Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →智能预警Skill - 提供价格预警、成交量预警、公告预警、技术指标预警 via AkShare
.claude/skills/aifinlab-akshare-alerts/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | -35% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -35% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 21% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -1% | 0% |
| 属性 | 内容 | |:---|:---| | 名称 | akshare-alerts | | 版本 | 1.1.0 | | 分类 | 智能预警 | | 状态 | ✅ 已上线 | | 维护者 | FinClaw Core Team | | 最后更新 | 2026-03-19 |
智能预警Skill，提供A股市场价格预警、成交量预警、涨跌停预警、公告预警、技术指标预警（金叉/死叉）等功能。帮助投资者及时捕捉市场异动。
| 用户输入 | 识别意图 | 调用函数 | |:---|:---|:---| | 设置价格预警 | alert_price | alert_price.py --code 000001 --above 15 | | 跌幅预警 | alert_price | alert_price.py --code 000001 --below 12 | | 涨跌停预警 | alert_limit | alert_limit.py | | 成交量异常 | alert_volume | alert_volume.py --threshold 5 |
| 数据类型 | 主要来源 | 备用来源 | 认证要求 | |:---|:---|:---|:---:| | 预警数据 | AkShare | - | 无需 |
| 类型 | 触发条件 | 用途 | |:---|:---|:---| | 价格突破 | 股价突破设定价位 | 捕捉突破机会 | | 价格跌破 | 股价跌破设定价位 | 止损提醒 | | 涨跌停 | 股票涨停或跌停 | 异动监控 | | 成交量异常 | 成交量放大N倍 | 资金异动 | | 公告预警 | 特定类型公告发布 | 事件驱动 | | 技术指标 | 金叉/死叉等信号 | 技术交易 |
bash python scripts/alert_price.py --code 000001 --above 15.0 python scripts/alert_price.py --code 000001 --below 12.0
bash python scripts/alert_limit.py
bash python scripts/alert_volume.py --threshold 5
| 脚本名 | 功能 | 入口点 | |:---|:---|:---:| | alert_price.py | 价格预警 | ✅ | | alert_limit.py | 涨跌停预警 | ✅ | | alert_volume.py | 成交量预警 | ✅ |
| 场景 | 推荐预警 | |:---|:---| | 突破买入 | 价格突破 + 成交量放大 | | 止损保护 | 价格跌破 + 技术指标死叉 | | 事件驱动 | 公告预警 + 涨跌停监控 | | 趋势跟踪 | 技术指标金叉/死叉 |
markdown--- 📊 **数据来源**: AkShare ⏱️ **预警时间**: 2026-03-19 10:30:15 📌 **预警类型**: 价格突破 🔗 **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-08 | fail→pass | 17,012 | 3,118 | -82% | 1 | 1 | 0% | 2,665 | 1,743 | -35% | 0 | 0 | — |
case-09 | fail→pass | 15,540 | 3,771 | -76% | 1 | 1 | 0% | 2,820 | 1,834 | -35% | 0 | 0 | — |
case-02 | fail→pass | 17,639 | 12,772 | -28% | 1 | 1 | 0% | 2,830 | 3,431 | +21% | 0 | 0 | — |
case-01 | fail→pass | 12,607 | 7,500 | -41% | 1 | 1 | 0% | 1,829 | 1,742 | -5% | 0 | 0 | — |
case-03 | fail→fail | 17,946 | 8,988 | -50% | 1 | 1 | 0% | 2,765 | 2,745 | -1% | 0 | 0 | — |
case-04 | fail→pass | 12,942 | 5,870 | -55% | 1 | 1 | 0% | 2,036 | 2,019 | -1% | 0 | 0 | — |
case-05 | fail→pass | 20,961 | 5,572 | -73% | 1 | 1 | 0% | 2,862 | 1,984 | -31% | 0 | 0 | — |
case-06 | fail→pass | 14,772 | 3,277 | -78% | 1 | 1 | 0% | 2,636 | 1,751 | -34% | 0 | 0 | — |
case-07 | fail→pass | 14,961 | 3,415 | -77% | 1 | 1 | 0% | 2,515 | 1,761 | -30% | 0 | 0 | — |
case-10 | fail→pass | 12,057 | 5,223 | -57% | 1 | 1 | 0% | 2,021 | 1,756 | -13% | 0 | 0 | — |
case-11 | fail→pass | 21,032 | 4,246 | -80% | 1 | 1 | 0% | 2,825 | 1,740 | -38% | 0 | 0 | — |
case-12 | pass→pass | 13,347 | 3,639 | -73% | 1 | 1 | 0% | 1,641 | 1,698 | +3% | 0 | 0 | — |
case-13 | fail→pass | 16,030 | 3,386 | -79% | 1 | 1 | 0% | 2,369 | 1,675 | -29% | 0 | 0 | — |
case-14 | pass→pass | 14,288 | 4,063 | -72% | 1 | 1 | 0% | 2,002 | 1,692 | -15% | 0 | 0 | — |
case-15 | pass→pass | 20,613 | 12,116 | -41% | 1 | 1 | 0% | 3,077 | 3,159 | +3% | 0 | 0 | — |
case-16 | fail→pass | 12,298 | 2,905 | -76% | 1 | 1 | 0% | 1,971 | 1,683 | -15% | 0 | 0 | — |
case-17 | pass→pass | 6,249 | 4,246 | -32% | 1 | 1 | 0% | 910 | 1,744 | +92% | 0 | 0 | — |
case-18 | fail→pass | 12,942 | 4,304 | -67% | 1 | 1 | 0% | 2,174 | 1,728 | -21% | 0 | 0 | — |
case-19 | fail→pass | 9,962 | 4,178 | -58% | 1 | 1 | 0% | 1,342 | 1,896 | +41% | 0 | 0 | — |
case-20 | pass→pass | 8,792 | 7,023 | -20% | 1 | 1 | 0% | 1,191 | 2,208 | +85% | 0 | 0 | — |
case-21 | pass→pass | 35,492 | 52,084 | +47% | 1 | 1 | 0% | 5,451 | 9,413 | +73% | 0 | 0 | — |
case-22 | pass→pass | 10,000 | 22,138 | +121% | 1 | 1 | 0% | 1,605 | 4,257 | +165% | 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 +64 percentage points is the difference between those two pass rates over the 22 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.