data-first

Define data requirements, gather sources, and validate quality before analysis.

1|Updated Jan 23, 2026
One-click install
npx skills add https://github.com/bobby-andris/Allied-FeedOps --skill data-first
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-first
Source: https://github.com/bobby-andris/Allied-FeedOps/tree/main/.claude/skills/data-first
Command: npx skills add https://github.com/bobby-andris/Allied-FeedOps --skill data-first

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Gather and verify real data before any analysis or planning to prevent fabricated examples and assumptions. If data is unavailable, explicitly state assumptions and obtain user approval before proceeding.

Core Features & Use Cases

  • Define data requirements for a task, including sources, schema, filters, and expected volume.
  • Gather, save, and validate data quality across sources before proceeding to analysis.
  • Use cases include research planning, performance reviews, market analysis, and audits that require factual data.

Quick Start

Outline data requirements and initiate a verified data collection workflow before analysis.

Frequently Asked Questions about data-first

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I verify data quality before starting data analytics or planning?

To verify data quality before data analytics, you must define data requirements including sources, schema, and filters. You then gather real results, validate them across sources, and document any gaps before proceeding with analysis.

What is the best way to define data requirements for research planning?

The best way to define data requirements for research planning is to explicitly identify necessary sources, expected volume, and filters. This ensures you collect factual data and prevent fabricated examples before analysis begins.

How do I proceed with market analysis when real data sources are unavailable?

When real data sources are unavailable for market analysis, you must explicitly state your assumptions and obtain user approval. You then proceed using clearly labeled assumptions rather than fabricated examples.

Can I use automated data gathering for performance reviews without manual validation?

No, automated data gathering for performance reviews requires validation. You must validate data quality across all sources, confirm data access, and document any gaps to ensure the review is based on verified data.

Why does data collection fail during audits that require factual data?

Data collection fails during audits when data access is unconfirmed or schema requirements are undefined. Successful audits require defining data requirements upfront, validating quality across sources, and documenting any existing gaps.