Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →A股行业研究/板块分析。当用户说"行业研究"、"板块分析"、"行业全景"、"sector overview"、"XX行业怎么样"、"XX板块前景"、"行业对比"、"产业链分析"时触发。通过 cn-stock-data 获取行业内主要公司数据，结合 web 搜索获取行业政策、市场规模、竞争格局等信息，生成结构化行业研究报告。支持券商行业报告风格（formal）和个人行业笔记风格（brief）。不适用于个股深度分析（用 a-share-earnings-analysis）或个股估值对标（用 a-share-comps）。
.claude/skills/aifinlab-a-share-sector/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 63% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 67% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-10 | ✓→✗ | ▼ Worse | -20% | 0% |
bashSCRIPTS="$SKILLS_ROOT/cn-stock-data/scripts" # 行业内主要公司行情（市值、PE、PB 等） python "$SCRIPTS/cn_stock_data.py" quote --code [CODE1],[CODE2],... # 各公司财务指标 python "$SCRIPTS/cn_stock_data.py" finance --code [CODE] # 各公司近 1 年日线（行业趋势对比） python "$SCRIPTS/cn_stock_data.py" kline --code [CODE] --freq daily --start [1年前日期] # 北向资金（行业层面资金偏好） python "$SCRIPTS/cn_stock_data.py" north_flow
补充：通过 web 搜索获取行业政策、市场规模、产业链结构、行业新闻。
通过 web 搜索获取：
通过 cn-stock-data 获取各公司数据，构建竞争格局表：
| 公司 | 市值(亿) | 收入(亿) | 市占率(%) | 毛利率(%) | ROE(%) | 核心优势 | |------|---------|---------|----------|----------|--------|---------| | ... | ... | ... | ... | ... | ... | ... |
分析要点：
从 cn-stock-data 获取并对比行业内公司的关键财务指标：
核心对比表：
| 公司 | 营收增速(%) | 净利润增速(%) | 毛利率(%) | 净利率(%) | ROE(%) | 资产负债率(%) | PE(TTM) | PB | |------|-----------|-------------|----------|----------|--------|-------------|---------|-----| | ... | ... | ... | ... | ... | ... | ... | ... | ... | | 行业中位数 | ... | ... | ... | ... | ... | ... | ... | ... |
标注行业中位数，识别优于/弱于中位数的公司。
根据风格要求输出（默认 formal）。参考 references/sector-template.md 中的模板。
| 维度 | formal（券商行业报告） | brief（个人行业笔记） | |------|-------------------|-------------------| | 篇幅 | 5-10 页 | 1-2 页 | | 行业全景 | 完整（市场规模+产业链+政策+驱动力） | 精简（1-2 段核心逻辑） | | 竞争格局表 | 完整（10+ 公司，含市占率） | 精简（Top 5 龙头） | | 财务对比 | 10+ 列指标 | 5-6 列核心指标 | | 估值 | 详细（含历史分位） | 当前水平 + 一句判断 | | 投资建议 | 客观描述机会与风险 | 可加个人观点 | | 免责声明 | 需要 | 不需要 |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 38,142 | 61,046 | +60% | 1 | 1 | 0% | 6,048 | 2,169 | -64% | 0 | 0 | — |
case-02 | fail→fail | 29,174 | 13,128 | -55% | 1 | 1 | 0% | 3,512 | 1,984 | -44% | 0 | 0 | — |
case-03 | fail→fail | 36,906 | 15,836 | -57% | 1 | 1 | 0% | 6,122 | 2,189 | -64% | 0 | 0 | — |
case-04 | fail→pass | 18,870 | 11,198 | -41% | 1 | 1 | 0% | 2,894 | 3,062 | +6% | 0 | 0 | — |
case-05 | fail→pass | 17,923 | 25,544 | +43% | 1 | 1 | 0% | 3,114 | 5,091 | +63% | 0 | 0 | — |
case-06 | pass→pass | 17,021 | 20,806 | +22% | 1 | 1 | 0% | 2,506 | 3,749 | +50% | 0 | 0 | — |
case-18 | pass→pass | 19,476 | 14,973 | -23% | 1 | 1 | 0% | 2,535 | 3,121 | +23% | 0 | 0 | — |
case-07 | pass→pass | 15,055 | 11,927 | -21% | 1 | 1 | 0% | 2,309 | 2,734 | +18% | 0 | 0 | — |
case-08 | pass→pass | 11,811 | 7,629 | -35% | 1 | 1 | 0% | 1,671 | 2,326 | +39% | 0 | 0 | — |
case-09 | fail→pass | 14,934 | 15,294 | +2% | 1 | 1 | 0% | 2,126 | 3,550 | +67% | 0 | 0 | — |
case-10 | pass→fail | 20,913 | 16,722 | -20% | 1 | 1 | 0% | 2,625 | 2,109 | -20% | 0 | 0 | — |
case-11 | pass→pass | 13,832 | 17,200 | +24% | 1 | 1 | 0% | 2,258 | 3,230 | +43% | 0 | 0 | — |
case-12 | pass→pass | 19,721 | 17,067 | -13% | 1 | 1 | 0% | 3,173 | 3,871 | +22% | 0 | 0 | — |
case-13 | fail→fail | 17,087 | 11,835 | -31% | 1 | 1 | 0% | 2,179 | 2,813 | +29% | 0 | 0 | — |
case-14 | fail→fail | 17,923 | 18,412 | +3% | 1 | 1 | 0% | 2,243 | 3,659 | +63% | 0 | 0 | — |
case-15 | fail→fail | 15,249 | 14,248 | -7% | 1 | 1 | 0% | 2,547 | 3,469 | +36% | 0 | 0 | — |
case-16 | fail→pass | 16,649 | 9,599 | -42% | 1 | 1 | 0% | 2,060 | 2,517 | +22% | 0 | 0 | — |
case-17 | pass→pass | 18,932 | 21,867 | +16% | 1 | 1 | 0% | 2,697 | 4,223 | +57% | 0 | 0 | — |
case-19 | pass→fail | 47,250 | 8,482 | -82% | 1 | 1 | 0% | 7,537 | 1,441 | -81% | 0 | 0 | — |
case-20 | pass→fail | 50,563 | 7,571 | -85% | 1 | 1 | 0% | 3,304 | 1,523 | -54% | 0 | 0 | — |
case-21 | pass→pass | 29,667 | 35,417 | +19% | 1 | 1 | 0% | 4,522 | 5,879 | +30% | 0 | 0 | — |
case-22 | pass→pass | 13,585 | 14,922 | +10% | 1 | 1 | 0% | 1,762 | 3,083 | +75% | 0 | 0 | — |
case-23 | pass→pass | 27,245 | 29,475 | +8% | 1 | 1 | 0% | 3,914 | 4,888 | +25% | 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. 23 cases were attempted, and 17 counted toward the lift figure. The other 6 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 +4 percentage points is the difference between those two pass rates over the 17 comparable cases. 5 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.