Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →高管持股Skill - 提供高管增减持、持股变动、薪酬分析 via AkShare
.claude/skills/aifinlab-akshare-executive/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | -34% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 5% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 31% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -15% | 0% |
| 属性 | 内容 | |:---|:---| | 名称 | akshare-executive | | 版本 | 1.1.0 | | 分类 | 高管持股 | | 状态 | ✅ 已上线 | | 维护者 | FinClaw Core Team | | 最后更新 | 2026-03-19 |
高管持股Skill，提供A股上市公司高管（董事、监事、高管）的持股变动、增减持记录、薪酬分析等功能。追踪管理层信心信号。
| 用户输入 | 识别意图 | 调用函数 | |:---|:---|:---| | 高管增减持 | executive_change | executive_change.py --limit 30 | | 茅台高管持股 | executive_stock | executive_stock.py --code 600519 | | 高管增持排行 | executive_buy | executive_buy.py | | 高管减持排行 | executive_sell | executive_sell.py |
| 数据类型 | 主要来源 | 备用来源 | 认证要求 | |:---|:---|:---|:---:| | 高管持股 | AkShare-交易所 | - | 无需 |
| 职位 | 说明 | |:---|:---| | 董事 | 董事长、副董事长、独立董事 | | 监事 | 监事会主席、监事 | | 高管 | 总经理、副总经理、财务总监、董秘 |
bash python scripts/executive_change.py --limit 30
bash python scripts/executive_stock.py --code 600519
bash python scripts/executive_buy.py
bash python scripts/executive_sell.py
| 脚本名 | 功能 | 入口点 | |:---|:---|:---:| | executive_change.py | 高管增减持 | ✅ | | executive_stock.py | 个股高管变动 | ✅ | | executive_buy.py | 高管增持排行 | ✅ | | executive_sell.py | 高管减持排行 | ✅ |
| 情形 | 信号强度 | 解读 | |:---|:---:|:---| | 董事长增持 | ⭐⭐⭐⭐⭐ | 最强烈信心信号 | | 总经理增持 | ⭐⭐⭐⭐ | 管理层看好 | | 多位高管同时增持 | ⭐⭐⭐⭐⭐ | 集体看好 | | 小额增持（<50万） | ⭐⭐ | 象征性增持 | | 高管减持（非解禁） | 🔴🔴🔴 | 需警惕 | | 解禁后减持 | 🔴🔴 | 正常套现 |
markdown--- 📊 **数据来源**: AkShare-交易所 ⏱️ **数据时间**: 2026-03-19 📌 **数据类型**: 高管增减持 🔗 **原始来源**: 上市公司公告 🔧 **分析工具**: FinClaw v1.0
akshare>=1.10.0
pandas>=1.3.0
pyyaml>=5.4.0| 版本 | 日期 | 变更内容 | |:---|:---:|:---| | 1.1.0 | 2026-03-19 | 符合FinClaw数据规范v1.0，新增高管增减持信号 | | 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-03 | fail→fail | 23,629 | 4,892 | -79% | 1 | 1 | 0% | 3,092 | 1,771 | -43% | 0 | 0 | — |
case-01 | fail→fail | 14,073 | 7,698 | -45% | 1 | 1 | 0% | 2,015 | 2,604 | +29% | 0 | 0 | — |
case-02 | fail→fail | 16,706 | 21,791 | +30% | 1 | 1 | 0% | 2,201 | 5,121 | +133% | 0 | 0 | — |
case-04 | fail→fail | 18,924 | 8,668 | -54% | 1 | 1 | 0% | 3,491 | 1,861 | -47% | 0 | 0 | — |
case-05 | fail→pass | 21,514 | 4,800 | -78% | 1 | 1 | 0% | 3,222 | 2,111 | -34% | 0 | 0 | — |
case-06 | pass→pass | 20,133 | 17,554 | -13% | 1 | 1 | 0% | 2,768 | 3,957 | +43% | 0 | 0 | — |
case-07 | fail→pass | 19,386 | 8,598 | -56% | 1 | 1 | 0% | 2,470 | 2,596 | +5% | 0 | 0 | — |
case-12 | fail→pass | 12,614 | 3,038 | -76% | 1 | 1 | 0% | 2,124 | 1,786 | -16% | 0 | 0 | — |
case-08 | fail→pass | 24,875 | 21,911 | -12% | 1 | 1 | 0% | 3,165 | 4,145 | +31% | 0 | 0 | — |
case-09 | fail→pass | 18,693 | 7,707 | -59% | 1 | 1 | 0% | 2,647 | 2,250 | -15% | 0 | 0 | — |
case-10 | fail→pass | 13,427 | 10,924 | -19% | 1 | 1 | 0% | 1,853 | 2,923 | +58% | 0 | 0 | — |
case-11 | fail→pass | 25,207 | 18,090 | -28% | 1 | 1 | 0% | 3,129 | 3,837 | +23% | 0 | 0 | — |
case-13 | pass→pass | 11,904 | 5,939 | -50% | 1 | 1 | 0% | 2,090 | 2,168 | +4% | 0 | 0 | — |
case-14 | pass→pass | 14,844 | 3,936 | -73% | 1 | 1 | 0% | 2,266 | 1,786 | -21% | 0 | 0 | — |
case-15 | pass→pass | 18,942 | 6,136 | -68% | 1 | 1 | 0% | 2,386 | 2,250 | -6% | 0 | 0 | — |
case-16 | fail→pass | 9,629 | 2,661 | -72% | 1 | 1 | 0% | 1,498 | 1,654 | +10% | 0 | 0 | — |
case-17 | pass→pass | 12,858 | 2,569 | -80% | 1 | 1 | 0% | 1,887 | 1,680 | -11% | 0 | 0 | — |
case-18 | fail→pass | 12,274 | 3,211 | -74% | 1 | 1 | 0% | 2,010 | 1,734 | -14% | 0 | 0 | — |
case-19 | fail→pass | 12,758 | 5,036 | -61% | 1 | 1 | 0% | 1,990 | 1,780 | -11% | 0 | 0 | — |
case-20 | fail→pass | 11,969 | 4,684 | -61% | 1 | 1 | 0% | 1,861 | 1,839 | -1% | 0 | 0 | — |
case-21 | pass→pass | 15,447 | 17,975 | +16% | 1 | 1 | 0% | 2,769 | 3,907 | +41% | 0 | 0 | — |
case-22 | pass→pass | 15,489 | 20,961 | +35% | 1 | 1 | 0% | 2,268 | 3,888 | +71% | 0 | 0 | — |
case-23 | pass→pass | 14,566 | 16,277 | +12% | 1 | 1 | 0% | 2,632 | 4,021 | +53% | 0 | 0 | — |
case-24 | pass→pass | 18,607 | 19,832 | +7% | 1 | 1 | 0% | 2,951 | 4,459 | +51% | 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. 24 cases were attempted. The headline lift of +46 percentage points is the difference between those two pass rates over the 24 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.