Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →A股市场集中度/筹码集中度分析。当用户说"集中度"、"concentration"、"筹码集中"、"HHI"、"CR10"、"龙头占比"时触发。量化分析市场或行业集中度。支持formal和brief风格。
.claude/skills/aifinlab-a-share-concentration-index/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 17% | 0% |
| case-20 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-22 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-02 | ✓→✗ | ▼ Worse | -42% | 0% |
bashSCRIPTS="$SKILLS_ROOT/cn-stock-data/scripts" python "$SCRIPTS/cn_stock_data.py" kline --code [CODE] --freq daily --start [日期] python "$SCRIPTS/cn_stock_data.py" quote --code [CODE] python "$SCRIPTS/cn_stock_data.py" finance --code [CODE]
历史集中度时序变化
| 维度 | formal | brief | |------|--------|-------| | 集中度指标 | CR5/10/20+HHI | CR5 | | 趋势 | 历史变化序列 | 升/降 | 默认风格：brief。
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-01 | fail→pass | 16,625 | 24,180 | +45% | 1 | 1 | 0% | 2,401 | 2,643 | +10% | 0 | 0 | — |
case-02 | pass→fail | 21,191 | 21,016 | -1% | 1 | 1 | 0% | 2,793 | 1,617 | -42% | 0 | 0 | — |
case-03 | fail→fail | 27,705 | 15,835 | -43% | 1 | 1 | 0% | 3,956 | 1,570 | -60% | 0 | 0 | — |
case-04 | fail→fail | 10,682 | 9,245 | -13% | 1 | 1 | 0% | 1,496 | 1,870 | +25% | 0 | 0 | — |
case-05 | pass→fail | 21,006 | 8,303 | -60% | 1 | 1 | 0% | 3,213 | 830 | -74% | 0 | 0 | — |
case-06 | pass→pass | 25,918 | 19,991 | -23% | 1 | 1 | 0% | 3,323 | 3,200 | -4% | 0 | 0 | — |
case-07 | pass→pass | 19,295 | 12,461 | -35% | 1 | 1 | 0% | 3,054 | 2,184 | -28% | 0 | 0 | — |
case-08 | pass→pass | 23,819 | 20,519 | -14% | 1 | 1 | 0% | 2,992 | 3,089 | +3% | 0 | 0 | — |
case-09 | pass→pass | 22,005 | 16,421 | -25% | 1 | 1 | 0% | 2,641 | 2,658 | +1% | 0 | 0 | — |
case-10 | pass→pass | 23,728 | 18,198 | -23% | 1 | 1 | 0% | 2,740 | 2,745 | +0% | 0 | 0 | — |
case-11 | pass→pass | 23,137 | 24,297 | +5% | 1 | 1 | 0% | 2,920 | 3,446 | +18% | 0 | 0 | — |
case-12 | pass→pass | 20,103 | 6,367 | -68% | 1 | 1 | 0% | 2,617 | 1,469 | -44% | 0 | 0 | — |
case-13 | pass→pass | 18,865 | 15,526 | -18% | 1 | 1 | 0% | 2,566 | 2,523 | -2% | 0 | 0 | — |
case-14 | pass→pass | 16,508 | 4,362 | -74% | 1 | 1 | 0% | 2,203 | 1,149 | -48% | 0 | 0 | — |
case-15 | pass→pass | 22,802 | 6,162 | -73% | 1 | 1 | 0% | 1,896 | 1,402 | -26% | 0 | 0 | — |
case-16 | pass→pass | 19,391 | 16,631 | -14% | 1 | 1 | 0% | 3,405 | 3,215 | -6% | 0 | 0 | — |
case-17 | pass→pass | 40,242 | 21,196 | -47% | 1 | 1 | 0% | 2,749 | 2,457 | -11% | 0 | 0 | — |
case-18 | pass→pass | 20,076 | 12,600 | -37% | 1 | 1 | 0% | 2,691 | 2,505 | -7% | 0 | 0 | — |
case-19 | fail→pass | 9,473 | 7,509 | -21% | 1 | 1 | 0% | 1,311 | 1,540 | +17% | 0 | 0 | — |
case-20 | fail→pass | 24,413 | 17,182 | -30% | 1 | 1 | 0% | 3,265 | 3,229 | -1% | 0 | 0 | — |
case-21 | pass→pass | 13,019 | 7,222 | -45% | 1 | 1 | 0% | 1,735 | 1,708 | -2% | 0 | 0 | — |
case-22 | fail→pass | 17,601 | 16,071 | -9% | 1 | 1 | 0% | 2,438 | 2,599 | +7% | 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 19 counted toward the lift figure. The other 3 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 +9 percentage points is the difference between those two pass rates over the 19 comparable cases. 3 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.