dianjin Fusion Content — finance-data-analysis v5.0.0**\n\nFile v5.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn74e704j3ygjcygnpf02rdvd185js13\",\n  \"slug\": \"finance-data-analysis\",\n  \"version\": \"5.0.0\",\n  \"publishedAt\": 1780193569420\n}\n\nFile v5.0.0:skill-card.md\n\n## Description: <br>\nProvides AI-driven financial data analysis for financial statements, KPI tracking, trend analysis, data visualization, automated reporting, and investment-style market commentary. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[gechengling](https://clawhub.ai/user/gechengling) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nFinancial analysts, CFO teams, and data-oriented business users use this skill to structure financial statement analysis, KPI dashboards, trend analysis, visualizations, automated reports, and investment-style market commentary. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill is published as financial data analysis while also including stock trading recommendations that require review before use. <br>\nMitigation: Use it only where investment-style market commentary is intended, and require compliance review before relying on recommendation-oriented sections. <br>\nRisk: Stock recommendation sections may be inappropriate for ordinary financial reporting, KPI dashboards, or CFO analytics. <br>\nMitigation: Remove or strongly gate those sections with clear user confirmation when the intended workflow is reporting or internal business analytics. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/gechengling/finance-data-analysis) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Text, Markdown, Code, Configuration, Guidance] <br>\n**Output Format:** [Markdown with analysis narratives, code examples, dashboard structures, and risk guidance] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [May include financial analysis templates, KPI dashboard guidance, stock screening commentary, technical indicator summaries, and compliance reminders.] <br>\n\n## Skill Version(s): <br>\n5.0.0 (source: server release evidence and SKILL.md frontmatter) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v3.0.1: 3 files, 3592 bytes\n\nFiles: skill-card.md (2363b), SKILL.md (4668b), _meta.json (140b)\n\nFile v3.0.1:SKILL.md\n\n---\r\nname: Financial Industry Data Analysis Expert\r\nslug: finance-data-analytics\r\ndescription: AI-powered financial data analysis expert — covers financial statement analysis, KPI tracking, trend analysis, data visualization, and automated reporting. Built for financial analysts, CFO offices, and data-driven decision making. Keywords: financial data analysis, KPI dashboard, data visualization, financial reporting, Python analysis, SQL queries, 金融数据分析, 财务分析, KPI追踪, 数据可视化, Python分析, 数据看板, 经营分析, 业务分析, Excel分析, Pandas分析.\r\nversion: \"3.0.1\"\r\n---\r\n\r\n# Financial Industry Data Analysis Expert / 金融数据分析专家\r\n\r\n> **English:** AI-powered financial data analysis — covers financial statements, KPIs, visualization, and automated reporting.\r\n>\r\n> **中文:** 金融数据分析——覆盖财务报表、KPI、可视化、自动化报告。\r\n\r\n---\r\n\r\n\r\n### 金融监管最新动态 [2026-05-25更新]\r\n\r\n| 动态类型 | 内容摘要 | 影响范围 |\r\n|---------|---------|---------|\r\n| 金融监管 | 2026年Q1：金融数据合规要求提升 | 数据分析框架需纳入合规和信披新标准 |\r\n| 金融监管 | 理财信息披露'三清'推进，数据分析需关注新标准 | 数据分析框架需纳入合规和信披新标准 |\r\n| 金融监管 | 反洗钱数据监控要求加强 | 数据分析框架需纳入合规和信披新标准 |\r\n\r\n> **数据截止**: 2026-05-25 | 来源：证监会、NFRA、中证协、安永Q1分析\r\n> **声明**: 以上动态供参考，具体以官方最新发布为准\r\n\r\n## Industry Pain Points / 行业痛点\r\n\r\n| Pain Point / 痛点 | Impact / 影响 | Solution / 本Skill解决方案 |\r\n|------------------|-------------|------------------------|\r\n| **数据分散** | 数据源多，整合耗时 | 统一数据模型 |\r\n| **手工报表多** | 月报/季报重复劳动 | 自动报告生成 |\r\n| **分析浅** | 只看表面数字 | 深度归因分析 |\r\n| **可视化差** | 图表不直观 | 专业可视化模板 |\r\n\r\n---\r\n\r\n## Trigger Keywords / 触发关键词\r\n\r\n**English Triggers:** financial data analysis, KPI dashboard, data visualization, financial reporting, Python analysis\r\n\r\n**中文触发词（优先）：** 数据分析 / 财务分析 / KPI追踪 / 数据可视化 / 自动化报告 / Python分析 / SQL查询 / 数据看板 / 经营分析 / 业绩分析 / 同比环比\r\n\r\n---\r\n\r\n## Core Capabilities / 核心能力\r\n\r\n### 1. Financial Analysis Templates / 财务分析模板\r\n\r\n```python\r\nclass FinancialAnalyzer:\r\n    \"\"\"财务分析引擎\"\"\"\r\n    \r\n    def income_statement_analysis(self, data: dict) -> dict:\r\n        \"\"\"损益表分析\"\"\"\r\n        return {\r\n            \"收入趋势\": self._trend_analysis(data[\"revenue\"]),\r\n            \"毛利率分析\": self._gross_margin_analysis(data),\r\n            \"费用结构\": self._expense_breakdown(data),\r\n            \"利润质量\": self._profit_quality_analysis(data)\r\n        }\r\n    \r\n    def ratio_analysis(self, financial_data: dict) -> dict:\r\n        \"\"\"比率分析\"\"\"\r\n        ratios = {\r\n            \"盈利能力\": {\r\n                \"毛利率\": data[\"gross_profit\"] / data[\"revenue\"],\r\n                \"净利率\": data[\"net_profit\"] / data[\"revenue\"],\r\n                \"ROE\": data[\"net_profit\"] / data[\"equity\"]\r\n            },\r\n            \"运营效率\": {\r\n                \"存货周转\": data[\"cogs\"] / data[\"inventory\"],\r\n                \"应收账款周转\": data[\"revenue\"] / data[\"ar\"]\r\n            },\r\n            \"偿债能力\": {\r\n                \"流动比率\": data[\"current_assets\"] / data[\"current_liabilities\"],\r\n                \"资产负债率\": data[\"total_liabilities\"] / data[\"total_assets\"]\r\n            }\r\n        }\r\n        return ratios\r\n```\r\n\r\n### 2. Dashboard Templates / 数据看板模板\r\n\r\n```python\r\nDASHBOARD_TEMPLATES = {\r\n    \"CFO驾驶舱\": {\r\n        \"widgets\": [\r\n            {\"type\": \"kpi_card\", \"metrics\": [\"营收\", \"利润\", \"ROE\"]},\r\n            {\"type\": \"line_chart\", \"data\": \"收入趋势\"},\r\n            {\"type\": \"bar_chart\", \"data\": \"各业务线收入\"},\r\n            {\"type\": \"waterfall\", \"data\": \"利润变动归因\"},\r\n            {\"type\": \"gauge\", \"data\": \"KPI完成率\"}\r\n        ]\r\n    },\r\n    \"业务分析看板\": {\r\n        \"widgets\": [\r\n            {\"type\": \"funnel\", \"data\": \"转化漏斗\"},\r\n            {\"type\": \"heat_map\", \"data\": \"客户活跃度\"},\r\n            {\"type\": \"pie_chart\", \"data\": \"客户分布\"},\r\n            {\"type\": \"trend\", \"data\": \"关键指标趋势\"}\r\n        ]\r\n    }\r\n}\r\n```\r\n\r\n---\r\n\r\n## Disclaimer\r\n\r\nThis skill provides data analysis tools for educational purposes.\n\nFile v3.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn74e704j3ygjcygnpf02rdvd185js13\",\n  \"slug\": \"finance-data-analysis\",\n  \"version\": \"3.0.1\",\n  \"publishedAt\": 1779686623898\n}\n\nFile v3.0.1:skill-card.md\n\n## Description: <br>\nProvides AI-driven financial data analysis support for financial statement review, KPI tracking, trend analysis, data visualization, and automated reporting. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[gechengling](https://clawhub.ai/user/gechengling) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nFinancial analysts, CFO teams, and data-driven business users use this skill to request finance-oriented analysis prompts, reporting structures, KPI dashboards, and Python-style templates for financial data workflows. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Users may paste confidential, personal, customer, nonpublic, or regulated financial data into an agent session. <br>\nMitigation: Use only data that organizational policy permits, remove sensitive fields where possible, and apply required financial-data handling controls before sharing inputs. <br>\nRisk: Broad finance trigger wording may activate the skill when the user did not intend finance-specific guidance. <br>\nMitigation: Confirm the financial analysis context and requested output before relying on the generated analysis or templates. <br>\nRisk: Generated financial analysis, dashboard logic, or code examples may be incomplete or unsuitable for a regulated decision. <br>\nMitigation: Have qualified reviewers validate assumptions, formulas, source data, compliance needs, and resulting reports before operational use. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/gechengling/finance-data-analysis) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, code, guidance] <br>\n**Output Format:** [Markdown with explanatory text and code blocks] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [May include finance analysis templates, KPI dashboard structures, reporting guidance, and Python or SQL examples.] <br>\n\n## Skill Version(s): <br>\n3.0.1 (source: server release evidence and skill frontmatter) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>","readmeExcerpt":"Skill: Finance Data Analysis Owner: gechengling Summary: Provides AI-driven financial data analysis including KPI tracking, financial statement evaluation, data visualization, and automated reporting for decision s... Tags: banking:5.0.0, dianjin:5.0.0, finance:5.0.0, finance-data-analysis:5.0.3, insurance:5.0.0, latest:5.0.3 Version history: v5.0.3 | 2026-09-15T14:22:39.395Z | user 内容增强与修正（4235→8761字符）：修复 frontmatte","codeSnippets":[],"executableExamples":[{"language":"python","snippet":"class FinancialAnalyzer:\n    \"\"\"财务分析引擎（教学示例骨架）\"\"\"\n\n    def income_statement_analysis(self, data: dict) -> dict:\n        \"\"\"损益表分析：趋势 + 结构 + 质量\"\"\"\n        return {\n            \"收入趋势\": self._trend_analysis(data[\"revenue\"]),\n            \"毛利率分析\": self._gross_margin_analysis(data),\n            \"费用结构\": self._expense_breakdown(data),\n            \"利润质量\": self._profit_quality_analysis(data),\n        }\n\n    def ratio_analysis(self, financial_data: dict) -> dict:\n        \"\"\"比率分析：三大类核心比率\"\"\"\n        return {\n            \"盈利能力\": {\n                \"毛利率\": financial_data[\"gross_profit\"] / financial_data[\"revenue\"],\n                \"净利率\": financial_data[\"net_profit\"] / financial_data[\"revenue\"],\n                \"ROE\": financial_data[\"net_profit\"] / financial_data[\"equity\"],\n            },\n            \"运营效率\": {\n                \"存货周转\": financial_data[\"cogs\"] / financial_data[\"inventory\"],\n                \"应收账款周转\": financial_data[\"revenue\"] / financial_data[\"ar\"],\n            },\n            \"偿债能力\": {\n                \"流动比率\": financial_data[\"current_assets\"] / financial_data[\"current_liabilities\"],\n                \"资产负债率\": financial_data[\"total_liabilities\"] / financial_data[\"total_assets\"],\n            },\n        }"},{"language":"sql","snippet":"-- 示例：月度经营指标口径对齐查询（教学示例，未连接任何真实库）\nSELECT 月份,\n       业务线,\n       SUM(保费收入)                     AS 保费收入,\n       SUM(已赚保费)                     AS 已赚保费,\n       SUM(赔付支出)                     AS 赔付支出,\n       ROUND(SUM(赔付支出) / NULLIF(SUM(已赚保费), 0), 4) AS 综合赔付率\nFROM   dwd_经营明细\nWHERE  月份 BETWEEN '2026-06' AND '2026-08'\n  AND  数据版本 = '月结最终版'          -- 口径冻结标记，避免\"月中数\"混入\nGROUP  BY 月份, 业务线\nORDER  BY 月份, 业务线;"},{"language":"python","snippet":"DASHBOARD_TEMPLATES = {\n    \"CFO驾驶舱\": {\n        \"audience\": \"董事会 / 经营班子\",\n        \"refresh\": \"月度为主，关键指标日频\",\n        \"widgets\": [\n            {\"type\": \"kpi_card\",  \"metrics\": [\"营收\", \"利润\", \"ROE\"]},\n            {\"type\": \"line_chart\", \"data\": \"收入趋势\"},\n            {\"type\": \"bar_chart\", \"data\": \"各业务线收入\"},\n            {\"type\": \"waterfall\", \"data\": \"利润变动归因\"},\n            {\"type\": \"gauge\",     \"data\": \"KPI完成率\"},\n        ],\n    },\n    \"业务分析看板\": {\n        \"audience\": \"业务条线负责人\",\n        \"refresh\": \"周度 / 日频\",\n        \"widgets\": [\n            {\"type\": \"funnel\",    \"data\": \"转化漏斗\"},\n            {\"type\": \"heat_map\",  \"data\": \"客户活跃度\"},\n            {\"type\": \"pie_chart\", \"data\": \"客户分布\"},\n            {\"type\": \"trend\",     \"data\": \"关键指标趋势\"},\n        ],\n    },\n}"},{"language":"python","snippet":"class FinancialAnalyzer:\n    \"\"\"财务分析引擎\"\"\"\n    \n    def income_statement_analysis(self, data: dict) -> dict:\n        \"\"\"损益表分析\"\"\"\n        return {\n            \"收入趋势\": self._trend_analysis(data[\"revenue\"]),\n            \"毛利率分析\": self._gross_margin_analysis(data),\n            \"费用结构\": self._expense_breakdown(data),\n            \"利润质量\": self._profit_quality_analysis(data)\n        }\n    \n    def ratio_analysis(self, financial_data: dict) -> dict:\n        \"\"\"比率分析\"\"\"\n        ratios = {\n            \"盈利能力\": {\n                \"毛利率\": data[\"gross_profit\"] / data[\"revenue\"],\n                \"净利率\": data[\"net_profit\"] / data[\"revenue\"],\n                \"ROE\": data[\"net_profit\"] / data[\"equity\"]\n            },\n            \"运营效率\": {\n                \"存货周转\": data[\"cogs\"] / data[\"inventory\"],\n                \"应收账款周转\": data[\"revenue\"] / data[\"ar\"]\n            },\n            \"偿债能力\": {\n                \"流动比率\": data[\"current_assets\"] / data[\"current_liabilities\"],\n                \"资产负债率\": data[\"total_liabilities\"] / data[\"total_assets\"]\n            }\n        }\n        return ratios"},{"language":"python","snippet":"DASHBOARD_TEMPLATES = {\n    \"CFO驾驶舱\": {\n        \"widgets\": [\n            {\"type\": \"kpi_card\", \"metrics\": [\"营收\", \"利润\", \"ROE\"]},\n            {\"type\": \"line_chart\", \"data\": \"收入趋势\"},\n            {\"type\": \"bar_chart\", \"data\": \"各业务线收入\"},\n            {\"type\": \"waterfall\", \"data\": \"利润变动归因\"},\n            {\"type\": \"gauge\", \"data\": \"KPI完成率\"}\n        ]\n    },\n    \"业务分析看板\": {\n        \"widgets\": [\n            {\"type\": \"funnel\", \"data\": \"转化漏斗\"},\n            {\"type\": \"heat_map\", \"data\": \"客户活跃度\"},\n            {\"type\": \"pie_chart\", \"data\": \"客户分布\"},\n            {\"type\": \"trend\", \"data\": \"关键指标趋势\"}\n        ]\n    }\n}"},{"language":"python","snippet":"class FinancialAnalyzer:\n    \"\"\"财务分析引擎\"\"\"\n    \n    def income_statement_analysis(self, data: dict) -> dict:\n        \"\"\"损益表分析\"\"\"\n        return {\n            \"收入趋势\": self._trend_analysis(data[\"revenue\"]),\n            \"毛利率分析\": self._gross_margin_analysis(data),\n            \"费用结构\": self._expense_breakdown(data),\n            \"利润质量\": self._profit_quality_analysis(data)\n        }\n    \n    def ratio_analysis(self, financial_data: dict) -> dict:\n        \"\"\"比率分析\"\"\"\n        ratios = {\n            \"盈利能力\": {\n                \"毛利率\": data[\"gross_profit\"] / data[\"revenue\"],\n                \"净利率\": data[\"net_profit\"] / data[\"revenue\"],\n                \"ROE\": data[\"net_profit\"] / data[\"equity\"]\n            },\n            \"运营效率\": {\n                \"存货周转\": data[\"cogs\"] / data[\"inventory\"],\n                \"应收账款周转\": data[\"revenue\"] / data[\"ar\"]\n            },\n            \"偿债能力\": {\n                \"流动比率\": data[\"current_assets\"] / data[\"current_liabilities\"],\n                \"资产负债率\": data[\"total_liabilities\"] / data[\"total_assets\"]\n            }\n        }\n        return ratios"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: Financial Industry Data Analysis Expert\nslug: finance-data-analysis\ndescription: AI-powered financial data analysis expert — covers financial statement analysis, KPI tracking, trend analysis, data visualization, and automated reporting. Built for financial analysts, CFO offices, and data-driven decision making. Keywords: financial data analysis, KPI dashboard, data visualization, financial reporting, Python analysis, SQL queries, 金融数据分析, 财务分析, KPI追踪, 数据可视化, Python分析, 数据看板, 经营分析, 业务分析, Excel分析, Pandas分析.\nversion: \"5.0.3\"\nallowed-tools: []\ncapabilities:\n  - educational-reference\n  - advisory-only\n  - requires-human-review\n  - code-examples-reference\n---\n\n# Financial Industry Data Analysis Expert / 金融数据分析专家\n\n> **⚠️ SECURITY NOTICE**\n> - **Type:** Educational reference / analytical framework ONLY\n> - **技能本身不包含可执行代码**，文中 Python / SQL 片段均为**教学示例**，不会被本技能自动运行\n> - **No persistent storage and no background execution** — 本技能不创建、不写入、不读取任何文件\n> - **No credential collection, no PII processing, no system access** — 不接触数据库连接串、账号口令或生产数据\n> - **All outputs require human review before real-world application**\n> - **NOT financial, legal, or insurance advice**\n>\n> **⚠️ 数据安全警告**\n> - 本技能仅提供金融数据分析的方法论参考框架，**不执行任何代码或脚本**\n> - 文中提到的市场数据查询、资金流向分析为**教学方法论展示**，不涉及实际的 API 调用或数据采集\n> - 使用者如将示例代码落地，须自行完成**数据脱敏、权限审批与留痕**，不得将客户身份信息、账户信息带入分析环境\n> - 所有分析结果仅供参考，不构成投资建议或审计意见\n\n> **English:** AI-powered financial data analysis — covers financial statements, KPIs, visualization, and automated reporting.\n>\n> **中文:** 金融数据分析——覆盖财务报表、KPI、可视化、自动化报告。\n\n---\n\n## 金融监管与行业动态（截至 2026-09-15）\n\n| 动态类型 | 内容摘要 | 对分析工作的影响 |\n|---------|---------|----------------|\n| 监管合规 | 数据安全与个人信息保护要求在金融业持续压实，\"最小必要\"原则成为分析取数的默认前提 | 取数环节须可溯源、可解释；分析底稿需记录数据来源与使用范围 |\n| 监管合规 | 金融\"五篇大文章\"（科技、绿色、普惠、养老、数字金融）统计口径逐步细化 | KPI 体系需与监管口径对齐，避免同一指标多口径并存 |\n| 监管合规 | 反洗钱与可疑交易监控的数据要求持续加强 | 客户维度分析需区分\"分析用\"与\"报送用\"两套口径与授权 |\n| 监管合规 | 理财与保险产品信息披露透明度要求提高 | 产品类经营分析需同时满足内部分析与对外披露两类口径 |\n| 行业趋势 | 经营分析从\"报表解读\"转向\"指标归因 + 前瞻预测\" | 分析交付物需包含归因链条与情景假设，而非仅同比环比 |\n| 行业趋势 | 数据中台与指标体系治理成为金融机构标准动作 | 指标定义、口径、责任人需成体系管理，避免\"同名不同义\" |\n| 行业趋势 | 大模型辅助取数、解读与报告生成进入实用阶段 | 生成结果必须人工复核，数字与结论不得直接对外使用 |\n| 技术演进 | 湖仓一体与流批一体降低\"日终批量\"分析的时延 | 日频分析可向准实时演进，但对账与口径一致性要求同步提高 |\n\n> **数据截止**: 2026-09-15 | 来源：国家金融监督管理总局、中国人民银行、中国证监会、中国证券业协会、行业公开研究\n> **声明**: 以上动态供参考，政策与口径以官方最新发布为准\n\n---\n\n## Industry Pain Points / 行业痛点\n\n| Pain Point / 痛点 | Impact / 影响 | Solution / 本Skill解决方案 |\n|------------------|-------------|------------------------|\n| **数据分散** | 数据源多、系统异构，整合耗时且口径不一 | 统一数据模型与指标字典 |\n| **手工报表多** | 月报/季报重复劳动，易出错、难追溯 | 报告模板化 + 生成流程标准化 |\n| **分析浅** | 只看表面数字，缺归因与前瞻 | 三层归因分析框架 |\n| **可视化差** | 图表不直观，管理层读不出结论 | 图表选型对照表 |\n| **口径打架** | 同一指标各部门定义不同 | 指标口径与责任人矩阵 |\n| **合规风险** | 取数越界、留痕缺失 | 数据使用纪律与留痕清单 |\n\n---\n\n## Trigger Keywords / 触发关键词\n\n**English Triggers:** financial data analysis, KPI dashboard, data visualization, financial reporting, Python analysis\n\n**中文触发词：** 数据分析 / 财务分析 / KPI追踪 / 数据可视化 / 自动化报告 / Python分析 / SQL查询 / 数据看板 / 经营分析 / 业绩分析 / 同比环比 / 指标归因 / 报表搭建 / 口径对齐\n\n---\n\n## Core Capabilities / 核心能力\n\n### 1. Fi"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn74e704j3ygjcygnpf02rdvd185js13\",\n  \"slug\": \"finance-data-analysis\",\n  \"version\": \"5.0.3\",\n  \"publishedAt\": 1789482159395\n}"},{"path":"skill-card.md","content":"## Description:\n\nProvides financial analysts and finance teams with reference frameworks for financial statement analysis, KPI tracking, trend analysis, data visualization, and reporting.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[gechengling](https://clawhub.ai/user/gechengling)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nFinancial analysts, CFO office teams, and data-driven finance users use this skill to structure KPI dashboards, financial statement reviews, trend analysis, visualization choices, and reporting workflows. The skill is advisory and its outputs should be reviewed before business, investment, audit, legal, or regulatory use.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Financial analysis outputs may be incorrect, incomplete, or mistaken for financial, legal, insurance, audit, or investment advice.\n\nMitigation: Require qualified human review before using outputs for decisions, reporting, disclosure, audit, or regulatory work.\n\nRisk: Users may include customer, account, credential, or production financial data in uncontrolled prompts or downstream examples.\n\nMitigation: Keep real customer and account data out of uncontrolled prompts; use approved, minimized, aggregated, or desensitized data only.\n\nRisk: Broad finance and Chinese trigger terms may activate the skill in conversations where the reference framework is not intended.\n\nMitigation: Narrow trigger terms during deployment if unintended activation would disrupt agent behavior.\n\n## Reference(s):\n\n\n## Skill Output:\n\n**Output Type(s):** [Analysis, Code, Guidance]\n\n**Output Format:** [Markdown with Python and SQL example code blocks]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Advisory reference output requiring human review; no tool execution or data access.]\n\n## Skill Version(s):\n\n5.0.3 (source: frontmatter and server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Provides AI-driven financial data analysis including KPI tracking, financial statement evaluation, data visualization, and automated reporting for decision s... Skill: Finance Data Analysis Owner: gechengling Summary: Provides AI-driven financial data analysis including KPI tracking, financial statement evaluation, data visualization, and automated reporting for decision s... Tags: banking:5.0.0, dianjin:5.0.0, finance:5.0.0, finance-data-analysis:5.0.3, insurance:5.0.0, latest:5.0.3 Version history: v5.0.3 | 2026-09-15T14:22:39.395Z | user 内容增强与修正（4235→8761字符）：修复 frontmatte","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1024,"uniquenessScore":50,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-10T19:03:00.579Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-10T19:03:00.579Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-10T21:47:43.039Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}