Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →公司研究助手 - 大盘蓝筹版。专注于大盘蓝筹公司研究，包括沪深 300、上证 50 成分股等行业龙头公司。 **触发场景**： - 用户研究大盘蓝筹公司（市值>500 亿、行业龙头、沪深 300 成分股） - 分析蓝筹公司财务指标（ROE、毛利率、现金流、分红率） - 蓝筹公司估值分析（PE、PB、DCF） - 蓝筹公司竞品对标、护城河分析 - 写蓝筹公司研报、投资建议 **关键词**："大盘"、"蓝筹"、"龙头"、"沪深 300"、"上证 50"、"市值"、"ROE"、"护城河"、"贵州茅台"、"宁德时代"、"招商银行"
.claude/skills/aifinlab-company-research-blue-chip/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 32% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 35% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 65% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 12% | 0% |
你是一名专注于大盘蓝筹公司的资深研究员，擅长分析行业龙头的竞争优势、财务质量、估值水平与长期投资价值。
| 标准 | 指标 | |------|------| | 市值 | >500 亿元 | | 行业地位 | 行业前三、市场份额领先 | | 财务质量 | ROE>15%、稳定现金流 | | 指数成分 | 沪深 300、上证 50 成分股 |
1. 公司定位（行业龙头/市值/地位）
2. 核心财务指标（ROE、毛利率、增速）
3. 估值水平（PE/PB 历史分位）
4. 投资亮点（2-3 条）
5. 风险提示1. 公司概况（业务、市值、行业地位）
2. 护城河分析（品牌/成本/网络/切换/牌照）
3. 财务分析（盈利/成长/现金流/健康度）
4. 竞争格局（市场份额、主要对手）
5. 估值分析（PE/PB/DCF、历史分位、同业对比）
6. 分红与回购
7. 催化剂与风险
8. 投资建议在标准分析基础上增加：
| 指标 | 公司 A | 公司 B | 公司 C | 行业平均 | |------|--------|--------|--------|----------| | 市值 (亿) | | | | | | PE-TTM | | | | | | PB | | | | | | ROE(%) | | | | | | 毛利率 (%) | | | | | | 净利率 (%) | | | | | | 营收增速 (%) | | | | | | 股息率 (%) | | | | |
输出前自查：
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-04 | fail→fail | 24,500 | 20,340 | -17% | 1 | 1 | 0% | 3,374 | 3,872 | +15% | 0 | 0 | — |
case-01 | fail→fail | 15,825 | 18,428 | +16% | 1 | 1 | 0% | 2,482 | 3,574 | +44% | 0 | 0 | — |
case-02 | fail→pass | 28,562 | 30,731 | +8% | 1 | 1 | 0% | 4,388 | 5,782 | +32% | 0 | 0 | — |
case-03 | fail→fail | 48,591 | 48,937 | +1% | 1 | 1 | 0% | 8,263 | 9,233 | +12% | 0 | 0 | — |
case-05 | pass→pass | 21,086 | 20,509 | -3% | 1 | 1 | 0% | 3,410 | 4,055 | +19% | 0 | 0 | — |
case-06 | fail→pass | 18,308 | 19,438 | +6% | 1 | 1 | 0% | 2,924 | 3,756 | +28% | 0 | 0 | — |
case-07 | pass→pass | 19,039 | 19,923 | +5% | 1 | 1 | 0% | 2,942 | 4,013 | +36% | 0 | 0 | — |
case-08 | pass→pass | 25,791 | 28,925 | +12% | 1 | 1 | 0% | 3,590 | 5,028 | +40% | 0 | 0 | — |
case-09 | fail→pass | 22,823 | 23,411 | +3% | 1 | 1 | 0% | 3,745 | 5,062 | +35% | 0 | 0 | — |
case-10 | fail→pass | 14,183 | 15,007 | +6% | 1 | 1 | 0% | 2,161 | 3,557 | +65% | 0 | 0 | — |
case-11 | fail→pass | 20,311 | 14,781 | -27% | 1 | 1 | 0% | 2,886 | 3,218 | +12% | 0 | 0 | — |
case-12 | pass→pass | 21,084 | 18,990 | -10% | 1 | 1 | 0% | 2,983 | 3,870 | +30% | 0 | 0 | — |
case-13 | fail→pass | 24,808 | 20,993 | -15% | 1 | 1 | 0% | 4,058 | 4,352 | +7% | 0 | 0 | — |
case-14 | pass→pass | 16,729 | 10,092 | -40% | 1 | 1 | 0% | 2,764 | 2,759 | -0% | 0 | 0 | — |
case-15 | pass→pass | 24,250 | 24,033 | -1% | 1 | 1 | 0% | 3,545 | 4,488 | +27% | 0 | 0 | — |
case-16 | pass→pass | 20,131 | 21,405 | +6% | 1 | 1 | 0% | 2,922 | 4,164 | +43% | 0 | 0 | — |
case-17 | pass→pass | 21,578 | 23,651 | +10% | 1 | 1 | 0% | 3,267 | 4,351 | +33% | 0 | 0 | — |
case-18 | fail→pass | 13,870 | 4,332 | -69% | 1 | 1 | 0% | 2,064 | 1,705 | -17% | 0 | 0 | — |
case-19 | pass→pass | 13,179 | 4,572 | -65% | 1 | 1 | 0% | 2,079 | 1,751 | -16% | 0 | 0 | — |
case-20 | pass→pass | 25,570 | 23,660 | -7% | 1 | 1 | 0% | 3,734 | 4,513 | +21% | 0 | 0 | — |
case-21 | fail→pass | 21,925 | 13,184 | -40% | 1 | 1 | 0% | 3,135 | 2,791 | -11% | 0 | 0 | — |
case-22 | fail→fail | 24,275 | 31,160 | +28% | 1 | 1 | 0% | 3,704 | 5,588 | +51% | 0 | 0 | — |
case-23 | pass→pass | 18,486 | 17,050 | -8% | 1 | 1 | 0% | 2,860 | 3,584 | +25% | 0 | 0 | — |
case-24 | pass→pass | 6,807 | 7,453 | +9% | 1 | 1 | 0% | 1,051 | 2,103 | +100% | 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. 24 cases were attempted. The headline lift of +33 percentage points is the difference between those two pass rates over the 24 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.