Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →股权质押Skill - 提供质押比例查询、风险预警、解禁股提醒 via AkShare
.claude/skills/aifinlab-akshare-pledge/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-15 | ✗→✓ | ▲ Improved | -13% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -34% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -11% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -18% | 0% |
| 属性 | 内容 | |:---|:---| | 名称 | akshare-pledge | | 版本 | 1.1.0 | | 分类 | 股权质押 | | 状态 | ✅ 已上线 | | 维护者 | FinClaw Core Team | | 最后更新 | 2026-03-19 |
股权质押Skill，提供A股上市公司股权质押比例查询、高质押风险预警、质押到期提醒、解禁股查询等功能。识别因股权质押可能引发的平仓风险。
| 用户输入 | 识别意图 | 调用函数 | |:---|:---|:---| | 茅台股权质押情况 | pledge_stock | pledge_stock.py --code 600519 | | 高质押风险股票 | pledge_high | pledge_high.py --limit 50 | | 最近解禁股 | pledge_unlock | pledge_unlock.py --days 30 | | 质押比例多少？ | pledge_stock | pledge_stock.py --code 000001 |
| 数据类型 | 主要来源 | 备用来源 | 认证要求 | |:---|:---|:---|:---:| | 股权质押 | AkShare-交易所 | - | 无需 | | 解禁股 | AkShare | - | 无需 |
| 质押比例 | 风险等级 | 说明 | |:---:|:---:|:---| | <30% | 🟢 低风险 | 正常范围 | | 30%-50% | 🟡 中风险 | 需关注 | | 50%-70% | 🟠 高风险 | 警戒区，平仓风险上升 | | >70% | 🔴 极高风险 | 极度危险，随时可能爆仓 |
bash python scripts/pledge_stock.py --code 600519
bash python scripts/pledge_high.py --limit 50
bash python scripts/pledge_unlock.py --days 30
| 脚本名 | 功能 | 入口点 | |:---|:---|:---:| | pledge_stock.py | 个股质押查询 | ✅ | | pledge_high.py | 高质押风险 | ✅ | | pledge_unlock.py | 解禁股查询 | ✅ |
股东将持有的股票作为质押物，向金融机构借款。如果股价下跌，可能触发补仓或强制平仓。
股价下跌 → 质押股票市值下降 → 触及预警线/平仓线
↓
股东需补仓或面临强制平仓
↓
大量抛售 → 股价进一步下跌| 质押比例 | 预警线 | 平仓线 | |:---:|:---:|:---:| | 一般情况 | 150% | 130% | | 高比例质押 | 160% | 140% |
注：质押率 = 借款金额/质押股票市值
| 解禁类型 | 影响 | |:---|:---| | 大股东解禁 | 可能减持，压力较大 | | 机构配售解禁 | 视市场情况而定 | | 员工持股解禁 | 一般影响较小 |
markdown--- 📊 **数据来源**: AkShare-交易所 ⏱️ **数据时间**: 2026-03-19 📌 **质押比例**: 45.2% 📌 **风险等级**: 🟠 高风险 🔗 **原始来源**: 上市公司公告 🔧 **分析工具**: FinClaw v1.0 ⚠️ **风险提示**: 股权质押风险高，需持续关注
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，新增风险等级划分 | | 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-15 | fail→pass | 14,603 | 2,630 | -82% | 1 | 1 | 0% | 2,090 | 1,822 | -13% | 0 | 0 | — |
case-16 | fail→pass | 18,054 | 3,366 | -81% | 1 | 1 | 0% | 2,920 | 1,915 | -34% | 0 | 0 | — |
case-01 | fail→fail | 20,677 | 10,103 | -51% | 1 | 1 | 0% | 2,524 | 2,868 | +14% | 0 | 0 | — |
case-02 | fail→fail | 25,595 | 21,329 | -17% | 1 | 1 | 0% | 4,128 | 5,060 | +23% | 0 | 0 | — |
case-03 | fail→fail | 12,796 | 9,333 | -27% | 1 | 1 | 0% | 1,951 | 1,654 | -15% | 0 | 0 | — |
case-04 | pass→pass | 26,901 | 19,628 | -27% | 1 | 1 | 0% | 3,817 | 4,135 | +8% | 0 | 0 | — |
case-05 | pass→pass | 24,230 | 19,009 | -22% | 1 | 1 | 0% | 3,307 | 4,254 | +29% | 0 | 0 | — |
case-06 | pass→pass | 13,301 | 15,226 | +14% | 1 | 1 | 0% | 2,492 | 4,239 | +70% | 0 | 0 | — |
case-07 | pass→pass | 12,921 | 5,166 | -60% | 1 | 1 | 0% | 1,922 | 2,239 | +16% | 0 | 0 | — |
case-08 | fail→pass | 15,931 | 4,562 | -71% | 1 | 1 | 0% | 2,152 | 2,174 | +1% | 0 | 0 | — |
case-09 | pass→pass | 14,473 | 8,100 | -44% | 1 | 1 | 0% | 2,184 | 2,417 | +11% | 0 | 0 | — |
case-10 | pass→pass | 13,713 | 8,310 | -39% | 1 | 1 | 0% | 2,390 | 2,855 | +19% | 0 | 0 | — |
case-11 | pass→pass | 11,925 | 4,191 | -65% | 1 | 1 | 0% | 2,126 | 2,106 | -1% | 0 | 0 | — |
case-12 | pass→pass | 19,003 | 17,066 | -10% | 1 | 1 | 0% | 2,531 | 3,993 | +58% | 0 | 0 | — |
case-13 | fail→pass | 11,161 | 2,135 | -81% | 1 | 1 | 0% | 2,003 | 1,774 | -11% | 0 | 0 | — |
case-14 | fail→pass | 12,057 | 5,499 | -54% | 1 | 1 | 0% | 2,222 | 1,819 | -18% | 0 | 0 | — |
case-17 | fail→pass | 19,753 | 3,889 | -80% | 1 | 1 | 0% | 2,756 | 2,065 | -25% | 0 | 0 | — |
case-18 | pass→pass | 24,739 | 14,546 | -41% | 1 | 1 | 0% | 2,238 | 3,452 | +54% | 0 | 0 | — |
case-19 | pass→pass | 16,662 | 15,926 | -4% | 1 | 1 | 0% | 2,328 | 3,452 | +48% | 0 | 0 | — |
case-20 | pass→pass | 15,315 | 20,430 | +33% | 1 | 1 | 0% | 2,630 | 4,147 | +58% | 0 | 0 | — |
case-21 | fail→pass | 9,734 | 2,609 | -73% | 1 | 1 | 0% | 1,745 | 1,812 | +4% | 0 | 0 | — |
case-22 | fail→pass | 14,660 | 3,459 | -76% | 1 | 1 | 0% | 2,408 | 2,038 | -15% | 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 21 counted toward the lift figure. The other 1 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 +36 percentage points is the difference between those two pass rates over the 21 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.