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.
对 Excel 数据进行数值格式标准化与清洗，支持大规模数据的 Parquet 转换流程，并完成关键指标的合计核对与结果文件导出。
This sub-skill covers one capability of the Excel workflow. For reading/counting/Parquet optimization, see the parent workflow SKILL.md.
Step1 对目标列进行数据清洗（去除空值、标准化数值格式），计算合计值，并与指定汇总 Sheet 中的合计行进行精确核对。
target_col = '目标数值列' # 示例：'建筑面积'
summary_sheet_name = 'Summary' # 示例汇总Sheet名
summary_item_col = '项目'
summary_value_col = '数值'
# 数据清洗：去除空值、强制转换为数值格式
df_cleaned = df_processed.dropna(subset=[target_col]).copy()
df_cleaned[target_col] = pd.to_numeric(df_cleaned[target_col], errors='coerce')
# 计算合计
total_calculated = df_cleaned[target_col].sum()
# 从指定 Sheet 中读取“合 计”行数值进行核对
try:
summary_sheet = pd.read_excel(file_path, sheet_name=summary_sheet_name)
expected_total = summary_sheet.loc[summary_sheet[summary_item_col] == '合 计', summary_value_col].values[0]
# 核对一致性 (处理浮点数精度问题)
if abs(total_calculated - expected_total) < 1e-6:
consistency = "一致"
difference = 0
else:
consistency = "不一致"
difference = abs(total_calculated - expected_total)
print(f"计算合计: {total_calculated}, 指定合计: {expected_total}, 一致性: {consistency}")
except Exception as e:
print(f"核对失败: {e}")
expected_total = None
npx skills add OpenSenseNova/SenseNova-Skills --skill numeric-format-normalizationHow 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.
Mostly actionable with clear steps; only a few small gaps remain.