# Data Validation First

> Data Validation First is an Agent Skill for testing & quality published in the aiming-lab/MetaClaw repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Use this skill before any data analysis, transformation, or modeling. Always inspect and validate the data before drawing conclusions or writing transformations.

- Skill name: `data-validation-first`
- Category: [Testing & Quality](https://www.openparable.com/skill/testing-quality/1)
- Source: https://github.com/aiming-lab/MetaClaw/blob/HEAD/memory_data/skills/data-validation-first/SKILL.md
- Repository: aiming-lab/MetaClaw (3,466 GitHub stars when collected)

## SKILL.md

# Data Validation First

Before writing any analysis code, understand the data:

```python
# Always run these first
df.shape          # rows x columns
df.dtypes         # column types
df.isnull().sum() # missing values per column
df.describe()     # statistics for numeric columns
df.head()         # sample rows
```

**Key questions:**
- Are there nulls in columns you'll join or filter on?
- Are numeric columns stored as strings? (parse_dates, astype)
- Are there unexpected duplicates (check primary key uniqueness)?
- Does the row count match your expectation from the source?

**Anti-pattern:** Running `.groupby().sum()` without first checking for nulls in the groupby key.

---

Source: https://www.openparable.com/skill/testing-quality/data-validation-first (OpenParable). Cite the canonical URL above.
