By agents-inc
Serverless GPU compute platform for AI model deployment — web endpoints, GPU functions, model serving, and TypeScript client patterns
The official skills marketplace for Agents Inc.
150+ skills covering everything from React and Prisma to Redis, ElevenLabs, and infrastructure tooling. Pick the skills that match your stack and install them via Claude Code. Need more control? The @agents-inc/cli lets you choose between plugin or eject mode, scoped to a single project or your entire machine.
Via Claude Code:
/plugin marketplace add agents-inc/skills
/plugin install <skill-name>@agents-inc
Via the Agents Inc CLI:
npx @agents-inc/cli init
Select your domains, skills and subagents, and configure everything in TypeScript. See the Agents Inc CLI.
Frameworks
React Vue Composition API Angular Standalone SolidJS Svelte
Meta Frameworks
Next.js Nuxt Remix Astro SvelteKit Qwik Docusaurus VitePress
State Management
Zustand Pinia NgRx SignalStore Jotai MobX Redux Toolkit
Data Fetching
SWR tRPC GraphQL + Apollo GraphQL + urql
Server State
React Query
Routing
React Router TanStack Router
Forms & Validation
React Hook Form TanStack Form Vee Validate Zod
UI Libraries
shadcn/ui Radix UI TanStack Table MUI Chakra UI Ant Design Mantine Headless UI Vuetify
Styling
Tailwind SCSS Modules CVA
Testing
Vitest Playwright Cypress React Testing Library Vue Test Utils
Mocks
MSW
Animation
Framer Motion CSS Animations View Transitions
Tooling
Storybook Vite
i18n
next-intl react-intl vue-i18n
Realtime
WebSockets Socket.IO SSE
PWA
Offline First Service Workers
Error Handling
Error Boundaries Result Types
Files
File Upload Patterns Image Handling
Performance & Accessibility
Web Performance Accessibility
Utilities
date-fns Native JS RxJS VueUse
Frameworks
Hono Express Fastify NestJS Elysia
Databases & ORMs
Drizzle Prisma TypeORM Sequelize Knex Mongoose MongoDB PostgreSQL MySQL Redis
CockroachDB EdgeDB SurrealDB Upstash Vercel KV Vercel Postgres
BaaS
Supabase Firebase Appwrite Neon PlanetScale Turso
Auth
Better Auth + Drizzle + Hono Clerk NextAuth
CMS
Payload Sanity Strapi
Commerce
Stripe
Email
Resend + React Email Resend Setup
Search
Elasticsearch Meilisearch
Vector DBs
Pinecone Qdrant Chroma Weaviate
Analytics
PostHog Analytics PostHog Setup
Feature Flags
PostHog Flags
Observability
Axiom + Pino + Sentry Axiom + Pino + Sentry Setup
Performance
API Performance
Providers
Anthropic SDK OpenAI SDK Google Gemini SDK Mistral SDK Cohere SDK ElevenLabs OpenAI Whisper Claude Vision
Orchestration
Vercel AI SDK LangChain LlamaIndex
Infrastructure
HuggingFace Inference LiteLLM Modal Ollama Replicate Together AI
Observability
Langfuse Promptfoo
Patterns
Tool Use Patterns
CI/CD
GitHub Actions Docker
Platform
Cloudflare Workers
Config
Env Config
Monorepos
Turborepo Nx pnpm Workspaces
Security
Auth Security
Tooling
Biome ESLint + Prettier Git Hooks TypeScript Config
Frameworks
Electron Tauri
Design
Expressive TypeScript
Reviewing
Code Reviewing CLI Reviewing
Methodology
Research Methodology
Each skill covers patterns, conventions, anti-patterns, edge cases, and real code examples for a single technology. Not surface-level docs, but the kind of knowledge you'd normally have to explain to Claude repeatedly.
src/skills/<domain>-<subcategory>-<name>/
├── SKILL.md # Main skill content
├── metadata.yaml # Version, compatibility, tags
├── reference.md # API reference
└── examples/
├── core.md # Core usage examples
└── {topic}.md # Topic-specific examples
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub agents-inc/skills --plugin ai-infrastructure-modalXquik REST API patterns for X post search, user and timeline reads, cursor pagination, media downloads, monitors, signed webhooks, and approval-gated X actions
Pino logging, Sentry error tracking, Axiom - structured logging with correlation IDs, error boundaries, performance monitoring, alerting
Clerk managed authentication - ClerkProvider, middleware, pre-built components, hooks, server-side auth, organizations, webhooks
PostHog analytics and feature flags setup
CLI code review patterns. Use when reviewing CLI applications built with Commander.js, @clack/prompts, picocolors. Covers exit codes, signal handling, error messages, user experience, testing adequacy.
Expert Modal.com serverless cloud platform system with comprehensive Modal 1.0 SDK (May 2025) features, GPU functions (T4/L4/A10G/L40S/A100/H100/H200/B200), autoscaler configuration, @modal.concurrent/@modal.batched decorators, Sandboxes for isolated code execution, CloudBucketMount for S3/GCS, and production deployment patterns. PROACTIVELY activate for: (1) ANY Modal.com task, (2) GPU configuration with fallbacks and multi-GPU, (3) Autoscaler settings (min/max/buffer containers, scaledown_window), (4) Web endpoints (FastAPI, ASGI, WSGI, custom servers), (5) @modal.concurrent for request concurrency, (6) @modal.batched for dynamic batching, (7) Sandboxes for untrusted code execution, (8) Scheduling (Cron with timezone, Period), (9) Storage (Volumes with commit(), Dict with TTL, Queue, CloudBucketMount), (10) Parallel processing (.map(), .starmap(), .spawn(), .for_each()), (11) Container lifecycle (@modal.enter, @modal.method, @modal.exit), (12) Image building (uv_pip_install, run_function for model downloads), (13) Secrets and environment management, (14) Deployment and CI/CD with GitHub Actions, (15) Cost optimization and 2025 pricing. Provides: Modal 1.0 stable API patterns, GPU selection guide with per-second pricing, autoscaler tuning strategies, concurrency and batching for ML inference, Sandbox security patterns, CloudBucketMount for external data, complete CLI reference, debugging workflows, and production-ready configurations.
Cloudflare Workers AI for serverless GPU inference. Use for LLMs, text/image generation, embeddings, or encountering AI_ERROR, rate limits, token exceeded errors.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
This skill should be used when users need to generate ideas, explore creative solutions, or systematically brainstorm approaches to problems. Use when users request help with ideation, content planning, product features, marketing campaigns, strategic planning, creative writing, or any task requiring structured idea generation. The skill provides 30+ research-validated prompt patterns across 14 categories with exact templates, success metrics, and domain-specific applications.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.