Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →财报数据Skill - 提供三大报表、财务指标、杜邦分析 via AkShare
.claude/skills/aifinlab-akshare-report/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 48% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 49% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 137% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -34% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -17% | 0% |
| 属性 | 内容 | |:---|:---| | 名称 | akshare-report | | 版本 | 1.1.0 | | 分类 | 财报数据 | | 状态 | ✅ 已上线 | | 维护者 | FinClaw Core Team | | 最后更新 | 2026-03-19 |
财报数据Skill，提供上市公司三大财务报表（资产负债表、利润表、现金流量表）查询、财务指标分析、杜邦分析等功能。
| 用户输入 | 识别意图 | 调用函数 | |:---|:---|:---| | 茅台财报数据 | financial_report | financial_report.py 600519 | | 财务指标分析 | financial_indicator | financial_indicator.py 600519 | | 杜邦分析 | financial_dupont | financial_dupont.py 600519 | | 最新季报 | financial_report | financial_report.py 600519 --latest |
| 数据类型 | 主要来源 | 备用来源 | 认证要求 | |:---|:---|:---|:---:| | 三大报表 | AkShare-东方财富 | - | 无需 | | 财务指标 | AkShare | - | 无需 |
| 报表 | 主要内容 | 关键指标 | |:---|:---|:---| | 资产负债表 | 资产、负债、股东权益 | 资产负债率、流动比率 | | 利润表 | 收入、成本、利润 | 营收、净利润、毛利率 | | 现金流量表 | 经营/投资/筹资现金流 | 经营现金流、自由现金流 |
bash python scripts/financial_report.py 600519 python scripts/financial_report.py 600519 --type annual
bash python scripts/financial_indicator.py 600519
bash python scripts/financial_dupont.py 600519
| 指标 | 公式 | 优秀标准 | |:---|:---|:---:| | ROE | 净利润/净资产 | >15% | | ROA | 净利润/总资产 | >8% | | 毛利率 | (营收-成本)/营收 | >30% | | 净利率 | 净利润/营收 | >10% | | 资产负债率 | 负债/资产 | <60% | | 流动比率 | 流动资产/流动负债 | >1.5 | | 速动比率 | (流动资产-存货)/流动负债 | >1.0 |
ROE = 净利率 × 资产周转率 × 权益乘数
净利润 营业收入 总资产
= ────── × ──────── × ────────
营业收入 总资产 净资产
解读:
- 净利率: 盈利能力
- 资产周转率: 运营效率
- 权益乘数: 财务杠杆| 脚本名 | 功能 | 入口点 | |:---|:---|:---:| | financial_report.py | 三大表数据 | ✅ | | financial_indicator.py | 财务指标 | ✅ | | financial_dupont.py | 杜邦分析 | ✅ |
markdown--- 📊 **数据来源**: AkShare-东方财富 ⏱️ **数据时间**: 2026-03-19 📌 **报告期**: 2025年年报 🔗 **原始来源**: 上市公司年报 🔧 **分析工具**: FinClaw v1.0
akshare>=1.10.0
pandas>=1.3.0
pyyaml>=5.4.0| 报告 | 披露时间 | |:---|:---| | 一季报 | 4月1日-4月30日 | | 半年报 | 7月1日-8月31日 | | 三季报 | 10月1日-10月31日 | | 年报 | 次年1月1日-4月30日 |
| 版本 | 日期 | 变更内容 | |:---|:---:|:---| | 1.1.0 | 2026-03-19 | 符合FinClaw数据规范v1.0，新增杜邦分析 | | 1.0.0 | 2026-03-13 | 初始版本 |
本Skill遵循 FinClaw 数据规范 v1.0 | 数据来源强制标注 | 禁止训练数据编造
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-22 | pass→pass | 11,523 | 2,802 | -76% | 1 | 1 | 0% | 1,887 | 1,869 | -1% | 0 | 0 | — |
case-03 | fail→pass | 20,759 | 27,101 | +31% | 1 | 1 | 0% | 3,081 | 4,564 | +48% | 0 | 0 | — |
case-13 | pass→pass | 12,138 | 10,201 | -16% | 1 | 1 | 0% | 2,133 | 3,125 | +47% | 0 | 0 | — |
case-01 | fail→fail | 7,420 | 7,081 | -5% | 1 | 1 | 0% | 484 | 1,842 | +281% | 0 | 0 | — |
case-02 | fail→pass | 17,781 | 12,367 | -30% | 1 | 1 | 0% | 2,483 | 3,690 | +49% | 0 | 0 | — |
case-04 | fail→pass | 9,610 | 12,232 | +27% | 1 | 1 | 0% | 1,401 | 3,315 | +137% | 0 | 0 | — |
case-05 | fail→fail | 13,506 | 11,845 | -12% | 1 | 1 | 0% | 1,710 | 3,286 | +92% | 0 | 0 | — |
case-06 | pass→pass | 7,709 | 4,854 | -37% | 1 | 1 | 0% | 990 | 2,218 | +124% | 0 | 0 | — |
case-07 | fail→pass | 20,141 | 3,568 | -82% | 1 | 1 | 0% | 3,053 | 2,015 | -34% | 0 | 0 | — |
case-08 | fail→pass | 19,400 | 4,763 | -75% | 1 | 1 | 0% | 2,534 | 2,094 | -17% | 0 | 0 | — |
case-09 | fail→pass | 15,486 | 3,796 | -75% | 1 | 1 | 0% | 2,180 | 2,166 | -1% | 0 | 0 | — |
case-10 | fail→pass | 10,897 | 3,237 | -70% | 1 | 1 | 0% | 1,531 | 1,867 | +22% | 0 | 0 | — |
case-11 | pass→pass | 12,333 | 8,977 | -27% | 1 | 1 | 0% | 1,914 | 2,725 | +42% | 0 | 0 | — |
case-12 | pass→pass | 10,722 | 13,598 | +27% | 1 | 1 | 0% | 1,644 | 3,441 | +109% | 0 | 0 | — |
case-14 | fail→pass | 9,743 | 4,848 | -50% | 1 | 1 | 0% | 1,679 | 2,319 | +38% | 0 | 0 | — |
case-15 | pass→pass | 4,476 | 3,323 | -26% | 1 | 1 | 0% | 647 | 2,068 | +220% | 0 | 0 | — |
case-16 | pass→pass | 8,599 | 5,407 | -37% | 1 | 1 | 0% | 1,193 | 2,606 | +118% | 0 | 0 | — |
case-17 | pass→pass | 9,405 | 5,454 | -42% | 1 | 1 | 0% | 1,258 | 2,492 | +98% | 0 | 0 | — |
case-18 | fail→pass | 11,345 | 5,951 | -48% | 1 | 1 | 0% | 2,146 | 2,647 | +23% | 0 | 0 | — |
case-19 | pass→pass | 11,241 | 4,200 | -63% | 1 | 1 | 0% | 1,921 | 2,299 | +20% | 0 | 0 | — |
case-20 | fail→pass | 6,063 | 3,366 | -44% | 1 | 1 | 0% | 839 | 2,108 | +151% | 0 | 0 | — |
case-21 | fail→fail | 9,266 | 9,887 | +7% | 1 | 1 | 0% | 1,696 | 3,303 | +95% | 0 | 0 | — |
case-23 | pass→pass | 11,457 | 3,276 | -71% | 1 | 1 | 0% | 1,851 | 1,992 | +8% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted, and 22 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +43 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.