80,000+ Skills to Supercharge Claude
The open directory for GitHub-integrated capabilities, tools, and prompts for your AI workflows.
task-external-models
by MadAppGang
Quick-reference for using external AI models with Task tool. CRITICAL - PROXY_MODE is NOT a Task parameter - it goes in...
technical-audit
by MadAppGang
Technical SEO audit methodology including crawlability, indexability, and Core Web Vitals analysis. Use when auditing pa...
patterns
by MadAppGang
Common agent patterns and templates for Claude Code. Use when implementing agents to follow proven patterns for proxy mo...
campaign-metrics
by MadAppGang
Cold email campaign KPIs, benchmarks, and diagnostic patterns
claudemem-orchestration
by MadAppGang
Use when orchestrating multi-agent code analysis with claudemem. Run claudemem once, share output across parallel agents...
final-cut-pro
by MadAppGang
Apple Final Cut Pro FCPXML format reference. Covers project structure, timeline creation, clip references, effects, and...
ui-design-review
by MadAppGang
Prompting patterns and review templates for UI design analysis with Gemini multimodal capabilities. Use when conducting...
multi-model-validation
by MadAppGang
Run multiple AI models in parallel for 3-5x speedup with ENFORCED performance statistics tracking. Use when validating w...
proof-of-work
by MadAppGang
Proof artifact generation patterns for task validation. Covers screenshots, test results, deployments, and confidence sc...
linear-integration
by MadAppGang
Linear API patterns and examples for autopilot. Includes authentication, webhooks, issue CRUD, state transitions, file a...
openrouter-trending-model...
by MadAppGang
Fetch trending programming models from OpenRouter rankings. Use when selecting models for multi-model review, updating m...
todowrite-orchestration
by MadAppGang
Track progress in multi-phase workflows with TodoWrite. Use when orchestrating 5+ phase commands, managing iteration loo...
developer-detective
by MadAppGang
⚡ Implementation analysis skill. Best for: 'how does X work', 'find implementation of', 'trace data flow', 'where is X...
shadcn-ui
by MadAppGang
shadcn/ui component library patterns. Covers CLI usage, installation, component categories, theming with CSS variables,...
release
by MadAppGang
Plugin release process for MAG Claude Plugins marketplace. Covers version bumping, marketplace.json updates, git tagging...
ultrathink-detective
by MadAppGang
⚡ Comprehensive analysis skill. Best for: 'comprehensive audit', 'deep analysis', 'full codebase review', 'multi-perspe...
multi-agent-coordination
by MadAppGang
Coordinate multiple agents in parallel or sequential workflows. Use when running agents simultaneously, delegating to su...
schemas
by MadAppGang
YAML frontmatter schemas for Claude Code agents and commands. Use when creating or validating agent/command files.
proxy-mode-reference
by MadAppGang
Reference guide for using PROXY_MODE with external AI models. Use when running multi-model reviews, understanding which...
sequence-best-practices
by MadAppGang
Email sequence design and optimization best practices
performance-security
by MadAppGang
Use when optimizing performance or reviewing security. Covers code-splitting, React Compiler patterns, asset optimizatio...
debug-mode
by MadAppGang
Enable, disable, and manage debug mode for agentdev sessions. Records all tool invocations, skill activations, hook trig...
model-tracking-protocol
by MadAppGang
MANDATORY tracking protocol for multi-model validation. Creates structured tracking tables BEFORE launching models, trac...
ab-testing-patterns
by MadAppGang
A/B testing methodology for cold email optimization