Ask me what skills you need
What are you building?
Tell me what you're working on and I'll find the best agent skills for you.
读取多工作表Excel文件，自动处理合并单元格与数据清洗，进行交叉分组统计并生成带总计行的结果表，最后绘制支持中英文字体的美化柱状图，适用于多维度数据汇总与可视化分析。
This sub-skill covers one capability of the Excel workflow. For reading/counting/Parquet optimization, see the parent workflow SKILL.md.
combined_df = pd.concat(data_frames, ignore_index=True)
# 数据清洗：使用正则表达式统一命名
if '题型' in combined_df.columns:
combined_df['题型'] = combined_df['题型'].astype(str).str.replace('判', '判断题', regex=False)
# 处理合并单元格技巧1：前向填充
if '流程描述' in combined_df.columns:
combined_df['流程描述'] = combined_df['流程描述'].fillna(method='ffill')
# 处理合并单元格技巧2：通过逻辑判断与手动映射还原完整名称
group_col = '项目阶段'
target_col = '控制要点'
if group_col in combined_df.columns and target_col in combined_df.columns:
project_stages, control_points = [], []
current_stage = None
for _, row in combined_df.iterrows():
stage = row[group_col]
point = row[target_col]
if pd.notna(point) and point != target_col:
if pd.notna(stage):
current_stage = stage
project_stages.append(current_stage)
control_points.append(point)
combined_df = pd.DataFrame({
group_col: project_stages,
target_col: control_points
})
# 分类映射函数骨架
npx skills add OpenSenseNova/SenseNova-Skills --skill bar-chart-visualizationHow clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
Clear and well structured, with only minor parts that might need a second read.
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
Partially actionable with several concrete steps, but still missing important details.