Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →REITs数据Skill - 提供公募REITs行情、收益分析、资产类型筛选 via AkShare
.claude/skills/aifinlab-akshare-reits/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 77% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 141% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 71% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 72% | 0% |
| 属性 | 内容 | |:---|:---| | 名称 | akshare-reits | | 版本 | 1.1.0 | | 分类 | REITs数据 | | 状态 | ✅ 已上线 | | 维护者 | FinClaw Core Team | | 最后更新 | 2026-03-19 |
REITs（房地产投资信托基金）数据Skill，提供A股公募REITs基金列表、行情查询、收益分析、按资产类型筛选、分红统计等功能。
| 用户输入 | 识别意图 | 调用函数 | |:---|:---|:---| | REITs列表 | reits_list | reits_list.py | | REITs行情 | reits_quote | reits_quote.py | | 产业园REITs | reits_type | reits_type.py --type 产业园 | | REITs分红 | reits_dividend | reits_dividend.py |
| 数据类型 | 主要来源 | 备用来源 | 认证要求 | |:---|:---|:---|:---:| | REITs数据 | AkShare | - | 无需 |
| 类型 | 代表产品 | 收益特征 | |:---|:---|:---| | 产业园 | 东吴苏园REIT、博时蛇口REIT | 租金收益+增值 | | 仓储物流 | 中金普洛斯REIT、红土盐田港REIT | 稳定租金 | | 高速公路 | 平安广州广河REIT、浙商沪杭甬REIT | 过路费收入 | | 生态环保 | 中航首钢绿能REIT、富国首创水务REIT | 特许经营权 | | 保障房 | 华夏北京保障房REIT、中金厦门安居REIT | 租金收入 | | 能源 | 鹏华深圳能源REIT、中信建投国家电投REIT | 发电收入 |
bash python scripts/reits_list.py
bash python scripts/reits_quote.py python scripts/reits_quote.py --code 180101
bash python scripts/reits_type.py --type 产业园 python scripts/reits_type.py --type 高速公路
bash python scripts/reits_dividend.py
| 脚本名 | 功能 | 入口点 | |:---|:---|:---:| | reits_list.py | REITs列表 | ✅ | | reits_quote.py | REITs行情 | ✅ | | reits_type.py | 类型筛选 | ✅ | | reits_dividend.py | 分红统计 | ✅ |
| 特点 | 说明 | |:---|:---| | 强制分红 | 收益分配比例≥90% | | 稳定现金流 | 底层资产产生稳定收益 | | 低相关性 | 与股票/债券相关性低 | | 流动性 | 交易所上市交易 | | 透明度 | 定期披露运营数据 |
| 来源 | 占比 | 特点 | |:---|:---:|:---| | 分红收益 | 70-80% | 稳定现金流入 | | 资本增值 | 20-30% | 底层资产升值 |
markdown--- 📊 **数据来源**: AkShare ⏱️ **数据时间**: 2026-03-19 📌 **REITs代码**: 180101 📌 **资产类型**: 产业园 🔗 **交易所**: 深圳证券交易所 🔧 **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6大资产类型 | | 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-11 | fail→fail | 20,140 | 13,510 | -33% | 1 | 1 | 0% | 3,372 | 2,238 | -34% | 0 | 0 | — |
case-12 | fail→fail | 30,531 | 9,235 | -70% | 1 | 1 | 0% | 5,061 | 1,887 | -63% | 0 | 0 | — |
case-04 | fail→pass | 18,338 | 22,503 | +23% | 1 | 1 | 0% | 2,586 | 4,576 | +77% | 0 | 0 | — |
case-10 | fail→pass | 17,810 | 30,901 | +74% | 1 | 1 | 0% | 3,148 | 7,599 | +141% | 0 | 0 | — |
case-01 | fail→pass | 20,821 | 13,499 | -35% | 1 | 1 | 0% | 3,745 | 3,722 | -1% | 0 | 0 | — |
case-02 | fail→pass | 10,561 | 11,232 | +6% | 1 | 1 | 0% | 1,811 | 3,096 | +71% | 0 | 0 | — |
case-03 | fail→pass | 21,543 | 30,339 | +41% | 1 | 1 | 0% | 3,456 | 5,957 | +72% | 0 | 0 | — |
case-05 | fail→fail | 15,337 | 14,652 | -4% | 1 | 1 | 0% | 2,764 | 3,671 | +33% | 0 | 0 | — |
case-06 | fail→fail | 11,798 | 11,745 | -0% | 1 | 1 | 0% | 1,835 | 3,419 | +86% | 0 | 0 | — |
case-07 | fail→fail | 19,716 | 12,060 | -39% | 1 | 1 | 0% | 3,465 | 2,086 | -40% | 0 | 0 | — |
case-08 | fail→pass | 21,004 | 33,778 | +61% | 1 | 1 | 0% | 3,447 | 4,365 | +27% | 0 | 0 | — |
case-09 | fail→pass | 29,735 | 24,991 | -16% | 1 | 1 | 0% | 3,978 | 5,994 | +51% | 0 | 0 | — |
case-13 | pass→pass | 8,049 | 5,701 | -29% | 1 | 1 | 0% | 1,437 | 2,337 | +63% | 0 | 0 | — |
case-14 | fail→pass | 15,914 | 7,551 | -53% | 1 | 1 | 0% | 2,556 | 2,425 | -5% | 0 | 0 | — |
case-15 | fail→fail | 12,303 | 8,685 | -29% | 1 | 1 | 0% | 1,882 | 1,928 | +2% | 0 | 0 | — |
case-16 | fail→pass | 17,770 | 13,832 | -22% | 1 | 1 | 0% | 2,975 | 3,936 | +32% | 0 | 0 | — |
case-17 | pass→pass | 21,728 | 17,049 | -22% | 1 | 1 | 0% | 2,808 | 3,653 | +30% | 0 | 0 | — |
case-18 | pass→pass | 24,009 | 14,917 | -38% | 1 | 1 | 0% | 2,849 | 3,721 | +31% | 0 | 0 | — |
case-19 | pass→pass | 20,881 | 19,659 | -6% | 1 | 1 | 0% | 2,577 | 3,800 | +47% | 0 | 0 | — |
case-20 | fail→pass | 21,111 | 23,684 | +12% | 1 | 1 | 0% | 3,808 | 4,699 | +23% | 0 | 0 | — |
case-21 | pass→pass | 18,244 | 9,640 | -47% | 1 | 1 | 0% | 2,951 | 2,914 | -1% | 0 | 0 | — |
case-22 | pass→pass | 20,736 | 18,952 | -9% | 1 | 1 | 0% | 3,114 | 3,949 | +27% | 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, and 18 counted toward the lift figure. The other 4 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 +45 percentage points is the difference between those two pass rates over the 18 comparable cases. 1 case got worse with the skill loaded, and it is 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.