diet103/claude-code-infrastructure-showcase

Examples of my Claude Code infrastructure with skill auto-activation, hooks, and agents

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 5 minutes ago
Added to GitGenius on September 1st, 2026
Created on October 30th, 2025
Open Issues & Pull Requests: 18 (+0)
GitHub issues: Enabled
Number of forks: 1,230
Total Stargazers: 10,016 (+0)
Total Subscribers: 105 (+0)

Repository Insights (GitGenius)

Most active contributors

Sign in to see contributor activity.

Related repositories by overlapping contributors

No overlapping-contributor repos identified yet.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Issue API getrepoissuespagesummary failed: 429 Rate limit exceeded. Please try again later.

Detailed Description

Claude Code Infrastructure Showcase is a reference library of production-tested patterns for Claude Code that demonstrates skill auto-activation, hooks, and agents.

The project addresses the problem that Claude Code skills do not activate automatically by default, which becomes critical when managing complex projects where developers need consistent access to domain-specific guidance without manual intervention. The solution uses three core mechanisms: skills (markdown guides that Claude loads contextually), hooks (bash scripts that run automatically at key moments like every prompt or before edits), and a skill-rules.json configuration file that maps prompts and files to the skills they should trigger. The infrastructure also includes specialized agents for complex tasks and a dev docs system designed to persist across context resets.

This is explicitly a reference library rather than a working application, meant for copying patterns into your own projects. It suits teams managing TypeScript microservices or other complex codebases where consistent architectural guidance matters. The showcase includes examples using a generic blog domain and demonstrates both regex-based skill activation (the default, requiring no API calls) and optional AI-powered classification using an external provider for intent-based matching. Setup takes fifteen to thirty minutes via a wizard that detects your tech stack, validates configuration, and runs eight health checks to verify successful integration. The tool requires Node.js 18 or higher, a Unix-like environment (macOS, Linux, or WSL2), and optionally jq for certain features.

Development activity shows sustained iteration refined through six months of real-world use in production. The project includes a setup wizard that validates its own work through comprehensive health checks rather than assuming success. The infrastructure supports both classic regex-only operation and graceful degradation when optional AI classification is unavailable due to missing API keys or network issues. Documentation emphasizes key concepts upfront and provides multiple integration paths including a manual option and a Claude Code-assisted option for users who prefer not to use the terminal directly.