rajib2k5

Dq — Data skill for Claude Code

Data community

Hunt silent data failures — grain/fan-out, freshness, reconciliation, absence-vs-zero, broken SCDs.

How to install Dq

Installs to ~/.claude/skills/rajib2k5-claude-staff-kit-dq/SKILL.md

Terminal

mkdir -p ~/.claude/skills/rajib2k5-claude-staff-kit-dq && curl -fsSL https://raw.githubusercontent.com/rajib2k5/claude-staff-kit/HEAD/commands/dq.md -o ~/.claude/skills/rajib2k5-claude-staff-kit-dq/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Dq does

description: Hunt silent data failures — grain/fan-out, freshness, reconciliation, absence-vs-zero, broken SCDs argument-hint: [table, model, or the number that looks wrong]

Invoke the `data-quality` skill.

Target: $ARGUMENTS

Run all seven checks, in order — starting with the grain check, because fan-out is the most damaging and presents as good news:

`SELECT , COUNT(*) FROM GROUP BY HAVING COUNT(*) > 1` must return zero rows.

Two traps to handle explicitly:

**Do not

Alternatives in Data

A Stock Data — A股全栈数据工具包 · 十一层架构 · 54端点 · 19数据源 · 零鉴权 Full-stack China A-share data toolkit for AI agents — 11 layers, 54 end 9.4k ★
Build Failure — Diagnose elasticsearch-js CI and local build failures 5.3k ★
Global Stock Data — US stock market data for AI coding assistants — zero-auth, official sources 1.5k ★