Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →FOF基金Skill - 提供FOF净值、业绩排行、持仓穿透、养老目标基金 via AkShare
.claude/skills/aifinlab-akshare-fof/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -48% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -54% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 5% | 0% |
| 属性 | 内容 | |:---|:---| | 名称 | akshare-fof | | 版本 | 1.1.0 | | 分类 | FOF基金 | | 状态 | ✅ 已上线 | | 维护者 | FinClaw Core Team | | 最后更新 | 2026-03-19 |
FOF（基金中的基金）Skill，提供FOF基金净值查询、业绩排行、持仓穿透分析、养老目标基金专题等功能。
| 用户输入 | 识别意图 | 调用函数 | |:---|:---|:---| | FOF基金列表 | fof_list | fof_list.py | | FOF净值 | fof_nav | fof_nav.py --code 006308 | | FOF业绩排行 | fof_rank | fof_rank.py --period 1y | | 养老目标基金 | fof_pension | fof_pension.py |
| 数据类型 | 主要来源 | 备用来源 | 认证要求 | |:---|:---|:---|:---:| | FOF数据 | AkShare | - | 无需 |
| 特点 | 说明 | |:---|:---| | 双重收费 | FOF管理费+底层基金费用 | | 分散投资 | 投资多只基金，二次分散 | | 专业选基 | 基金经理专业筛选基金 | | 适合人群 | 没有时间研究基金的投资者 |
bash python scripts/fof_list.py
bash python scripts/fof_nav.py --code 006308
bash python scripts/fof_rank.py --period 1y
bash python scripts/fof_pension.py
| 脚本名 | 功能 | 入口点 | |:---|:---|:---:| | fof_list.py | FOF列表 | ✅ | | fof_nav.py | FOF净值 | ✅ | | fof_rank.py | FOF排行 | ✅ | | fof_pension.py | 养老FOF | ✅ |
markdown--- 📊 **数据来源**: AkShare ⏱️ **数据时间**: 2026-03-19 📌 **基金类型**: FOF 🔗 **原始来源**: 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-01 | fail→fail | 23,376 | 17,995 | -23% | 1 | 1 | 0% | 2,946 | 3,634 | +23% | 0 | 0 | — |
case-02 | fail→fail | 11,701 | 7,980 | -32% | 1 | 1 | 0% | 1,792 | 2,241 | +25% | 0 | 0 | — |
case-03 | fail→fail | 18,325 | 27,122 | +48% | 1 | 1 | 0% | 3,213 | 5,916 | +84% | 0 | 0 | — |
case-04 | fail→pass | 19,522 | 4,757 | -76% | 1 | 1 | 0% | 3,145 | 1,650 | -48% | 0 | 0 | — |
case-05 | fail→fail | 7,261 | 3,106 | -57% | 1 | 1 | 0% | 1,162 | 1,438 | +24% | 0 | 0 | — |
case-06 | pass→pass | 16,596 | 15,183 | -9% | 1 | 1 | 0% | 2,239 | 3,402 | +52% | 0 | 0 | — |
case-07 | fail→pass | 12,324 | 2,788 | -77% | 1 | 1 | 0% | 1,822 | 1,526 | -16% | 0 | 0 | — |
case-08 | fail→pass | 11,187 | 3,371 | -70% | 1 | 1 | 0% | 1,580 | 1,676 | +6% | 0 | 0 | — |
case-09 | fail→pass | 21,961 | 3,334 | -85% | 1 | 1 | 0% | 3,194 | 1,460 | -54% | 0 | 0 | — |
case-10 | fail→pass | 14,844 | 9,735 | -34% | 1 | 1 | 0% | 2,396 | 2,519 | +5% | 0 | 0 | — |
case-11 | fail→pass | 16,570 | 3,718 | -78% | 1 | 1 | 0% | 2,469 | 1,698 | -31% | 0 | 0 | — |
case-12 | fail→pass | 17,537 | 6,558 | -63% | 1 | 1 | 0% | 2,549 | 2,104 | -17% | 0 | 0 | — |
case-13 | fail→pass | 14,676 | 5,498 | -63% | 1 | 1 | 0% | 2,377 | 1,601 | -33% | 0 | 0 | — |
case-14 | pass→pass | 10,401 | 2,109 | -80% | 1 | 1 | 0% | 1,453 | 1,372 | -6% | 0 | 0 | — |
case-15 | fail→pass | 10,550 | 3,517 | -67% | 1 | 1 | 0% | 1,385 | 1,519 | +10% | 0 | 0 | — |
case-16 | pass→pass | 19,653 | 20,190 | +3% | 1 | 1 | 0% | 2,463 | 3,663 | +49% | 0 | 0 | — |
case-17 | pass→pass | 20,582 | 15,140 | -26% | 1 | 1 | 0% | 2,516 | 3,275 | +30% | 0 | 0 | — |
case-18 | pass→pass | 22,631 | 12,591 | -44% | 1 | 1 | 0% | 3,181 | 2,580 | -19% | 0 | 0 | — |
case-19 | fail→pass | 20,833 | 10,427 | -50% | 1 | 1 | 0% | 3,106 | 2,645 | -15% | 0 | 0 | — |
case-20 | pass→pass | 12,513 | 7,275 | -42% | 1 | 1 | 0% | 1,514 | 2,202 | +45% | 0 | 0 | — |
case-21 | pass→pass | 13,177 | 3,903 | -70% | 1 | 1 | 0% | 2,138 | 1,666 | -22% | 0 | 0 | — |
case-22 | pass→pass | 7,063 | 2,951 | -58% | 1 | 1 | 0% | 1,164 | 1,446 | +24% | 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. 22 cases were attempted. The headline lift of +45 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.