Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →股东数据Skill - 提供股东增减持、机构持仓、筹码分布、十大流通股东 via AkShare
.claude/skills/aifinlab-akshare-holders/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 30% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -36% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -42% | 0% |
| 属性 | 内容 | |:---|:---| | 名称 | akshare-holders | | 版本 | 1.1.0 | | 分类 | 股东数据 | | 状态 | ✅ 已上线 | | 维护者 | FinClaw Core Team | | 最后更新 | 2026-03-19 |
股东数据Skill，提供股东增减持动态、机构持仓变化、筹码分布分析、十大流通股东等信息。追踪大股东、机构、散户的持仓变动，识别主力进出信号。
| 用户输入 | 识别意图 | 调用函数 | |:---|:---|:---| | 茅台股东增减持 | holders_change | holders_change.py 600519 | | 机构持仓情况 | holders_institutional | holders_institutional.py 600519 | | 筹码分布如何？ | holders_chips | holders_chips.py 600519 | | 最新十大股东 | holders_top10 | holders_change.py --detail |
| 数据类型 | 主要来源 | 备用来源 | 认证要求 | |:---|:---|:---|:---:| | 股东增减持 | AkShare-交易所 | - | 无需 | | 机构持仓 | AkShare-交易所 | - | 无需 | | 筹码分布 | AkShare | - | 无需 | | 十大股东 | AkShare-交易所 | - | 无需 |
bash python scripts/holders_change.py 600519 python scripts/holders_change.py --detail # 详细持股变动
bash python scripts/holders_institutional.py 600519
bash python scripts/holders_chips.py 600519
| 脚本名 | 功能 | 入口点 | |:---|:---|:---:| | holders_change.py | 股东增减持 | ✅ | | holders_institutional.py | 机构持仓 | ✅ | | holders_chips.py | 筹码分布 | ✅ |
| 情形 | 信号强度 | 解读 | |:---|:---:|:---| | 大股东增持 >5% | ⭐⭐⭐⭐⭐ | 强烈看好，底部信号 | | 董监高增持 | ⭐⭐⭐⭐ | 管理层信心 | | 机构大幅增持 | ⭐⭐⭐ | 机构调研后加仓 | | 小股东增持 | ⭐⭐ | 一般性投资 |
| 情形 | 信号强度 | 解读 | |:---|:---:|:---| | 大股东减持 >5% | 🔴🔴🔴🔴🔴 | 重大利空 | | 董监高减持 | 🔴🔴🔴🔴 | 需警惕 | | 机构大幅减持 | 🔴🔴🔴 | 机构看空 | | 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**: 股东增减持 🔗 **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 | | 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-01 | fail→pass | 17,055 | 17,386 | +2% | 1 | 1 | 0% | 2,772 | 3,605 | +30% | 0 | 0 | — |
case-02 | fail→pass | 20,390 | 16,520 | -19% | 1 | 1 | 0% | 3,096 | 3,271 | +6% | 0 | 0 | — |
case-03 | fail→pass | 26,795 | 24,622 | -8% | 1 | 1 | 0% | 3,501 | 4,290 | +23% | 0 | 0 | — |
case-04 | fail→pass | 21,447 | 6,503 | -70% | 1 | 1 | 0% | 3,839 | 2,455 | -36% | 0 | 0 | — |
case-05 | pass→pass | 16,009 | 3,504 | -78% | 1 | 1 | 0% | 2,547 | 1,914 | -25% | 0 | 0 | — |
case-06 | fail→pass | 18,006 | 3,392 | -81% | 1 | 1 | 0% | 3,234 | 1,861 | -42% | 0 | 0 | — |
case-07 | fail→pass | 7,730 | 2,869 | -63% | 1 | 1 | 0% | 1,275 | 1,792 | +41% | 0 | 0 | — |
case-08 | pass→pass | 24,572 | 13,338 | -46% | 1 | 1 | 0% | 2,982 | 3,267 | +10% | 0 | 0 | — |
case-09 | fail→pass | 19,379 | 10,974 | -43% | 1 | 1 | 0% | 2,692 | 2,860 | +6% | 0 | 0 | — |
case-10 | fail→fail | 17,579 | 15,702 | -11% | 1 | 1 | 0% | 2,552 | 3,531 | +38% | 0 | 0 | — |
case-11 | fail→pass | 19,028 | 12,796 | -33% | 1 | 1 | 0% | 2,646 | 3,248 | +23% | 0 | 0 | — |
case-12 | fail→pass | 19,729 | 15,954 | -19% | 1 | 1 | 0% | 2,785 | 3,309 | +19% | 0 | 0 | — |
case-13 | fail→pass | 22,769 | 14,935 | -34% | 1 | 1 | 0% | 2,759 | 3,298 | +20% | 0 | 0 | — |
case-14 | fail→pass | 18,400 | 17,836 | -3% | 1 | 1 | 0% | 2,563 | 3,904 | +52% | 0 | 0 | — |
case-15 | fail→pass | 23,729 | 8,649 | -64% | 1 | 1 | 0% | 3,009 | 2,664 | -11% | 0 | 0 | — |
case-16 | fail→pass | 10,249 | 3,378 | -67% | 1 | 1 | 0% | 1,374 | 1,692 | +23% | 0 | 0 | — |
case-17 | fail→pass | 18,401 | 2,754 | -85% | 1 | 1 | 0% | 2,373 | 1,783 | -25% | 0 | 0 | — |
case-18 | fail→pass | 10,915 | 3,366 | -69% | 1 | 1 | 0% | 1,706 | 1,805 | +6% | 0 | 0 | — |
case-19 | fail→pass | 8,087 | 2,135 | -74% | 1 | 1 | 0% | 1,263 | 1,590 | +26% | 0 | 0 | — |
case-20 | pass→pass | 24,191 | 11,869 | -51% | 1 | 1 | 0% | 3,694 | 3,408 | -8% | 0 | 0 | — |
case-21 | fail→fail | 24,394 | 22,732 | -7% | 1 | 1 | 0% | 3,157 | 4,355 | +38% | 0 | 0 | — |
case-22 | fail→fail | 19,987 | 20,447 | +2% | 1 | 1 | 0% | 3,043 | 4,528 | +49% | 0 | 0 | — |
case-23 | fail→fail | 19,657 | 19,795 | +1% | 1 | 1 | 0% | 2,902 | 4,202 | +45% | 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. The headline lift of +70 percentage points is the difference between those two pass rates over the 23 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.