search-first

Research existing tools, libraries, and patterns before implementing custom code.

Updated May 9, 2026
One-click install
npx skills add https://github.com/kk20300113-png/my-claude-skills --skill search-first-kk20300113-png
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: search-first
Source: https://github.com/kk20300113-png/my-claude-skills/tree/main/search-first
Command: npx skills add https://github.com/kk20300113-png/my-claude-skills --skill search-first-kk20300113-png

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the wasted effort of writing custom code for problems that already have well-maintained existing solutions, reducing unnecessary development time and technical debt.

Core Features & Use Cases

  • Systematic Research Workflow: Guides you to search npm/PyPI, MCP servers, Claude skills, and GitHub open source projects before writing any custom code.
  • Structured Decision Matrix: Helps you choose between adopting an existing tool as-is, extending it with a thin wrapper, composing multiple small tools, or building a fully custom solution based on candidate evaluation scores.
  • Use Case: When you need to add dead link checking for markdown files, this Skill helps you find and adopt the existing textlint-rule-no-dead-link package instead of writing a custom link checker from scratch.

Quick Start

Use the search-first skill to research existing tools and libraries before writing custom code for the new data validation feature you are implementing.

Frequently Asked Questions about search-first

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

FAQPage Schema
How do I evaluate existing open source libraries before writing custom code?

To evaluate existing open source libraries before writing custom code, assess candidate solutions against functionality, maintenance status, community support, documentation quality, license compatibility, and dependency footprint. This structured evaluation helps select the optimal adoption, extension, composition, or custom build approach.

What's the best way to find existing tools for new software feature development?

The best way to find existing tools for new software feature development is to execute a systematic research workflow. Search npm, PyPI, MCP servers, Claude skills, and GitHub open source projects before writing any custom code to eliminate redundant development and reduce technical debt.

When should I build a custom solution instead of reusing an existing dependency?

You should build a custom solution instead of reusing an existing dependency when a structured decision matrix indicates that candidate solutions score too low in functionality, maintenance status, or license compatibility. This evaluation determines whether to adopt, extend, compose, or build from scratch.

Does this research workflow work for adding third-party integrations and utility creation?

Yes, this research workflow applies to software engineering tasks including third-party integration implementation and utility creation. It enforces the evaluation of existing tools, libraries, and patterns to prevent reinventing the wheel and accumulating unnecessary technical debt.

How do I decide between adopting a package as-is or extending it with a thin wrapper?

To decide between adopting a package as-is or extending it with a thin wrapper, use a structured decision matrix based on candidate evaluation scores. Compare functionality, dependency footprint, and license compatibility to select the optimal adoption, extension, composition, or custom build approach.

Why should I search for existing packages before implementing data validation features?

You should search for existing packages before implementing data validation features to avoid reinventing the wheel. Researching existing tools and libraries eliminates wasted effort, reduces unnecessary development time, and prevents the accumulation of technical debt from redundant custom code.