Skill

search-first

Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Reduces wrong-approach friction.

Install

npx claudepluginhub arosenkranz/claude-code-config --plugin workflow-skills

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Systematizes the "search for existing solutions before implementing" workflow. Directly addresses the #1 friction pattern: picking the wrong tool/approach on the first attempt.

SKILL.md

Similar Skills

agent-eval

Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.

everything-claude-code

157.7k

agent-harness-construction

Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.

everything-claude-code

157.7k

accessibility

Designs, implements, and audits WCAG 2.2 AA accessible UIs for Web (ARIA/HTML5), iOS (SwiftUI traits), and Android (Compose semantics). Audits code for compliance gaps.

everything-claude-code

157.7k

Stats

Parent Repo Stars1

Parent Repo Forks0

Last CommitApr 6, 2026

Actions

View Source View Plugin View on GitHub View README

/search-first — Research Before You Code

Systematizes the "search for existing solutions before implementing" workflow. Directly addresses the #1 friction pattern: picking the wrong tool/approach on the first attempt.

Trigger

Use this skill when:

Starting a new feature that likely has existing solutions
Adding a dependency or integration
The user asks "add X functionality" and you're about to write code
Before creating a new utility, helper, or abstraction

Workflow

1. NEED ANALYSIS
   Define what functionality is needed
   Identify language/framework constraints
   Check deployment target (Cloudflare Workers? Homelab Docker?)

2. PARALLEL SEARCH
   - Does this already exist in the repo? → rg through modules/tests
   - npm / PyPI for packages
   - MCP servers available (check settings.json)
   - Existing skills in ~/.claude/skills/
   - GitHub code search for maintained OSS

3. EVALUATE
   Score candidates: functionality, maintenance, community,
   docs, license, dependency footprint

4. DECIDE
   - Exact match, well-maintained → ADOPT as-is
   - Partial match, good foundation → EXTEND with thin wrapper
   - Multiple weak matches → COMPOSE 2-3 small packages
   - Nothing suitable → BUILD custom, informed by research

5. IMPLEMENT
   Install package / Configure MCP / Write minimal custom code

Platform Constraints Check

Before recommending any package, verify compatibility:

Target	Constraints
Cloudflare Workers	No Node.js APIs, ESM only, Web Platform APIs only
Raspberry Pi 5 / Docker	ARM64 compatible, low memory footprint
Browser / Client	Bundle size matters, tree-shakeable preferred

Quick Mode (inline)

Before writing a utility, run through:

Does this already exist in the repo?
Is this a common problem? → Search npm/PyPI
Is there an MCP server for it? → Check ~/.claude/settings.json
Is there a skill for it? → Check ~/.claude/skills/
Is there a maintained GitHub implementation?

Full Mode (agent)

For non-trivial functionality, launch a research agent:

Agent(subagent_type="Explore", prompt="
  Research existing tools for: [DESCRIPTION]
  Language/framework: [LANG]
  Deploy target: [Cloudflare Workers / Docker / Local]
  Return: Top 3 candidates with pros/cons
")

Anti-Patterns

Jumping to code: Writing a utility without checking if one exists
Ignoring MCP: Not checking if an MCP server already provides the capability
Over-customizing: Wrapping a library so heavily it loses its benefits
Dependency bloat: Installing a massive package for one small feature
Wrong platform: Installing a Node.js-only package for a Cloudflare Workers project