Skip to content
Skills Library
Data & analytics · Analysis

data-profiling

/data-profiling

【数据轮廓速览】当用户刚上传数据、问"数据有多少行"、"有哪些字段"、"数据长什么样"时使用。描述数据结构(行列数、字段类型、缺失率、分布特征、数据质量),不计算建模指标。无需目标变量。与 feature-analysis 的区别:只做"描述"不做"分析",不计算IV/PSI/相关性等建模指标。

Licence
MIT
Last repository change
17.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
4
Scripts
3
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 17.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What to check before installing
  • 3 scripts in this package. Review them before installing, as Claude may execute them.

Scripts: _vendor/__init__.py, _vendor/result_emitter.py, scripts/profiler.py

What it does and when to use it

【数据轮廓速览】当用户刚上传数据、问"数据有多少行"、"有哪些字段"、"数据长什么样"时使用。描述数据结构(行列数、字段类型、缺失率、分布特征、数据质量),不计算建模指标。无需目标变量。与 feature-analysis 的区别:只做"描述"不做"分析",不计算IV/PSI/相关性等建模指标。

Triggers from the description

数据有多少行有哪些字段数据长什么样
Original author description

【数据轮廓速览】当用户刚上传数据、问"数据有多少行"、"有哪些字段"、"数据长什么样"时使用。描述数据结构(行列数、字段类型、缺失率、分布特征、数据质量),不计算建模指标。无需目标变量。与 feature-analysis 的区别:只做"描述"不做"分析",不计算IV/PSI/相关性等建模指标。

How it works

  1. 参数说明
  2. 执行方式
  3. 产物示例
  4. 报告输出结构
  5. 自适应展示
  6. 与其他 Skill 的关系
  7. 注意事项
Original SKILL.md headings · 91 lines, 240 words
SKILL.md preview
---
name: data-profiling
category: 数据探索
description: 【数据轮廓速览】当用户刚上传数据、问"数据有多少行"、"有哪些字段"、"数据长什么样"时使用。描述数据结构(行列数、字段类型、缺失率、分布特征、数据质量),不计算建模指标。无需目标变量。与 feature-analysis 的区别:只做"描述"不做"分析",不计算IV/PSI/相关性等建模指标。
next_steps:
  - skill: feature-analysis
    text: 全量特征分析,推荐建模方案
    prompt: 全面分析所有特征,推荐建模方案
---

# 数据洞察报告 (portable)

基于 `scripts/profiler.py` 主脚本,对数据集进行轮廓扫描,生成数据概况报告。

---

## 参数说明

| 参数 | 必选 | 默认值 | 说明 |
|------|:----:|--------|------|
| `--data_path` | ✅ | - | 数据文件路径(parquet/csv) |
| `--output` | | `data_profiling_report.md` | 报告输出路径 |
| `--output_dir` | | `./outputs/<ts>` | 产物输出目录 |
| `--output_name` | | `data_profiling_report` | 报告基名(不含扩展名) |
| `--config` | | - | JSON 配置文件路径 |

---

## 执行方式

```bash
python scripts/profiler.py \
  --data_path ./examples/toy.parquet \
  --output_dir ./outputs/profile_run
```

执行结束后:
- 产物目录 `<output_dir>/` 下生成:
  - `report.md` — 数据概况报告
  - `result.json` — 结构化产物清单(见 PROTOCOL.md)
- stdout 末行打印 `result.json` 绝对路径,Agent 读这个文件即可

---

## 产物示例

```json
{
  "skill": "data-profiling",
  "status": "success",
  "files": [
    {"path": ".../report.md", "role": "report"}
  ],
  "metrics": {"n_rows": 10000, "n_cols": 28, "n_missing_cols": 5},
  "summary": "中等规模数据集(10,000行),28 个字段,数值型为主,发现 2 个高缺失字段"
}
```

---

## 报告输出结构

| 章节 | 内容 |
|------|------|
| 1. 数据概览 | 文件名、格式、大小、行列数、字段类型分布饼图 |
| 2. 字段详情清单 | 每个字段的类型、缺失率、唯一值数、示例值 |
| 3. 数值特征分析 | 描述性统计(均值/标准差/分位数/偏度/峰度)+ histogram 分布图 |
| 4. 类别特征分析 | 唯一值数、Top 值占比、集中度 + bar chart |
| 5. 缺失值分析 | 缺失率排名表格 + 柱状图 |
| 6. 数据质量 | 重复行、空列、常量列、高缺失列 |
| 7. 样本预览 | 前 5 行数据展示 |

---

## 自适应展示

当数值/类别特征数量超过 20 个时,统计表格和图表只展示前 20 个,避免报告过长。

---

## 与其他 Skill 的关系

| Skill | 用途区别 |
|-------|----------|
| **data-profiling** | 快速了解数据轮廓,不做深度分析 |
| feature-analysis | 深度特征分析(IV、PSI、相关性等),需要目标变量 |
| xgb-modeling | 建模全流程,需要目标变量 |

**建议流程**:
1. 先用 `data-profiling` 了解数据基本情况
2. 根据洞察结果,决定是否需要 `feature-analysis` 或 `xgb-modeling`

---

## 注意事项

1. **无需目标变量**:本 Skill 不需要提供目标变量,纯数据描述
2. **快速轻量**:执行速度快,适合大数据集的快速扫描
3. **自动类型推断**:识别数值型、类别型、布尔型、时间型、文本型字段
Files in this package (4)
  • SKILL.md 3 KB
  • _vendor/__init__.py 1 KB
  • _vendor/result_emitter.py 7 KB
  • scripts/profiler.py 12 KB

Versions

RepositoryScoreLicence
This page · aliyun/qwen-dianjin100MIT
Harrypatria/data-mining-ml100MIT
ai-analyst-lab/ai-analyst100MIT
ai-analyst-lab/ai-analyst-plugin100MIT

Database snapshot: 13.11.2026 · package version b4fc17fac68c (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100explore-data
    Profile and explore a dataset to understand its shape, quality, and patterns. Use when encountering a new table or file, checking null rates and column distributions, spotting data quality issues like duplicates or suspicious values, or deciding which dimensions and metrics to analyze.
  • 98exploratory-data-analysis
    Perform systematic exploratory data analysis to understand dataset structure, distributions, relationships, and anomalies before modeling. Use when a dataset is new, its quality is unknown, or the user requests open-ended profiling; use data-analysis instead for a defined…
  • 100profiling-tables
    Deep-dive data profiling for a specific table. Use when the user asks to profile a table, wants statistics about a dataset, asks about data quality, or needs to understand a table's structure and content. Requires a table name.
  • 98eda-report
    Run exploratory data analysis on a dataset and produce a structured report. Use when the user says "explore this dataset", "EDA on X", "analyze this data", "what's in this dataset", "summarize this data", "first look at the data", "understand this dataset before modeling", "data…
  • 90programmatic-eda
    Systematic exploratory data analysis. Activate when a dataset needs profiling — structure check, nulls, outliers, distributions, correlations — before deeper analysis begins.
  • 100feature-analysis
    【特征深度分析】当用户需要"全面分析特征"、"生成特征报告"、"看相关性"、"推荐建模方案"、"跑一遍特征"、"特征全景"、"哪些特征有用"时使用。包含四大维度:基础统计、IV值、PSI稳定性、相关性分析,输出四套建模特征方案。前提条件:必须提供目标变量。不做单特征快速探索,不做模型训练。与 univariate-analysis 的区别:本 Skill 是全量特征深度分析+方案推荐,univariate-analysis 聚焦少量特征快速分析。

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.