search-first

Search npm, PyPI, MCP servers, and GitHub for existing libraries before coding.

1|Updated Mar 5, 2026
One-click install
npx skills add https://github.com/beratcelik1/compound-claude --skill search-first-beratcelik1
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: search-first
Source: https://github.com/beratcelik1/compound-claude/tree/main/skills/search-first
Command: npx skills add https://github.com/beratcelik1/compound-claude --skill search-first-beratcelik1

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Prevents wasted effort by ensuring developers research existing libraries, MCP capabilities, and OSS patterns before writing new custom code, reducing duplication and dependency bloat.

Core Features & Use Cases

  • Parallel discovery: Searches npm, PyPI, internal MCP servers, and GitHub to surface existing implementations and packages.
  • Evaluation matrix: Scores candidates by functionality, maintenance, documentation, license, and dependency impact to recommend adopt/extend/compose/build actions.
  • Agent integration: Invokes a researcher agent for structured, repeatable research workflows when planning features or adding dependencies.
  • Use Case: When adding an HTTP client wrapper, run the skill to discover proven libraries, evaluate trade-offs, and produce an adoption plan that minimizes custom code.

Quick Start

Launch the researcher agent to compare npm, PyPI, MCP servers, and GitHub for existing implementations of the requested functionality and return a recommended action with reasoning.

Frequently Asked Questions about search-first

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

FAQPage Schema
How do I find existing libraries before writing custom code?

Evaluate existing libraries by scoring candidates on functionality, maintenance activity, documentation quality, license compatibility, and dependency impact to determine whether to adopt, extend, compose, or build a solution.

What is the best way to search npm and PyPI for dependency reuse?

The best way to search npm and PyPI for dependency reuse is running a parallel discovery process that queries both registries alongside internal MCP servers and GitHub to return a recommended adoption action with implementation notes.

When should I research existing packages instead of building from scratch?

Research existing packages when starting new features, adding dependencies, integrating services, or creating utilities where established open-source solutions may already exist, ensuring proven implementations are evaluated before custom code is written.

Can I evaluate GitHub repositories for maintenance and license compatibility?

Yes, you can evaluate GitHub repositories for maintenance and license compatibility by applying an evaluation matrix that scores candidates on functionality, documentation, maintenance activity, and dependency impact to recommend an adoption action.

Why do I need to check internal MCP servers before adding new dependencies?

Checking internal MCP servers before adding new dependencies prevents duplication and dependency bloat by discovering existing capabilities and OSS patterns already available within your internal infrastructure.