search-first

Guide teams to search existing tools and libraries before coding.

4|7|Updated Apr 9, 2026
One-click install
npx skills add https://github.com/arbisoft/ai-skillforge --skill search-first-arbisoft
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: search-first
Source: https://github.com/arbisoft/ai-skillforge/tree/main/Claude/skills/search-first
Command: npx skills add https://github.com/arbisoft/ai-skillforge --skill search-first-arbisoft

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Research-first workflow helps developers systematically search for existing tools, libraries, and patterns before writing custom code, reducing duplication and accelerating delivery.

Core Features & Use Cases

  • Guided five-step workflow: NEED ANALYSIS, PARALLEL SEARCH, EVALUATE, DECIDE, IMPLEMENT.
  • Parallel surface search across npm, MCP servers, GitHub, and web resources with a researcher agent.
  • Use cases include starting new features, adding dependencies, or integrating systems with confidence that existing solutions are leveraged.

Quick Start

Trigger the search-first skill at project planning; the system will perform NEED ANALYSIS and PARALLEL SEARCH to surface candidates before coding.

Frequently Asked Questions about search-first

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

FAQPage Schema
How do I search for existing libraries and patterns before writing custom code?

To search for existing libraries before coding, use a research-first workflow to perform parallel surface searches across npm, MCP servers, GitHub, and web resources, ensuring you evaluate and leverage existing tools rather than duplicating effort.

What is a research-first workflow for software development?

A research-first workflow is a repeatable, auditable five-step process—NEED ANALYSIS, PARALLEL SEARCH, EVALUATE, DECIDE, and IMPLEMENT—that guides teams to identify existing tools and patterns before starting feature development.

How do I reduce code duplication when adding new dependencies?

Reduce code duplication when adding dependencies by triggering a parallel search across npm and MCP servers to identify and evaluate existing libraries, ensuring you decide on an established solution before implementation.

Does a research-first approach work for system integration initiatives?

Yes, a research-first approach works for system integration initiatives by conducting need analysis and parallel searches to surface candidates across web resources and GitHub, allowing teams to integrate systems with confidence.

What's the best way to evaluate existing tools before starting feature development?

The best way to evaluate existing tools is to follow a structured workflow that analyzes needs, performs parallel searches, and evaluates surfaced candidates to ensure existing solutions are leveraged before implementation.