Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →概念板块Skill - 提供概念板块行情、龙头股、资金流向 via AkShare
.claude/skills/aifinlab-akshare-concept/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-21 | ✗→✓ | ▲ Improved | -30% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 45% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 56% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | 45% | 0% |
| case-14 | ✓→✓ | ＝ Same ✓ | 38% | 0% |
| 属性 | 内容 | |:---|:---| | 名称 | akshare-concept | | 版本 | 1.1.0 | | 分类 | 概念板块 | | 状态 | ✅ 已上线 | | 维护者 | FinClaw Core Team | | 最后更新 | 2026-03-19 |
概念板块Skill，提供A股市场概念板块行情、板块资金流向、龙头股分析、热点题材追踪等功能。覆盖人工智能、芯片、新能源等热门概念。
| 用户输入 | 识别意图 | 调用函数 | |:---|:---|:---| | 概念板块列表 | concept_list | concept_list.py | | 人工智能板块 | concept_quote | concept_quote.py --name 人工智能 | | 芯片概念龙头 | concept_stocks | concept_stocks.py --name 芯片 | | 热点题材 | concept_hot | concept_list.py --hot |
| 数据类型 | 主要来源 | 备用来源 | 认证要求 | |:---|:---|:---|:---:| | 概念板块 | AkShare-同花顺 | - | 无需 | | 资金流向 | AkShare | - | 无需 |
| 概念 | 代表个股 | 驱动因素 | |:---|:---|:---| | 人工智能 | 科大讯飞、寒武纪 | ChatGPT、大模型 | | 芯片/半导体 | 中芯国际、北方华创 | 国产替代 | | 新能源 | 宁德时代、比亚迪 | 碳中和、电动化 | | 光伏 | 隆基绿能、通威股份 | 清洁能源 | | 充电桩 | 特锐德、盛弘股份 | 新基建 | | 数字经济 | 浪潮信息、中科曙光 | 政策驱动 | | 中特估 | 中国移动、中国石油 | 估值修复 | | 减肥药 | 常山药业、翰宇药业 | 海外映射 |
bash python scripts/concept_list.py python scripts/concept_list.py --hot
bash python scripts/concept_quote.py --name 人工智能 python scripts/concept_quote.py --name 芯片
bash python scripts/concept_stocks.py --name 新能源
| 脚本名 | 功能 | 入口点 | |:---|:---|:---:| | concept_list.py | 概念板块列表 | ✅ | | concept_quote.py | 板块行情 | ✅ | | concept_stocks.py | 板块个股 | ✅ |
| 风险 | 说明 | |:---|:---| | 概念炒作 | 缺乏业绩支撑，波动大 | | 热点轮动 | 热点切换快，追高风险 | | 龙头股风险 | 涨幅过大后回调风险 | | 政策依赖 | 部分概念依赖政策驱动 |
markdown--- 📊 **数据来源**: AkShare-同花顺 ⏱️ **数据时间**: 2026-03-19 📌 **概念名称**: 人工智能 🔗 **原始来源**: 同花顺概念板块 🔧 **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，新增热门概念 | | 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-10 | fail→fail | 8,389 | 18,900 | +125% | 1 | 1 | 0% | 1,350 | 3,804 | +182% | 0 | 0 | — |
case-01 | fail→fail | 16,857 | 9,517 | -44% | 1 | 1 | 0% | 2,567 | 2,821 | +10% | 0 | 0 | — |
case-02 | fail→fail | 9,917 | 12,745 | +29% | 1 | 1 | 0% | 1,606 | 3,061 | +91% | 0 | 0 | — |
case-03 | fail→fail | 20,423 | 12,640 | -38% | 1 | 1 | 0% | 2,964 | 3,556 | +20% | 0 | 0 | — |
case-04 | pass→pass | 26,419 | 29,993 | +14% | 1 | 1 | 0% | 3,610 | 5,222 | +45% | 0 | 0 | — |
case-05 | pass→pass | 22,842 | 27,033 | +18% | 1 | 1 | 0% | 3,719 | 5,809 | +56% | 0 | 0 | — |
case-06 | pass→pass | 21,545 | 20,081 | -7% | 1 | 1 | 0% | 2,815 | 4,083 | +45% | 0 | 0 | — |
case-07 | fail→fail | 21,460 | 23,786 | +11% | 1 | 1 | 0% | 3,073 | 4,954 | +61% | 0 | 0 | — |
case-08 | fail→fail | 21,280 | 16,088 | -24% | 1 | 1 | 0% | 3,540 | 3,894 | +10% | 0 | 0 | — |
case-09 | fail→fail | 17,170 | 12,971 | -24% | 1 | 1 | 0% | 2,552 | 3,296 | +29% | 0 | 0 | — |
case-11 | fail→fail | 21,397 | 17,020 | -20% | 1 | 1 | 0% | 3,255 | 3,525 | +8% | 0 | 0 | — |
case-12 | fail→fail | 13,752 | 12,551 | -9% | 1 | 1 | 0% | 2,459 | 3,011 | +22% | 0 | 0 | — |
case-13 | fail→fail | 22,167 | 11,229 | -49% | 1 | 1 | 0% | 3,244 | 3,042 | -6% | 0 | 0 | — |
case-14 | pass→pass | 16,132 | 15,306 | -5% | 1 | 1 | 0% | 2,426 | 3,336 | +38% | 0 | 0 | — |
case-15 | fail→fail | 16,625 | 11,067 | -33% | 1 | 1 | 0% | 2,885 | 3,234 | +12% | 0 | 0 | — |
case-16 | fail→fail | 22,542 | 12,870 | -43% | 1 | 1 | 0% | 2,881 | 3,489 | +21% | 0 | 0 | — |
case-17 | fail→fail | 32,709 | 21,454 | -34% | 1 | 1 | 0% | 2,560 | 3,367 | +32% | 0 | 0 | — |
case-18 | fail→fail | 17,533 | 14,664 | -16% | 1 | 1 | 0% | 2,566 | 3,329 | +30% | 0 | 0 | — |
case-19 | fail→fail | 19,829 | 15,653 | -21% | 1 | 1 | 0% | 3,116 | 3,395 | +9% | 0 | 0 | — |
case-20 | fail→fail | 10,887 | 13,847 | +27% | 1 | 1 | 0% | 1,566 | 2,217 | +42% | 0 | 0 | — |
case-21 | fail→pass | 27,414 | 2,148 | -92% | 1 | 1 | 0% | 2,286 | 1,596 | -30% | 0 | 0 | — |
case-22 | fail→fail | 17,711 | 9,437 | -47% | 1 | 1 | 0% | 3,058 | 2,765 | -10% | 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 +5 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.