Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →A股概念板块/题材分析/热点概念追踪。当用户说"概念板块"、"题材"、"热点板块"、"概念股"、"XX概念"、"AI概念"、"新能源概念"、"XX板块有哪些股票"、"今天什么板块涨了"、"风口"、"概念板块分析"、"热点题材"时触发。MUST USE when user asks about concept/thematic sectors, hot topics, or which concept boards are trending in A-shares. 基于 adata 概念板块数据和 cn-stock-data 行情数据，分析概念板块构成、走势、龙头股、资金流向。支持研报风格（formal）和快速解读风格（brief）。
.claude/skills/aifinlab-a-share-concept/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 30% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -37% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-17 | ✗→✓ | ▲ Improved | -21% | 0% |
| case-21 | ✗→✓ | ▲ Improved | -36% | 0% |
bashSCRIPTS="$SKILLS_ROOT/cn-stock-data/scripts" # 概念板块列表（adata） python -c "import adata; df=adata.stock.info.concept_constituent(wait_time=0); print(df.head(20).to_json(orient='records', force_ascii=False))" # 概念板块成分股（adata，需指定 concept_code） python -c "import adata; df=adata.stock.info.concept_constituent(concept_code='BK0655'); print(df.to_json(orient='records', force_ascii=False))" # 成分股行情 python "$SCRIPTS/cn_stock_data.py" quote --code [CODE1],[CODE2],... # 成分股K线 python "$SCRIPTS/cn_stock_data.py" kline --code [CODE] --freq daily --start [日期] # 成分股资金流向 python "$SCRIPTS/cn_stock_data.py" fund_flow --code [CODE]
补充：通过 web 搜索获取概念板块热度、新闻催化剂、政策驱动因素。
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→fail | 21,306 | 14,706 | -31% | 1 | 1 | 0% | 2,745 | 1,319 | -52% | 0 | 0 | — |
case-02 | fail→fail | 33,010 | 9,779 | -70% | 1 | 1 | 0% | 4,638 | 1,095 | -76% | 0 | 0 | — |
case-03 | fail→fail | 33,347 | 10,410 | -69% | 1 | 1 | 0% | 4,400 | 1,167 | -73% | 0 | 0 | — |
case-04 | pass→fail | 27,522 | 13,094 | -52% | 1 | 1 | 0% | 3,245 | 1,440 | -56% | 0 | 0 | — |
case-05 | pass→fail | 25,082 | 11,479 | -54% | 1 | 1 | 0% | 3,355 | 1,326 | -60% | 0 | 0 | — |
case-06 | pass→fail | 31,945 | 13,951 | -56% | 1 | 1 | 0% | 4,466 | 1,248 | -72% | 0 | 0 | — |
case-07 | fail→pass | 18,095 | 17,145 | -5% | 1 | 1 | 0% | 2,223 | 2,890 | +30% | 0 | 0 | — |
case-08 | pass→pass | 20,276 | 23,630 | +17% | 1 | 1 | 0% | 2,455 | 3,811 | +55% | 0 | 0 | — |
case-09 | pass→pass | 11,023 | 16,438 | +49% | 1 | 1 | 0% | 1,621 | 2,814 | +74% | 0 | 0 | — |
case-10 | pass→pass | 20,148 | 20,726 | +3% | 1 | 1 | 0% | 2,816 | 3,798 | +35% | 0 | 0 | — |
case-11 | pass→pass | 10,674 | 9,067 | -15% | 1 | 1 | 0% | 1,437 | 1,729 | +20% | 0 | 0 | — |
case-12 | pass→fail | 9,012 | 9,249 | +3% | 1 | 1 | 0% | 1,138 | 1,083 | -5% | 0 | 0 | — |
case-13 | pass→fail | 29,297 | 10,094 | -66% | 1 | 1 | 0% | 4,441 | 1,126 | -75% | 0 | 0 | — |
case-14 | fail→pass | 15,302 | 6,574 | -57% | 1 | 1 | 0% | 2,652 | 1,658 | -37% | 0 | 0 | — |
case-15 | fail→pass | 18,026 | 11,745 | -35% | 1 | 1 | 0% | 2,632 | 2,584 | -2% | 0 | 0 | — |
case-16 | pass→pass | 17,859 | 25,782 | +44% | 1 | 1 | 0% | 2,367 | 3,368 | +42% | 0 | 0 | — |
case-17 | fail→pass | 21,774 | 12,354 | -43% | 1 | 1 | 0% | 2,759 | 2,178 | -21% | 0 | 0 | — |
case-18 | pass→pass | 21,594 | 21,610 | +0% | 1 | 1 | 0% | 3,096 | 3,710 | +20% | 0 | 0 | — |
case-19 | pass→pass | 12,486 | 3,880 | -69% | 1 | 1 | 0% | 2,344 | 1,315 | -44% | 0 | 0 | — |
case-20 | pass→pass | 16,354 | 15,335 | -6% | 1 | 1 | 0% | 2,229 | 2,645 | +19% | 0 | 0 | — |
case-21 | fail→pass | 15,802 | 3,220 | -80% | 1 | 1 | 0% | 1,817 | 1,160 | -36% | 0 | 0 | — |
case-22 | pass→pass | 21,217 | 33,446 | +58% | 1 | 1 | 0% | 3,075 | 3,655 | +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 14 counted toward the lift figure. The other 8 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 0 percentage points is the difference between those two pass rates over the 14 comparable cases. 7 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.