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.
根据文件行数动态切换大文件处理策略（Parquet转换），通过逐行扫描或列匹配提取关键指标并计算占比、均值等统计量，最终输出结构化Excel报告及可视化图表。
This sub-skill covers one capability of the Excel workflow. For reading/counting/Parquet optimization, see the parent workflow SKILL.md.
Step1 在数据中动态定位关键字段，通过逐行扫描匹配关键词提取数值，并进行条件筛选与占比计算。
key_values = {}
target_col = None
value_col = 'target_value_col'
# 动态查找目标分类列
for col in df_analysis.columns:
if 'keyword1' in col.lower() or 'keyword2' in col.lower():
target_col = col
break
# 通用字段查找逻辑：逐行扫描匹配关键词并提取首个正数
for idx, row in df_analysis.iterrows():
row_str = str(row.values)
if '指标A' in row_str and '指标A' not in key_values:
for val in row.values:
if isinstance(val, (int, float)) and val > 0:
key_values['指标A'] = val
break
if '指标B' in row_str and '指标B' not in key_values:
for val in row.values:
if isinstance(val, (int, float)) and val > 0:
key_values['指标B'] = val
break
# 条件筛选与统计
if target_col and '特定类别' in df_analysis[target_col].unique():
df_filtered = df_analysis[df_analysis[target_col] == '特定类别']
if value_col in df_filtered.columns:
npx skills add OpenSenseNova/SenseNova-Skills --skill percentage-calculationHow clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
Mostly clear, but there are still a few confusing or poorly structured parts.
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.