Data & analysis

csv-profiler

Try it

Profile and analyze CSV or other tabular data — column types, summary statistics, missing values, and anomalies. Use when the user needs to understand, clean, or sanity-check a dataset.

What it does

Profile and analyze CSV or other tabular data — column types, summary statistics, missing values, and anomalies. Use when the user needs to understand, clean, or sanity-check a dataset.

The skill document

CSV Profiler

Turn a raw CSV (or TSV, or an existing DataFrame) into a clear profile of what the data actually contains.

Workflow

  1. Load and detect. Read the file; detect delimiter, encoding, and header. Report row and column counts.

  2. Classify columns. For each column, assign a type: numeric, datetime, categorical, boolean, or free text.

  3. Summarize. For each column report:

    • Numeric: min, max, mean, median, missing count, distinct count.
    • Categorical: top values with counts, distinct count, missing count.
    • Datetime: min/max range and count of unparseable values.
  4. Flag anomalies. Call out:

    • Missing or empty values, and all-null columns.
    • Mixed types within a single column.
    • Duplicate rows and near-duplicate keys.
    • Outliers beyond roughly 1.5×IQR.
  5. Recommend. Suggest concrete cleaning steps (drop, fill, cast, dedupe) and note which columns look usable as identifiers or join keys.

Related skills

Upload data files, get back analysis with charts, cleaned datasets, statistical reports, and dashboards.

114 installs5 stars

Inspect delimited tables (CSV/TSV) before any analysis: column names, encodings, delimiters, row counts, inferred types, and first/last rows. Use when the user asks to peek a CSV, list headers, show head/tail, preview schema, check dtypes, or before pandas work on .csv/.tsv/.tab files. Use when the user runs /csv-inspect. Do not use for Excel workbooks (.xlsx) or for writing statistical reports — inspect only, then stop or hand off.

CSV数据分析免费版,提供快速统计与基础筛选,零外部依赖,适合轻量数据探索。Use when 需要数据分析、报表生成、统计洞察、数据可视化时使用。不适用于实时流数据处理。适用于独立开发者、企业团队和自动化工作流场景。支持中文交互,无需复杂配置即开即用。输出结果可直接使用,减少二次加工成本。提供结构化输出和错误处理机制。

1 installs

CSV 工具集 v1.1.0 — 子命令+安全增强。 预览、筛选、排序、合并、分割、去重、验证、统计、 列操作(重命名/选择/计算列)、类型检测、数据画像、抽样。 纯Python标准库(csv模块),无外部依赖。 Use when: - 需要快速处理CSV文件(预览/筛选/排序/统计) - 合并多个CSV文件或分割大CSV文件 - CSV数据去重、列操作、类型检测、数据画像 Do NOT use when: - 非CSV格式数据(JSON/YAML/Excel/数据库) - 需要写回原始输入文件 - 简单的数据查看(推荐用 cat/head 等系统命令) 🎉 v1.1.0 新增子命令:

DataGate parses untrusted CSV or JSON through a deterministic tool boundary before model analysis. Use for requests like "analyze this CSV", "summarize this...

13 installs

自动检测编码与分隔符,读取并清洗CSV数据,支持基础合并与导出。Use when 需要数据分析、报表生成、统计洞察、数据可视化时使用。不适用于实时流数据处理。适用于独立开发者、企业团队和自动化工作流场景。支持中文交互,无需复杂配置即开即用。输出结果可直接使用,减少二次加工成本。提供结构化输出和错误处理机制。