Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →QFII/QDII数据Skill - 提供QFII持仓、QDII基金、外资动向分析 via AkShare
.claude/skills/aifinlab-akshare-qfii/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -55% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 11% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -28% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -49% | 0% |
| 属性 | 内容 | |:---|:---| | 名称 | akshare-qfii | | 版本 | 1.1.0 | | 分类 | QFII/QDII | | 状态 | ✅ 已上线 | | 维护者 | FinClaw Core Team | | 最后更新 | 2026-03-19 |
QFII/QDII数据Skill，提供QFII（合格境外机构投资者）持仓、QDII（合格境内机构投资者）基金、外资动向分析等功能。
| 用户输入 | 识别意图 | 调用函数 | |:---|:---|:---| | QFII持仓 | qfii_holdings | qfii_holdings.py --year 2024 --quarter 3 | | QDII基金列表 | qdii_list | qdii_list.py | | QDII净值 | qdii_nav | qdii_nav.py --code 000041 |
| 数据类型 | 主要来源 | 备用来源 | 认证要求 | |:---|:---|:---|:---:| | QFII/QDII | AkShare | - | 无需 |
| 维度 | QFII | QDII | |:---|:---|:---| | 方向 | 外资投资A股 | 内资投资海外 | | 主体 | 境外机构 | 境内机构 | | 标的 | A股/债券 | 海外股票/基金 | | 额度 | 有额度限制 | 有额度限制 |
bash python scripts/qfii_holdings.py --year 2024 --quarter 3
bash python scripts/qdii_list.py
bash python scripts/qdii_nav.py --code 000041
| 脚本名 | 功能 | 入口点 | |:---|:---|:---:| | qfii_holdings.py | QFII持仓 | ✅ | | qdii_list.py | QDII列表 | ✅ | | qdii_nav.py | QDII净值 | ✅ |
markdown--- 📊 **数据来源**: AkShare ⏱️ **数据时间**: 2026-03-19 📌 **数据类型**: QFII持仓/QDII基金 🔗 **原始来源**: 证监会/基金业协会 🔧 **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-12 | pass→pass | 12,086 | 2,863 | -76% | 1 | 1 | 0% | 1,504 | 1,410 | -6% | 0 | 0 | — |
case-01 | fail→pass | 16,827 | 18,462 | +10% | 1 | 1 | 0% | 2,825 | 3,101 | +10% | 0 | 0 | — |
case-02 | fail→fail | 18,462 | 9,923 | -46% | 1 | 1 | 0% | 2,721 | 1,470 | -46% | 0 | 0 | — |
case-03 | fail→fail | 11,481 | 13,138 | +14% | 1 | 1 | 0% | 1,704 | 1,553 | -9% | 0 | 0 | — |
case-04 | fail→pass | 22,966 | 5,002 | -78% | 1 | 1 | 0% | 4,151 | 1,883 | -55% | 0 | 0 | — |
case-05 | fail→pass | 20,906 | 12,558 | -40% | 1 | 1 | 0% | 2,872 | 3,183 | +11% | 0 | 0 | — |
case-06 | fail→pass | 13,681 | 3,757 | -73% | 1 | 1 | 0% | 2,270 | 1,636 | -28% | 0 | 0 | — |
case-07 | fail→fail | 17,655 | 26,251 | +49% | 1 | 1 | 0% | 2,942 | 4,075 | +39% | 0 | 0 | — |
case-08 | fail→fail | 15,327 | 12,705 | -17% | 1 | 1 | 0% | 2,874 | 1,366 | -52% | 0 | 0 | — |
case-09 | fail→pass | 20,816 | 5,246 | -75% | 1 | 1 | 0% | 3,952 | 2,029 | -49% | 0 | 0 | — |
case-10 | fail→fail | 17,444 | 15,761 | -10% | 1 | 1 | 0% | 2,937 | 1,841 | -37% | 0 | 0 | — |
case-11 | pass→pass | 9,000 | 4,657 | -48% | 1 | 1 | 0% | 1,203 | 1,498 | +25% | 0 | 0 | — |
case-13 | pass→pass | 5,893 | 2,368 | -60% | 1 | 1 | 0% | 1,038 | 1,442 | +39% | 0 | 0 | — |
case-14 | pass→pass | 13,540 | 4,487 | -67% | 1 | 1 | 0% | 1,731 | 1,579 | -9% | 0 | 0 | — |
case-15 | fail→pass | 11,179 | 2,538 | -77% | 1 | 1 | 0% | 1,821 | 1,450 | -20% | 0 | 0 | — |
case-16 | fail→fail | 13,525 | 12,710 | -6% | 1 | 1 | 0% | 2,535 | 1,513 | -40% | 0 | 0 | — |
case-17 | fail→pass | 10,328 | 2,316 | -78% | 1 | 1 | 0% | 1,982 | 1,351 | -32% | 0 | 0 | — |
case-18 | fail→pass | 15,654 | 3,635 | -77% | 1 | 1 | 0% | 2,322 | 1,649 | -29% | 0 | 0 | — |
case-19 | fail→pass | 20,147 | 2,716 | -87% | 1 | 1 | 0% | 1,760 | 1,478 | -16% | 0 | 0 | — |
case-20 | pass→pass | 14,456 | 6,818 | -53% | 1 | 1 | 0% | 2,156 | 2,303 | +7% | 0 | 0 | — |
case-21 | fail→fail | 16,075 | 16,005 | -0% | 1 | 1 | 0% | 2,238 | 3,936 | +76% | 0 | 0 | — |
case-22 | fail→fail | 14,533 | 16,625 | +14% | 1 | 1 | 0% | 2,601 | 3,828 | +47% | 0 | 0 | — |
case-23 | fail→fail | 22,130 | 25,721 | +16% | 1 | 1 | 0% | 4,719 | 6,229 | +32% | 0 | 0 | — |
case-24 | pass→pass | 11,225 | 8,262 | -26% | 1 | 1 | 0% | 1,710 | 2,292 | +34% | 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, and 19 counted toward the lift figure. The other 5 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 +38 percentage points is the difference between those two pass rates over the 19 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
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.