skills.rest
ibytechaos
ibytechaosCOMMUNITY
Explore all skills by this author →
GitHub

search-first

Searches npm, PyPI, MCP servers, and GitHub for existing solutions before writing custom code.

1|Updated Oct 11, 2025
Search Tags:#npm#code reuse#pypi#dependency research#github search#mcp servers#library evaluation
One-click install
npx skills add https://github.com/ibytechaos/claude --skill search-first-ibytechaos
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: search-first
Source: https://github.com/ibytechaos/claude/tree/main/plugins/everything-claude-code/skills/search-first
Command: npx skills add https://github.com/ibytechaos/claude --skill search-first-ibytechaos

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Developers often reinvent the wheel by writing custom utilities and integrations without checking whether maintained libraries, MCP servers, or existing skills already solve the problem, leading to unnecessary code and dependency bloat. ## Core Features & Use Cases - Structured Research Workflow: Runs a five-stage pipeline covering need analysis, parallel search across npm/PyPI, MCP servers, and GitHub, candidate evaluation, and an adopt/extend/build decision. - Decision Matrix: Scores candidates on functionality, maintenance, community, documentation, license, and dependencies to choose between adopting, extending, composing, or building custom. - Use Case: Before adding dead-link checking to a docs site, the skill finds textlint-rule-no-dead-link on npm and recommends adopting it directly instead of writing a custom checker. ## Quick Start Ask the assistant to research existing tools and libraries for the functionality you are about to implement before writing any code.

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?▼

Search npm or PyPI for packages matching your need, check for MCP servers and existing skills, then run GitHub code search for maintained open-source implementations. Score candidates on functionality, maintenance, and license before deciding to adopt, extend, or build.

When should I adopt a library versus building a custom solution?▼

Adopt when an exact match is well-maintained with a permissive license like MIT or Apache. Extend when a partial match provides a good foundation, and build custom only when no suitable option exists after research.

How do I check if an MCP server already provides a capability?▼

Inspect ~/.claude/settings.json for configured MCP servers and search available MCP integrations before writing integration code. The workflow treats MCP discovery as a parallel search track alongside npm and PyPI.

What are the risks of skipping dependency research?▼

Skipping research leads to reinventing existing utilities, ignoring MCP capabilities, over-wrapping libraries until they lose their benefits, and installing bloated packages for small features. A quick search pass prevents these anti-patterns.

Can this workflow integrate with planning and architecture agents?▼

Yes, the planner agent invokes research before architecture review so plans incorporate existing tools, and the architect consults research for technology stack decisions and integration pattern discovery.

Related Skills

Explore More Software Engineering Skills→
0xMuluh0xMuluh
1

reuse-before-implementing

Evaluates existing language, package, and ecosystem capabilities before implementing new code or dependencies.

Community
Intermediate
kasperjungekasperjunge
450

create-plan

Create implementation plans with milestones, tasks, and success criteria.

Community
Advanced
ZESCODEZESCODE

search-first

Search package registries and MCP servers before writing custom code.

Community
Intermediate
FerroxLabsFerroxLabs
21

ferrox-fast

Apply trivial low-risk code changes directly without planning.

Community
Basic