Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →A股业绩前瞻/季报预览/财报预期情景分析。当用户提到"业绩前瞻"或"earnings preview"就触发。关键词："业绩前瞻"、"季报预览"、"预期怎么样"、"earnings preview"、"XX下周发财报"、"财报前怎么看"、"业绩预告分析"、"预计业绩"、"业绩展望"、"财报前瞻"、"预计这个季度业绩"、"业绩预期"、"情景分析"、"业绩预测"。MUST USE when user asks about earnings preview, pre-earnings scenario analysis, earnings expectations/forecast, or quarterly outlook before earnings release. This is the ONLY skill for pre-earnings forward-looking analysis. 在财报发布前，基于历史数据和市场预期构建牛/熊/基准三种情景分析。通过 cn-stock-data 获取历史财务趋势，结合 web 搜索获取市场一致预期和业绩预告。支持机构前瞻风格（form
.claude/skills/aifinlab-a-share-earnings-preview/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -20% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 38% | 0% |
| case-04 | ✓→✗ | ▼ Worse | -39% | 0% |
bashSCRIPTS="$SKILLS_ROOT/cn-stock-data/scripts" # 历史财务指标（分析趋势） python "$SCRIPTS/cn_stock_data.py" finance --code [CODE] # 最新行情（当前估值水平） python "$SCRIPTS/cn_stock_data.py" quote --code [CODE] # 近 6 个月 K 线（股价已 price-in 多少预期） python "$SCRIPTS/cn_stock_data.py" kline --code [CODE] --freq daily --start [6个月前日期] # 资金流向（机构是否提前布局） python "$SCRIPTS/cn_stock_data.py" fund_flow --code [CODE] --days 30
补充：通过 web 搜索获取：
财务指标预期（基于历史趋势 + 市场预期）：
| 指标 | 上季度实际 | 去年同期 | 市场预期 | 个人预判 | |------|-----------|---------|---------|---------| | 营业收入(亿) | | | | | | 同比增速(%) | | | | | | 归母净利润(亿) | | | | | | 同比增速(%) | | | | | | 毛利率(%) | | | | | | 净利率(%) | | | | |
行业特定运营指标（通过 web 搜索获取）：
构建三种情景：
| | 牛市情景(Bull) | 基准情景(Base) | 熊市情景(Bear) | |--|--------------|--------------|--------------| | 营收 | | | | | 净利润 | | | | | 关键驱动 | 什么因素超预期] | 符合市场预期] | 什么因素低于预期] | | 概率 | XX% | XX% | XX% | | 股价反应 | +X% to +X% | -X% to +X% | -X% to -X% |
每个情景的逻辑必须自洽，概率合计 = 100%
列出决定股价反应的 3-5 个关键观察点：
根据用户需求选择 formal 或 brief 风格，参考 references/preview-template.md 中的模板。
| 维度 | formal（机构前瞻） | brief（个人预判） | |------|-------------------|-----------------| | 篇幅 | 2-3 页 | 半页 | | 历史趋势 | 4-8 季度完整表格 | 简述趋势方向 | | 情景分析 | 完整三情景 + 概率 + 股价反应估计 | 简化版（重点写偏离预期的情景） | | 运营指标 | 行业特定的 3-5 个 | 1-2 个最关键的 | | 催化剂 | 完整检查清单 | 1-2 个最重要观察点 | | 交易建议 | 不给（只分析） | 可加个人操作思路 | | 免责声明 | 需要 | 不需要 |
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 | pass→fail | 21,994 | 11,341 | -48% | 1 | 1 | 0% | 3,434 | 2,084 | -39% | 0 | 0 | — |
case-05 | pass→fail | 31,949 | 89,916 | +181% | 1 | 1 | 0% | 5,881 | 1,952 | -67% | 0 | 0 | — |
case-06 | pass→fail | 21,869 | 14,026 | -36% | 1 | 1 | 0% | 3,219 | 2,664 | -17% | 0 | 0 | — |
case-07 | fail→pass | 15,643 | 6,422 | -59% | 1 | 1 | 0% | 3,032 | 2,484 | -18% | 0 | 0 | — |
case-01 | fail→fail | 29,804 | 31,920 | +7% | 1 | 1 | 0% | 5,046 | 2,366 | -53% | 0 | 0 | — |
case-02 | fail→fail | 21,385 | 10,040 | -53% | 1 | 1 | 0% | 3,011 | 2,098 | -30% | 0 | 0 | — |
case-03 | fail→fail | 23,414 | 9,217 | -61% | 1 | 1 | 0% | 4,042 | 2,114 | -48% | 0 | 0 | — |
case-08 | fail→pass | 17,771 | 3,609 | -80% | 1 | 1 | 0% | 2,629 | 2,102 | -20% | 0 | 0 | — |
case-09 | fail→pass | 12,885 | 3,553 | -72% | 1 | 1 | 0% | 2,428 | 2,182 | -10% | 0 | 0 | — |
case-10 | pass→pass | 19,740 | 15,621 | -21% | 1 | 1 | 0% | 3,152 | 3,986 | +26% | 0 | 0 | — |
case-11 | pass→pass | 19,545 | 18,189 | -7% | 1 | 1 | 0% | 2,983 | 4,265 | +43% | 0 | 0 | — |
case-12 | pass→pass | 18,780 | 16,910 | -10% | 1 | 1 | 0% | 2,637 | 3,917 | +49% | 0 | 0 | — |
case-13 | fail→fail | 20,011 | 11,253 | -44% | 1 | 1 | 0% | 3,231 | 2,098 | -35% | 0 | 0 | — |
case-14 | fail→pass | 16,159 | 11,703 | -28% | 1 | 1 | 0% | 2,386 | 3,304 | +38% | 0 | 0 | — |
case-15 | pass→pass | 20,981 | 10,152 | -52% | 1 | 1 | 0% | 3,225 | 2,951 | -8% | 0 | 0 | — |
case-16 | fail→fail | 14,079 | 2,968 | -79% | 1 | 1 | 0% | 2,137 | 1,927 | -10% | 0 | 0 | — |
case-17 | pass→pass | 20,330 | 22,374 | +10% | 1 | 1 | 0% | 3,003 | 4,795 | +60% | 0 | 0 | — |
case-18 | pass→pass | 20,993 | 22,274 | +6% | 1 | 1 | 0% | 3,105 | 4,851 | +56% | 0 | 0 | — |
case-19 | pass→pass | 21,738 | 17,715 | -19% | 1 | 1 | 0% | 2,926 | 4,210 | +44% | 0 | 0 | — |
case-20 | pass→pass | 6,390 | 5,473 | -14% | 1 | 1 | 0% | 843 | 2,245 | +166% | 0 | 0 | — |
case-21 | pass→pass | 12,536 | 6,273 | -50% | 1 | 1 | 0% | 1,768 | 2,567 | +45% | 0 | 0 | — |
case-22 | pass→pass | 18,164 | 15,290 | -16% | 1 | 1 | 0% | 2,873 | 3,875 | +35% | 0 | 0 | — |
case-23 | pass→pass | 20,693 | 24,054 | +16% | 1 | 1 | 0% | 2,703 | 4,653 | +72% | 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 16 counted toward the lift figure. The other 7 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 16 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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/28/2026 | -9% |
Other measured skills in the registry, with their headline benchmark lift.