Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →A股财报日历/业绩预告汇总。当用户说"财报日历"、"业绩预告"、"什么时候发财报"、"XX什么时候出报告"、"earnings calendar"、"最近谁发财报"、"业绩快报"、"业绩预告汇总"、"哪些公司业绩超预期"时触发。汇总近期已发布和即将发布的财报/业绩预告，分析业绩超预期和不及预期的情况。支持研报风格（formal）和快速查询风格（brief）。不适用于个股深度财报分析（用 a-share-earnings-analysis）。
.claude/skills/aifinlab-a-share-earnings-calendar/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-17 | ✗→✓ | ▲ Improved | -36% | 0% |
| case-18 | ✗→✓ | ▲ Improved | -44% | 0% |
| case-02 | ✓→✗ | ▼ Worse | -36% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 17% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 1% | 0% |
bashSCRIPTS="$SKILLS_ROOT/cn-stock-data/scripts" # 个股财务数据（已发布的） python "$SCRIPTS/cn_stock_data.py" finance --code [CODE] # 个股行情（看业绩公告后股价反应） python "$SCRIPTS/cn_stock_data.py" quote --code [CODE]
核心数据通过 akshare 获取：
bash# 业绩预告汇总（date 格式 YYYYMMDD，取季末日期：0331/0630/0930/1231） python -c "import akshare as ak; df=ak.stock_yjyg_em(date='20260331'); print(df.head(20).to_json(orient='records', force_ascii=False))" # 业绩快报 python -c "import akshare as ak; df=ak.stock_yjkb_em(date='20260331'); print(df.head(20).to_json(orient='records', force_ascii=False))"
补充：用 web 搜索获取财报披露时间表、市场一致预期、分析师预测。
| 维度 | formal | brief | |------|--------|-------| | 输出 | 完整业绩日历报告 | 关键信息列表 | | 覆盖 | 全市场统计+重点个股 | 仅用户关注的个股/板块 | | 分析 | 超预期/低于预期详细分析 | 预增/预减数量统计 | | 时间表 | 未来2周完整披露排期 | 近期重点关注 |
默认 brief；用户要求"详细/报告/研报"时用 formal。
references/earnings-calendar-guide.md 了解业绩预告类型定义和财报季节奏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 | 39,106 | 9,442 | -76% | 1 | 1 | 0% | 5,069 | 1,265 | -75% | 0 | 0 | — |
case-02 | pass→fail | 14,852 | 10,542 | -29% | 1 | 1 | 0% | 2,467 | 1,572 | -36% | 0 | 0 | — |
case-03 | fail→fail | 30,874 | 13,375 | -57% | 1 | 1 | 0% | 4,483 | 1,337 | -70% | 0 | 0 | — |
case-04 | pass→pass | 18,959 | 15,634 | -18% | 1 | 1 | 0% | 2,580 | 3,022 | +17% | 0 | 0 | — |
case-05 | pass→pass | 14,191 | 10,187 | -28% | 1 | 1 | 0% | 2,287 | 2,311 | +1% | 0 | 0 | — |
case-06 | pass→pass | 14,302 | 17,063 | +19% | 1 | 1 | 0% | 1,950 | 2,995 | +54% | 0 | 0 | — |
case-11 | pass→pass | 8,795 | 4,017 | -54% | 1 | 1 | 0% | 1,170 | 1,497 | +28% | 0 | 0 | — |
case-07 | pass→pass | 11,127 | 9,180 | -17% | 1 | 1 | 0% | 1,734 | 2,110 | +22% | 0 | 0 | — |
case-08 | pass→pass | 22,256 | 19,977 | -10% | 1 | 1 | 0% | 2,859 | 3,872 | +35% | 0 | 0 | — |
case-09 | pass→pass | 12,439 | 4,095 | -67% | 1 | 1 | 0% | 2,145 | 1,636 | -24% | 0 | 0 | — |
case-10 | pass→pass | 16,203 | 4,573 | -72% | 1 | 1 | 0% | 2,145 | 1,726 | -20% | 0 | 0 | — |
case-12 | pass→pass | 12,193 | 4,754 | -61% | 1 | 1 | 0% | 1,877 | 1,748 | -7% | 0 | 0 | — |
case-13 | pass→pass | 16,705 | 15,512 | -7% | 1 | 1 | 0% | 2,556 | 3,475 | +36% | 0 | 0 | — |
case-14 | pass→pass | 21,576 | 27,811 | +29% | 1 | 1 | 0% | 2,687 | 3,517 | +31% | 0 | 0 | — |
case-15 | fail→fail | 17,883 | 14,535 | -19% | 1 | 1 | 0% | 2,222 | 2,941 | +32% | 0 | 0 | — |
case-16 | fail→fail | 19,174 | 3,067 | -84% | 1 | 1 | 0% | 2,166 | 1,390 | -36% | 0 | 0 | — |
case-17 | fail→pass | 13,463 | 2,762 | -79% | 1 | 1 | 0% | 2,033 | 1,304 | -36% | 0 | 0 | — |
case-18 | fail→pass | 13,630 | 3,856 | -72% | 1 | 1 | 0% | 2,410 | 1,361 | -44% | 0 | 0 | — |
case-19 | pass→pass | 20,056 | 22,376 | +12% | 1 | 1 | 0% | 2,956 | 3,854 | +30% | 0 | 0 | — |
case-20 | fail→fail | 34,048 | 11,117 | -67% | 1 | 1 | 0% | 3,495 | 1,519 | -57% | 0 | 0 | — |
case-21 | fail→fail | 24,600 | 8,749 | -64% | 1 | 1 | 0% | 3,078 | 1,389 | -55% | 0 | 0 | — |
case-22 | fail→fail | 23,190 | 8,863 | -62% | 1 | 1 | 0% | 3,260 | 1,396 | -57% | 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 16 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 +5 percentage points is the difference between those two pass rates over the 16 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.