Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →A股管理层质量评估/公司治理分析。当用户说"管理层"、"管理层怎么样"、"公司治理"、"management"、"CEO"、"董事长"、"高管"、"治理结构"、"XX的管理层靠谱吗"、"实控人"、"管理层激励"时触发。评估上市公司管理层能力（战略/执行/资本配置）、治理结构（股权制衡/独董/激励机制）、诚信记录，辅助判断管理层是否值得信赖。支持研报风格（formal）和快速评估风格（brief）。
.claude/skills/aifinlab-a-share-management-quality/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-19 | ✓→✗ | ▼ Worse | -31% | 0% |
| case-20 | ✓→✗ | ▼ Worse | -67% | 0% |
| case-05 | ✓→✗ | ▼ Worse | -24% | 0% |
| case-06 | ✓→✗ | ▼ Worse | -29% | 0% |
bashSCRIPTS="$SKILLS_ROOT/cn-stock-data/scripts" # 财务数据（业绩趋势反映执行力） python "$SCRIPTS/cn_stock_data.py" finance --code [CODE] # 十大股东（股权结构/集中度） python -c "import efinance as ef; df=ef.stock.get_top10_stock_holder_info(stock_code='[CODE]'); print(df.to_json(orient='records', force_ascii=False))" # 个股行情 python "$SCRIPTS/cn_stock_data.py" quote --code [CODE] # K线（任期内股价表现） python "$SCRIPTS/cn_stock_data.py" kline --code [CODE] --freq daily --start [日期]
补充：通过 web 搜索获取管理层简历、过往业绩、诚信记录、薪酬数据、年报致辞、投资者关系互动、处罚记录等。
通过 web 搜索获取核心高管信息：
通过 cn-stock-data finance 获取财务数据，分析管理层任期内：
> 好的管理层 = 说到做到，业绩趋势稳步向上。
通过 efinance 十大股东数据 + web 搜索：
> 详见 references/management-quality-guide.md 中的治理红旗和A股特色问题。
> 管理层大量增持 = 利益绑定信号；频繁减持 = 需警惕。
| 维度 | formal | brief | |------|--------|-------| | 输出格式 | 完整治理分析报告（4-6页） | 快速评估要点 | | 管理层画像 | 核心高管逐人分析 | 仅列关键人物和亮点/风险点 | | 业绩追踪 | 多年财务趋势图表+承诺兑现度 | 仅ROE/营收趋势方向 | | 治理结构 | 股权结构图+独董/委员会详情 | 仅标注治理红旗/绿旗 | | 利益一致性 | 持股/激励/薪酬详细数据 | 仅增减持方向和激励有无 | | 综合评分 | 五维雷达图（能力/诚信/激励/治理/稳定性） | 一句话结论+评级 | | 结论 | 客观陈述各维度评估 | 可加简要判断（"管理层可信"/"需关注XX风险"） |
默认风格：brief。用户要求"详细分析"/"出报告"时用 formal。
综合评级参考：
python# 调用 skill result = run_skill({ "param1": "value1", "param2": "value2" })
bashpython scripts/run_skill.py --input data.json
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-09 | pass→pass | 19,656 | 24,447 | +24% | 1 | 1 | 0% | 2,727 | 4,477 | +64% | 0 | 0 | — |
case-10 | pass→pass | 18,836 | 20,563 | +9% | 1 | 1 | 0% | 2,548 | 3,947 | +55% | 0 | 0 | — |
case-11 | pass→pass | 17,505 | 9,332 | -47% | 1 | 1 | 0% | 2,533 | 2,806 | +11% | 0 | 0 | — |
case-12 | pass→pass | 14,465 | 13,934 | -4% | 1 | 1 | 0% | 2,211 | 3,553 | +61% | 0 | 0 | — |
case-13 | pass→pass | 22,876 | 18,684 | -18% | 1 | 1 | 0% | 2,788 | 3,909 | +40% | 0 | 0 | — |
case-14 | pass→pass | 23,330 | 21,280 | -9% | 1 | 1 | 0% | 3,271 | 4,082 | +25% | 0 | 0 | — |
case-15 | pass→pass | 18,355 | 19,513 | +6% | 1 | 1 | 0% | 2,629 | 4,193 | +59% | 0 | 0 | — |
case-16 | fail→fail | 25,516 | 11,388 | -55% | 1 | 1 | 0% | 3,938 | 2,176 | -45% | 0 | 0 | — |
case-17 | pass→pass | 20,575 | 18,006 | -12% | 1 | 1 | 0% | 2,829 | 3,648 | +29% | 0 | 0 | — |
case-18 | fail→fail | 35,078 | 9,982 | -72% | 1 | 1 | 0% | 4,498 | 1,916 | -57% | 0 | 0 | — |
case-19 | pass→fail | 17,349 | 7,892 | -55% | 1 | 1 | 0% | 2,820 | 1,959 | -31% | 0 | 0 | — |
case-20 | pass→fail | 28,831 | 40,873 | +42% | 1 | 1 | 0% | 5,792 | 1,892 | -67% | 0 | 0 | — |
case-21 | pass→pass | 24,840 | 28,819 | +16% | 1 | 1 | 0% | 3,775 | 5,735 | +52% | 0 | 0 | — |
case-01 | fail→fail | 16,746 | 32,929 | +97% | 1 | 1 | 0% | 2,192 | 1,813 | -17% | 0 | 0 | — |
case-02 | fail→fail | 31,112 | 13,759 | -56% | 1 | 1 | 0% | 4,751 | 2,226 | -53% | 0 | 0 | — |
case-03 | fail→fail | 27,105 | 10,788 | -60% | 1 | 1 | 0% | 3,126 | 2,051 | -34% | 0 | 0 | — |
case-04 | fail→pass | 17,997 | 16,776 | -7% | 1 | 1 | 0% | 2,621 | 2,839 | +8% | 0 | 0 | — |
case-05 | pass→fail | 17,215 | 11,010 | -36% | 1 | 1 | 0% | 2,653 | 2,020 | -24% | 0 | 0 | — |
case-06 | pass→fail | 20,835 | 10,103 | -52% | 1 | 1 | 0% | 2,531 | 1,789 | -29% | 0 | 0 | — |
case-07 | pass→fail | 34,976 | 16,161 | -54% | 1 | 1 | 0% | 4,752 | 1,957 | -59% | 0 | 0 | — |
case-08 | fail→fail | 21,605 | 8,839 | -59% | 1 | 1 | 0% | 2,920 | 1,739 | -40% | 0 | 0 | — |
case-22 | pass→pass | 21,658 | 20,033 | -8% | 1 | 1 | 0% | 2,921 | 3,462 | +19% | 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 11 counted toward the lift figure. The other 11 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 -18 percentage points is the difference between those two pass rates over the 11 comparable cases. 9 cases got worse with the skill loaded, and they are 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.