Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →债券数据Skill - 提供国债、企业债、可转债行情、收益率曲线、转股价值分析 via AkShare
.claude/skills/aifinlab-akshare-bond/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-17 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 49% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 80% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -6% | 0% |
| 属性 | 内容 | |:---|:---| | 名称 | akshare-bond | | 版本 | 1.1.0 | | 分类 | 债券数据 | | 状态 | ✅ 已上线 | | 维护者 | FinClaw Core Team | | 最后更新 | 2026-03-19 |
债券数据Skill，提供国债、企业债、可转债的行情数据、收益率曲线、可转债基本面分析（转股价值、溢价率）等。覆盖交易所债券市场和银行间市场数据。
| 用户输入 | 识别意图 | 调用函数 | |:---|:---|:---| | 国债收益率多少？ | bond_yield | bond_yield.py | | 查询可转债 | bond_convertible | bond_convertible.py | | 债券市场行情 | bond_quote | bond_quote.py | | 可转债转股价值 | bond_conversion | bond_convertible.py --detail |
| 数据类型 | 主要来源 | 备用来源 | 认证要求 | |:---|:---|:---|:---:| | 债券行情 | AkShare-交易所 | - | 无需 | | 可转债数据 | AkShare-东方财富 | - | 无需 | | 收益率曲线 | AkShare-央行 | - | 无需 |
bash python scripts/bond_quote.py python scripts/bond_quote.py --type treasury # 国债
bash python scripts/bond_convertible.py python scripts/bond_convertible.py 110059 # 特定可转债
bash python scripts/bond_yield.py python scripts/bond_yield.py --term 10y # 10年期
| 脚本名 | 功能 | 入口点 | |:---|:---|:---:| | bond_quote.py | 债券行情 | ✅ | | bond_convertible.py | 可转债数据 | ✅ | | bond_yield.py | 收益率曲线 | ✅ |
| 类型 | 代码前缀 | 特征 | |:---|:---|:---| | 国债 | 019xxx | 国家信用，无违约风险 | | 地方政府债 | 130xxx/109xxx | 地方政府发行 | | 企业债 | 120xxx/127xxx | 企业发行，信用风险 | | 公司债 | 122xxx/112xxx | 上市公司发行 | | 可转债 | 110xxx/113xxx/128xxx | 可转换股票 |
| 指标 | 说明 | 投资意义 | |:---|:---|:---| | 转股价值 | (100/转股价) × 正股价 | 转换成股票的价值 | | 转股溢价率 | (转债价-转股价值)/转股价值 | 溢价越低，股性越强 | | 纯债价值 | 按到期收益率折现的价值 | 债底保护 | | 到期收益率(YTM) | 持有到期的年化收益 | 保底收益 | | 双低值 | 转债价 + 溢价率×100 | 综合评估指标 |
| 策略 | 条件 | 特点 | |:---|:---|:---| | 双低策略 | 低价格 + 低溢价 | 攻守兼备 | | 低溢价策略 | 溢价率 < 10% | 股性强，跟随正股 | | 高收益策略 | YTM > 3% | 债性强，保底高 | | 打新策略 | 申购新债 | 低风险套利 |
| 曲线形态 | 含义 | 经济信号 | |:---|:---|:---| | 向上倾斜 | 长期利率 > 短期利率 | 正常经济，增长预期 | | 平坦 | 长短利率接近 | 经济放缓信号 | | 倒挂 | 短期利率 > 长期利率 | 衰退预警 |
本Skill所有输出数据将按以下格式标注来源：
markdown--- 📊 **数据来源**: AkShare-东方财富/交易所 ⏱️ **数据时间**: 2026-03-19 10:30:15 📌 **债券类型**: 可转债 🔗 **原始来源**: 上海证券交易所 🔧 **分析工具**: FinClaw v1.0
akshare>=1.10.0
pandas>=1.3.0
pyyaml>=5.4.0| 市场 | 时间 | |:---|:---| | 交易所债券 | 09:30-11:30, 13:00-15:00 | | 银行间市场 | 09:00-12:00, 13:30-16:30 |
| 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 |
finclaw/config/data_source_config.yaml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-08 | pass→pass | 20,385 | 4,582 | -78% | 1 | 1 | 0% | 2,719 | 2,391 | -12% | 0 | 0 | — |
case-09 | pass→pass | 13,306 | 7,554 | -43% | 1 | 1 | 0% | 2,393 | 2,668 | +11% | 0 | 0 | — |
case-10 | pass→pass | 7,287 | 5,565 | -24% | 1 | 1 | 0% | 1,324 | 2,657 | +101% | 0 | 0 | — |
case-16 | pass→pass | 16,445 | 3,039 | -82% | 1 | 1 | 0% | 2,258 | 2,076 | -8% | 0 | 0 | — |
case-17 | fail→pass | 18,781 | 5,667 | -70% | 1 | 1 | 0% | 2,955 | 2,596 | -12% | 0 | 0 | — |
case-01 | fail→pass | 18,770 | 13,104 | -30% | 1 | 1 | 0% | 2,953 | 3,316 | +12% | 0 | 0 | — |
case-02 | fail→pass | 16,865 | 14,218 | -16% | 1 | 1 | 0% | 2,551 | 3,806 | +49% | 0 | 0 | — |
case-03 | fail→pass | 11,728 | 34,799 | +197% | 1 | 1 | 0% | 1,742 | 3,144 | +80% | 0 | 0 | — |
case-04 | pass→pass | 6,254 | 7,794 | +25% | 1 | 1 | 0% | 1,148 | 2,559 | +123% | 0 | 0 | — |
case-05 | pass→pass | 5,106 | 6,426 | +26% | 1 | 1 | 0% | 809 | 2,825 | +249% | 0 | 0 | — |
case-06 | pass→pass | 7,633 | 8,345 | +9% | 1 | 1 | 0% | 1,030 | 3,154 | +206% | 0 | 0 | — |
case-07 | pass→pass | 11,833 | 5,131 | -57% | 1 | 1 | 0% | 1,805 | 2,479 | +37% | 0 | 0 | — |
case-11 | pass→pass | 15,558 | 14,104 | -9% | 1 | 1 | 0% | 2,276 | 3,555 | +56% | 0 | 0 | — |
case-12 | pass→pass | 14,372 | 14,250 | -1% | 1 | 1 | 0% | 2,175 | 3,810 | +75% | 0 | 0 | — |
case-13 | pass→pass | 13,320 | 5,681 | -57% | 1 | 1 | 0% | 1,873 | 2,539 | +36% | 0 | 0 | — |
case-14 | fail→pass | 16,841 | 3,229 | -81% | 1 | 1 | 0% | 2,401 | 2,258 | -6% | 0 | 0 | — |
case-15 | pass→pass | 12,215 | 3,462 | -72% | 1 | 1 | 0% | 1,948 | 2,148 | +10% | 0 | 0 | — |
case-18 | fail→pass | 18,809 | 4,592 | -76% | 1 | 1 | 0% | 2,533 | 2,338 | -8% | 0 | 0 | — |
case-19 | fail→fail | 21,075 | 23,330 | +11% | 1 | 1 | 0% | 3,857 | 6,100 | +58% | 0 | 0 | — |
case-20 | fail→fail | 9,380 | 14,198 | +51% | 1 | 1 | 0% | 1,697 | 4,480 | +164% | 0 | 0 | — |
case-21 | fail→fail | 19,410 | 22,562 | +16% | 1 | 1 | 0% | 2,871 | 5,747 | +100% | 0 | 0 | — |
case-22 | fail→fail | 28,035 | 25,871 | -8% | 1 | 1 | 0% | 4,364 | 6,886 | +58% | 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 +27 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.