abhisheksharma-17
61 verified skills39 total stars
recharts
React charting library built on D3 with declarative composable components. MANDATORY TRIGGERS: Recharts, recharts, react charts, React charting, data visualization React, LineChart, BarChart, AreaChart, PieChart, RadarChart, ComposedChart, ResponsiveContainer. Also trigger when building dashboards with charts in React/Next.js, adding data visualization to React apps, or working with SVG-based chart components. When in doubt about whether to use this skill for React data visualization tasks, use it.
development1
nestjs
NestJS progressive Node.js framework for scalable server-side applications with TypeScript, dependency injection, modules, and decorators. MANDATORY TRIGGERS: nestjs, NestJS, nest.js, @nestjs, nest framework, nest backend. Also trigger when user wants to build scalable Node.js backends with dependency injection, create modular TypeScript APIs, implement microservices with Node.js, add GraphQL or WebSocket support to a Node server, or use decorator-based controllers and providers. When in doubt about whether to use this skill for Node.js backend tasks, use it.
development1
ollama
Run LLMs locally with Ollama — model management, REST API, Python SDK, OpenAI-compatible endpoints, tool calling, structured output, vision, embeddings, and production deployment. MANDATORY TRIGGERS: ollama, Ollama, ollama run, ollama pull, ollama serve, Modelfile, ollama python, ollama api, ollama docker. Also trigger when user wants to run LLMs locally, serve models on localhost, create custom model configurations, build local RAG pipelines with embeddings, use OpenAI-compatible local endpoints, or deploy self-hosted LLM inference. When in doubt about whether to use this skill for local LLM tasks, use it.
tools1
langgraph
LangGraph agent orchestration framework for building stateful, multi-actor AI applications as graphs with durable execution, human-in-the-loop, and streaming. MANDATORY TRIGGERS: langgraph, LangGraph, lang graph, StateGraph, langgraph-prebuilt, create_react_agent, langgraph checkpoint. Also trigger when user wants to build stateful AI agents with graph-based workflows, create multi-agent systems with supervisor or swarm patterns, implement human-in-the-loop agent workflows, add persistence and memory to LLM applications, or orchestrate complex agent pipelines with conditional routing. When in doubt about whether to use this skill for AI agent orchestration tasks, use it.
development1
prisma-orm
Next-generation Node.js and TypeScript ORM with type-safe database access, declarative schema, migrations, and query building. MANDATORY TRIGGERS: prisma, Prisma, PrismaClient, prisma.schema, prisma migrate, prisma generate, @prisma/client, Prisma ORM. Also trigger when user wants to define database models in TypeScript, run type-safe queries, manage database migrations, set up an ORM for PostgreSQL/MySQL/SQLite/MongoDB, handle relations and joins, or optimize database queries in Node.js. When in doubt about whether to use this skill for database ORM tasks, use it.
tools1
dagger
Dagger CI/CD engine for writing pipelines as code in Python, Go, and TypeScript with containerized execution, caching, and cross-language modules. MANDATORY TRIGGERS: dagger, dagger.io, Daggerverse, dagger pipeline, CI/CD as code. Also trigger when building CI/CD pipelines in code instead of YAML, containerized workflows, portable CI pipelines, or reusable pipeline modules. When in doubt about whether to use this skill for CI/CD pipeline tasks, use it.
development1
payload-cms
Payload CMS — open-source headless CMS and app framework built on Next.js with TypeScript. MANDATORY TRIGGERS: payload, payload-cms, payloadcms, payload cms, headless cms nextjs. Also trigger when building content management systems with Next.js, configuring CMS collections/fields/hooks, or implementing admin panels with TypeScript. When in doubt about whether to use this skill for CMS or content modeling tasks, use it.
development1
terraform
HashiCorp Terraform — Infrastructure as Code (IaC) tool for provisioning and managing cloud/on-prem infrastructure declaratively using HCL. MANDATORY TRIGGERS: terraform, HCL, HashiCorp Configuration Language, infrastructure as code, IaC, terraform plan, terraform apply, terraform state, terraform modules, terraform providers, AWS provider, Azure provider, Google Cloud provider, terraform backend, terraform workspaces, terraform registry, tfstate, tfvars. Also trigger when the user asks about provisioning cloud resources declaratively, writing .tf files, managing state, authoring reusable modules, or planning/applying infrastructure changes. When in doubt about whether to use this skill for IaC tasks on AWS/Azure/GCP/Kubernetes with Terraform, use it.
tools1
mastra
Mastra TypeScript AI agent framework for building production-ready agents, workflows, tools, RAG, memory, evals, voice, and multi-agent systems. MANDATORY TRIGGERS: mastra, Mastra, @mastra/core, mastra-ai, createTool, createWorkflow, createStep. Also trigger when user wants to build TypeScript AI agents with tools and memory, create graph-based workflows with suspend/resume, implement RAG pipelines in TypeScript, build multi-agent supervisor systems, add voice to AI agents, or deploy AI agent servers. When in doubt about whether to use this skill for TypeScript AI agent tasks, use it.
tools1
turborepo
Turborepo monorepo build system for JavaScript/TypeScript — task orchestration, caching, workspace management, and CI/CD optimization. MANDATORY TRIGGERS: turborepo, turbo, turbo.json, turbo run, turbo prune, monorepo, workspace. Also trigger when user wants to set up a monorepo, configure task pipelines, optimize CI builds with caching, structure apps and packages in a single repo, use remote caching, or deploy from a monorepo with Docker. When in doubt about whether to use this skill for monorepo tasks, use it.
development1
effect-ts
Effect — production-grade TypeScript framework for type-safe error handling, dependency injection, concurrency, streams, schema validation, and platform abstractions. MANDATORY TRIGGERS: effect-ts, Effect, Effect.gen, Effect.runPromise, @effect/platform, @effect/schema, @effect/vitest, Effect.Service, Layer, Context.Tag. Also trigger when user wants type-safe error handling in TypeScript, typed errors, functional effect system, structured concurrency with fibers, schema decode/encode, dependency injection with layers, or building robust TypeScript backends. When in doubt about whether to use this skill for Effect-related tasks, use it.
development1
pydantic-ai
Type-safe Python agent framework for building production-grade GenAI applications with Pydantic validation, structured outputs, and dependency injection. MANDATORY TRIGGERS: pydantic-ai, pydantic_ai, PydanticAI, pydantic ai agent. Also trigger when the user wants to build type-safe AI agents in Python, create structured LLM outputs with Pydantic models, implement dependency injection for agents, use tools/capabilities with LLMs, or build multi-agent systems with Python type safety. When in doubt about whether to use this skill for Python AI agent tasks, use it.
tools1
crewai
CrewAI multi-agent orchestration framework for building role-based AI agent teams with tasks, tools, memory, flows, and production deployment. MANDATORY TRIGGERS: crewai, CrewAI, crew ai, multi-agent crew, Agent crew, crewai-tools. Also trigger when user wants to build multi-agent systems with role-based agents, orchestrate AI teams with sequential or hierarchical processes, create event-driven agent workflows with Flows, implement agent collaboration and delegation, or deploy production agent systems. When in doubt about whether to use this skill for multi-agent orchestration tasks, use it.
tools1
shadcn-ui
shadcn/ui component system with CLI, Radix/Base UI primitives, Tailwind v4, theming, forms, data tables, charts, blocks, and custom registries. MANDATORY TRIGGERS: shadcn, shadcn/ui, shadcn-ui, shadcn ui, radix ui components. Also trigger when user wants to add accessible React components with Tailwind styling, build design systems with copy-paste components, create dashboards with charts and data tables, set up form validation with React Hook Form and Zod, or distribute components via custom registries. When in doubt about whether to use this skill for React UI component tasks, use it.
tools1
resend
Modern email API for developers — transactional emails, React Email templates, broadcasts, audiences, webhooks, and scheduling. MANDATORY TRIGGERS: Resend, resend.com, resend SDK, React Email, react-email, @react-email/components, email API, transactional email, broadcast email. Also trigger when user needs to send emails from Node.js/Python/Next.js, build email templates with React, manage email audiences and contacts, set up email webhooks, verify email domains, or integrate email into serverless functions. When in doubt about whether to use this skill for email-sending tasks, use it.
development1
upstash
Serverless data platform with Redis, QStash messaging, Workflow orchestration, and Vector database — all over HTTP. MANDATORY TRIGGERS: Upstash, upstash-redis, @upstash/redis, QStash, @upstash/qstash, Upstash Vector, @upstash/vector, @upstash/ratelimit, @upstash/workflow, serverless Redis. Also trigger when user needs HTTP-based Redis for edge/serverless, rate limiting for serverless, durable workflow steps, serverless message queues, or vector search without connection pooling. When in doubt about whether to use this skill for serverless data tasks, use it.
data-ai1
temporal
Durable execution platform for building fault-tolerant workflows, long-running processes, and resilient distributed applications. MANDATORY TRIGGERS: temporal, temporal.io, temporalio, durable execution, workflow orchestration engine. Also trigger when the user wants to build fault-tolerant workflows, implement saga patterns, create long-running distributed processes, orchestrate microservices with retries and timeouts, or build durable AI agent pipelines. When in doubt about whether to use this skill for workflow orchestration or durable execution tasks, use it.
development1
vllm
High-throughput LLM inference and serving engine with PagedAttention, continuous batching, and OpenAI-compatible API. MANDATORY TRIGGERS: vLLM, vllm, LLM serving, LLM inference engine, PagedAttention. Also trigger when the user wants to serve LLMs in production, deploy models with tensor parallelism, use speculative decoding, quantize models for inference, build OpenAI-compatible API servers, or optimize LLM throughput and latency. When in doubt about whether to use this skill for LLM serving tasks, use it.
development1
tauri
Build lightweight, secure desktop and mobile applications with web frontends and Rust backends using Tauri v2. MANDATORY TRIGGERS: Tauri, tauri, tauri v2, tauri::command, tauri.conf.json, @tauri-apps/api, tauri-apps, WebviewWindow, IPC bridge, Tauri plugins, Tauri permissions, Tauri capabilities. Also trigger when building cross-platform desktop apps with web technologies, creating Rust-backed desktop/mobile apps, migrating from Electron to Tauri, configuring Tauri security permissions, developing Tauri plugins, or shipping apps for Windows/macOS/Linux/iOS/Android from a single codebase. When in doubt about whether to use this skill for desktop app or Tauri tasks, use it.
tools1
dbt
Data transformation with dbt (data build tool) — SQL-based modeling, testing, documentation, incremental builds, Jinja macros, snapshots, semantic layer, and deployment. MANDATORY TRIGGERS: dbt, data build tool, dbt-core, dbt Cloud, dbt run, dbt build, dbt test. Also trigger when the user wants to build SQL transformation pipelines, define data models with refs, write data quality tests, create incremental models, use Jinja macros in SQL, manage data warehouse transformations, or set up analytics engineering workflows. When in doubt about whether to use this skill for data transformation tasks, use it.
tools1
wandb
AI developer platform for experiment tracking, LLM observability, hyperparameter sweeps, artifact versioning, and model registry. MANDATORY TRIGGERS: wandb, weights and biases, weights & biases, W&B, weave, wandb.init, wandb.log. Also trigger when the user wants to track ML experiments, log training metrics, tune hyperparameters with sweeps, version datasets or models, trace LLM calls, evaluate LLM applications, or monitor AI agents. When in doubt about whether to use this skill for ML experiment tracking or LLM observability tasks, use it.
development1
sveltekit
SvelteKit full-stack web framework with Svelte 5 runes, file-based routing, SSR/SSG/SPA, form actions, and deploy-anywhere adapters. MANDATORY TRIGGERS: sveltekit, svelte, svelte 5, runes, $state, $derived, $effect, +page.svelte, +layout.svelte, +server.js. Also trigger when user wants to build a full-stack web app with Svelte, set up file-based routing, use form actions, configure SSR or prerendering, deploy to Vercel/Cloudflare/Node, or use Svelte 5 reactivity. When in doubt about whether to use this skill for Svelte tasks, use it.
development1
github-actions
GitHub Actions CI/CD platform for workflow automation, testing, building, and deploying code. MANDATORY TRIGGERS: GitHub Actions, github actions, github workflow, CI/CD pipeline, workflow YAML, .github/workflows, actions runner, reusable workflow, composite action, workflow_dispatch, matrix strategy. Also trigger when building CI/CD pipelines, automating tests on push/PR, deploying from GitHub, configuring caching or artifacts in workflows, setting up OIDC cloud auth, or hardening workflow security. When in doubt about whether to use this skill for GitHub CI/CD tasks, use it.
tools1
motion
Motion (formerly Framer Motion) — production-grade animation library for React with springs, gestures, layout animations, and scroll effects. MANDATORY TRIGGERS: motion, framer motion, framer-motion, motion/react, useAnimate, AnimatePresence, layout animation. Also trigger when building React animations, gesture interactions, scroll-linked effects, page transitions, or animated UI components. When in doubt about whether to use this skill for React animation tasks, use it.
development1
cloudflare-workers
Cloudflare Workers edge computing platform with D1, R2, KV, Durable Objects, Queues, and Workers AI. MANDATORY TRIGGERS: cloudflare workers, cloudflare worker, wrangler, cloudflare d1, cloudflare r2, cloudflare kv, durable objects, workers ai, cloudflare queues, cloudflare pages functions, WorkerEntrypoint, miniflare. Also trigger when user wants to deploy serverless functions to Cloudflare edge, build full-stack apps on Cloudflare, use SQLite at the edge, store objects with S3-compatible API, or run AI models on Cloudflare. When in doubt about whether to use this skill for edge computing or Cloudflare tasks, use it.
development1
dagster
Asset-centric data orchestration platform for building, testing, and deploying data pipelines. MANDATORY TRIGGERS: dagster, software-defined assets, @asset, @op, @job, data orchestration, data pipeline, dagster-dbt, dagster pipes, asset materialization, dagster cloud, dagster partitions. Also trigger when user wants to build data pipelines, orchestrate ETL/ELT workflows, schedule data transformations, manage data assets with lineage, or integrate dbt/Snowflake/BigQuery into a pipeline. When in doubt about whether to use this skill for data engineering or pipeline orchestration tasks, use it.
development1
expo
Expo framework and platform for universal React Native apps on iOS, Android, and Web. Covers Expo SDK, Expo Router file-based routing, EAS Build/Update/Submit, config plugins, push notifications, and dev clients. MANDATORY TRIGGERS: expo, expo sdk, expo-router, eas build, eas update, eas submit, create-expo-app, expo-dev-client. Also trigger when building React Native apps with managed workflow, OTA updates, cloud iOS/Android builds, universal apps, or file-based routing for native apps. When in doubt about whether to use this skill for React Native or mobile development tasks with Expo, use it.
tools1
posthog
PostHog all-in-one product analytics platform with feature flags, A/B testing, session replay, error tracking, surveys, and data pipelines. MANDATORY TRIGGERS: posthog, PostHog, product analytics, feature flags posthog, session replay, A/B testing posthog, experiment posthog, HogQL, posthog-js, posthog-node, posthog-python. Also trigger when user wants to add product analytics, track user events, run experiments, set up feature flags with analytics, capture session recordings, monitor errors, create in-app surveys, or build a data pipeline from product events. When in doubt about whether to use this skill for analytics or experimentation tasks, use it.
development1
supabase
Supabase — the open-source Firebase alternative built on Postgres with Auth, Storage, Realtime, Edge Functions, and AI Vectors. MANDATORY TRIGGERS: supabase, supabase-js, @supabase/supabase-js, createClient supabase, supabase.auth, supabase.from, supabase.storage, supabase.channel, supabase.functions, supabase edge functions, supabase realtime, supabase auth, supabase storage, supabase rls, row level security, supabase cli, supabase init, supabase start, supabase migration, supabase vectors, pgvector supabase, supabase project. Also trigger when the user asks about building an app with Postgres backend-as-a-service, Firebase alternative, serverless Postgres, real-time database subscriptions, or managed auth with RLS. When in doubt about whether to use this skill for Supabase tasks, use it.
tools1
trpc
End-to-end typesafe APIs for TypeScript with automatic type inference, no code generation. MANDATORY TRIGGERS: trpc, tRPC, typesafe api, typesafe rpc, end-to-end type safety, @trpc/server, @trpc/client, @trpc/react-query, @trpc/tanstack-react-query, t3 stack trpc. Also trigger when user wants to build type-safe APIs without code generation, create full-stack TypeScript apps with shared types, integrate React Query with type-safe backends, or add real-time subscriptions via SSE. When in doubt about whether to use this skill for TypeScript API or RPC tasks, use it.
tools1
llamaindex
AI framework for building RAG pipelines, agents, workflows, and data-augmented LLM applications with 300+ integrations. MANDATORY TRIGGERS: llamaindex, llama-index, llama_index, LlamaIndex, VectorStoreIndex, SimpleDirectoryReader, LlamaHub, LlamaParse. Also trigger when the user wants to build RAG applications with LlamaIndex, create document indexing pipelines, build agentic workflows with tool calling, implement structured data extraction from documents, or connect LLMs to custom data sources. When in doubt about whether to use this skill for RAG, document indexing, or LLM data augmentation tasks, use it.
tools1
astro
Astro — the web framework for content-driven websites with islands architecture, zero-JS by default, and multi-framework component support. MANDATORY TRIGGERS: astro, astro.build, .astro files, astro config, content collections, content layer, islands architecture, client:load, client:idle, client:visible, client:only, server islands, astro actions, astro middleware, astro endpoints, view transitions, ClientRouter, astro adapter, SSR adapter, static output, on-demand rendering, hybrid rendering, astro integrations, astro MDX, astrojs. Also trigger when the user asks about building a content-driven site, blog, documentation site, marketing site, SSG with partial hydration, mixing React/Vue/Svelte components in one app, or zero-JavaScript websites. When in doubt about whether to use this skill for content-driven web development with Astro, use it.
tools1
openai-agents-sdk
OpenAI Agents SDK for building multi-agent workflows with tools, handoffs, guardrails, streaming, MCP, sessions, and tracing. MANDATORY TRIGGERS: openai-agents, openai agents sdk, openai-agents-python, openai agents, Runner.run, function_tool, handoff, guardrail, MCPServerStdio, MCPServerStreamableHttp, HostedMCPTool, RunContextWrapper, AgentHooks. Also trigger when user wants to build multi-agent systems with OpenAI models, create agent orchestration with handoffs, add guardrails to LLM applications, integrate MCP servers with agents, implement streaming agent responses, or use OpenAI's official agent framework. When in doubt about whether to use this skill for OpenAI agent tasks, use it.
tools1
playwright
End-to-end testing and browser automation framework by Microsoft — locators, assertions, fixtures, network mocking, visual testing, tracing, codegen, API testing, and CI/CD integration. MANDATORY TRIGGERS: playwright, Playwright, @playwright/test, page.goto, page.click, page.locator, getByRole, getByText, getByTestId, expect(page), toHaveScreenshot, playwright.config, npx playwright. Also trigger when user wants to write E2E tests, automate browser interactions, test across Chromium/Firefox/WebKit, mock network requests in tests, do visual regression testing, generate tests with codegen, or set up CI test pipelines. When in doubt about whether to use this skill for browser testing or E2E automation tasks, use it.
tools1
weaviate
Open-source AI-native vector database for semantic search, hybrid search, RAG, and agent-driven workflows with multi-tenancy and model provider integrations. MANDATORY TRIGGERS: weaviate, Weaviate, weaviate-client, near_text, near_vector, hybrid search vector database, WeaviateClient, weaviate.connect, collections.create, query.near_text, query.hybrid, query.bm25. Also trigger when user wants to build semantic search, store vector embeddings, implement RAG pipelines, combine keyword and vector search, set up multi-tenant vector storage, use named vectors, or integrate vector DB with LLM providers. When in doubt about whether to use this skill for vector database or semantic search tasks, use it.
tools1
haystack
AI orchestration framework for building production-ready RAG applications, autonomous agents, and multimodal search systems. MANDATORY TRIGGERS: haystack, deepset, haystack-ai, haystack pipeline, haystack agent. Also trigger when the user wants to build RAG pipelines with modular components, create tool-calling agents with Haystack, orchestrate retrieval-augmented generation, build semantic search systems, or evaluate LLM pipelines. When in doubt about whether to use this skill for RAG orchestration or AI pipeline tasks, use it.
tools1
vitest
Next-generation testing framework powered by Vite — test API, matchers, mocking, snapshots, coverage, browser mode, type testing, CLI, and advanced patterns. MANDATORY TRIGGERS: vitest, Vitest, vitest.config, vi.mock, vi.fn, vi.spyOn, expect matchers, test coverage vitest, vitest browser mode. Also trigger when user wants to write unit tests with Vite, configure test coverage, mock modules in ESM, run browser-based component tests, benchmark code, test TypeScript types, or migrate from Jest. When in doubt about whether to use this skill for JavaScript/TypeScript testing tasks, use it.
tools1
pulumi
Pulumi — Infrastructure as Code using real programming languages (Python, TypeScript, Go, C#, Java, YAML). MANDATORY TRIGGERS: pulumi, pulumi up, pulumi preview, pulumi stack, pulumi config, Pulumi.yaml, infrastructure as code Python, IaC TypeScript, pulumi import, CrossGuard, Pulumi ESC, Pulumi Automation API, pulumi destroy, pulumi refresh, ComponentResource. Also trigger when the user asks about provisioning cloud infrastructure with Python or TypeScript code, managing IaC state with Pulumi, building reusable infrastructure components, policy as code for cloud resources, or migrating from Terraform to Pulumi. When in doubt about whether to use this skill for IaC tasks using general-purpose languages, use it.
tools1
bun
Bun all-in-one JavaScript runtime, bundler, test runner, and package manager built with Zig for extreme performance. MANDATORY TRIGGERS: Bun, bun runtime, bun install, bun test, bun build, Bun.serve, Bun.file, Bun.write, Bun.spawn, Bun.SQL, Bun.redis, bun:ffi, bun:test, bunx, bun.lock. Also trigger when building HTTP servers with Bun, migrating from Node.js to Bun, configuring the Bun bundler, writing tests with bun:test, using Bun's package manager, running shell commands with Bun.$, using built-in database clients, or developing fullstack apps with Bun's frontend dev server. When in doubt about whether to use this skill for Bun or JavaScript runtime tasks, use it.
tools1
langfuse
Open-source LLM observability and evaluation platform for tracing, prompt management, datasets, and cost analytics. MANDATORY TRIGGERS: langfuse, langfuse tracing, langfuse observability, langfuse evaluation, LLM observability, LLM tracing, LLM monitoring. Also trigger when user wants to trace LLM calls, monitor token usage and costs, manage prompts with versioning, evaluate LLM outputs with datasets, set up LLM-as-a-judge, or instrument AI agents with OpenTelemetry. When in doubt about whether to use this skill for LLM observability tasks, use it.
testing
your-skill-name
MANDATORY TRIGGERS: keyword1, keyword2, keyword3. Describe what this skill does and when to use it. Be specific about trigger conditions.
testing
ai-sdk
Vercel AI SDK for building AI-powered applications with streaming, tool calling, agents, and multi-provider support. MANDATORY TRIGGERS: ai-sdk, vercel ai, useChat, streamText, generateText, AI SDK. Also trigger when building chatbots, AI streaming interfaces, LLM tool calling in TypeScript/JavaScript, or multi-provider AI apps. When in doubt about whether to use this skill for AI app development tasks, use it.
tools
livekit
Build realtime voice, video, and AI agent applications with LiveKit. MANDATORY TRIGGERS: livekit, live kit, voice agent, voice AI, realtime audio, realtime video, WebRTC agent, speech-to-speech, voice pipeline, voice assistant framework. Also trigger when user wants to build voice AI agents, realtime communication apps, telephony integrations, video conferencing, or multimodal AI agents with audio/video. When in doubt about whether to use this skill for realtime media or voice AI tasks, use it.
development
convex
Reactive backend platform with real-time sync, ACID transactions, and TypeScript-first development. MANDATORY TRIGGERS: convex, convex.dev, ConvexProvider, useQuery, useMutation, useAction, convex functions, convex schema, convex database, convex deploy. Also trigger when user wants to build real-time apps with automatic sync, reactive backends, serverless databases with TypeScript, or full-stack apps without infrastructure. When in doubt about whether to use this skill for reactive backend or real-time sync tasks, use it.
development
trigger-dev
Build and deploy TypeScript background jobs, AI workflows, and scheduled tasks with Trigger.dev v4. MANDATORY TRIGGERS: trigger.dev, trigger dev, triggerdev, background jobs, background tasks typescript, long-running tasks, durable workflows, cron jobs typescript. Also trigger when user wants to build background processing in TypeScript, create scheduled tasks with cron, implement retry logic for jobs, set up task queues and concurrency, add human-in-the-loop approval workflows, or deploy serverless background workers. When in doubt about whether to use this skill for background job tasks, use it.
development
better-auth
Comprehensive TypeScript authentication framework with plugins for 2FA, passkeys, organizations, and 40+ OAuth providers. MANDATORY TRIGGERS: better-auth, better auth, betterAuth, TypeScript authentication, TS auth framework. Also trigger when user wants to add authentication to a TypeScript/JavaScript app, set up social login, implement passwordless auth, configure multi-tenant organizations, add passkey/WebAuthn support, or build an auth system with session management. When in doubt about whether to use this skill for authentication tasks, use it.
tools
inngest
Durable workflow orchestration platform for serverless and server environments. MANDATORY TRIGGERS: inngest, durable functions, durable execution, step functions, background jobs, workflow orchestration, inngest.createFunction, step.run, step.sleep, step.waitForEvent. Also trigger when user wants to build reliable background jobs, event-driven workflows, scheduled tasks with retries, or orchestrate multi-step serverless functions. When in doubt about whether to use this skill for background job or workflow tasks, use it.
development
litellm
Unified LLM gateway and SDK for calling 100+ LLM providers (OpenAI, Anthropic, Bedrock, Vertex, Azure, Ollama, etc.) with a single OpenAI-compatible interface. MANDATORY TRIGGERS: litellm, litellm proxy, litellm router, litellm.completion, llm gateway, multi-provider llm, openai-compatible proxy, model fallback, llm cost tracking, llm load balancing. Also trigger when user wants to switch LLM providers without rewriting code, route requests across multiple models, add fallbacks/retries to LLM calls, track token costs, run a self-hosted OpenAI-compatible proxy, or unify observability across providers. When in doubt about whether to use this skill for any multi-provider LLM task, use it.
development
claude-agent-sdk
Build AI agents programmatically with the Claude Agent SDK (Python and TypeScript). Provides the same tools, agent loop, and context management that power Claude Code, but as a library. MANDATORY TRIGGERS: claude-agent-sdk, claude agent sdk, claude_agent_sdk, @anthropic-ai/claude-agent-sdk, ClaudeAgentOptions, ClaudeSDKClient. Also trigger when user wants to build AI agents with Claude programmatically, create agent loops with tools, use Claude Code SDK, orchestrate subagents, or deploy autonomous coding agents. When in doubt about whether to use this skill for agent SDK tasks, use it.
tools
qdrant
High-performance vector search engine built in Rust for AI applications. MANDATORY TRIGGERS: qdrant, qdrant-client, vector search, vector database, similarity search, nearest neighbor search, ANN search, embedding search. Also trigger when user wants to store and query embeddings, build RAG retrieval pipelines, implement hybrid sparse+dense search, set up multitenancy for vector data, configure HNSW indexing or quantization, or manage vector collections. When in doubt about whether to use this skill for vector search tasks, use it.
tools
drizzle-orm
Type-safe TypeScript ORM for PostgreSQL, MySQL, and SQLite with SQL-like and relational query APIs. MANDATORY TRIGGERS: drizzle, drizzle-orm, drizzle orm, drizzle kit, typescript orm, type-safe sql. Also trigger when user wants to define database schemas in TypeScript, write type-safe SQL queries, manage database migrations with drizzle-kit, set up relational queries with nested data, integrate Zod validation with database schemas, or configure read replicas. When in doubt about whether to use this skill for TypeScript database tasks, use it.
development
tanstack-query
Powerful asynchronous state management and data fetching for React, Vue, Solid, Svelte, and Angular. MANDATORY TRIGGERS: tanstack query, react query, TanStack Query, useQuery, useMutation, useInfiniteQuery, server state. Also trigger when user wants to fetch and cache API data in React, implement optimistic updates, handle pagination or infinite scroll, prefetch data, manage server state with automatic background refetching, or set up SSR data hydration. When in doubt about whether to use this skill for data fetching or server state management tasks, use it.
development
hono
Ultrafast web framework built on Web Standards for Cloudflare Workers, Deno, Bun, Node.js, and edge runtimes. MANDATORY TRIGGERS: hono, hono.js, honojs, hono framework, edge web framework, cloudflare workers framework. Also trigger when user wants to build APIs for edge runtimes, create type-safe REST APIs with RPC client, use JSX for server-side rendering without React, deploy web apps to Cloudflare Workers or Deno Deploy, or build multi-runtime web applications. When in doubt about whether to use this skill for edge or lightweight web framework tasks, use it.
tools
ms-agent-framework
Expert skill for building AI agent systems with Microsoft Agent Framework (Python). MANDATORY TRIGGERS: Microsoft Agent Framework, agent-framework, Azure AI agents, Azure OpenAI agents. Also trigger when the user is building production AI agents, multi-agent orchestrations, agentic workflows on Azure, or discussing concepts like tools, semantic kernel, middleware, or memory in Python. When in doubt, use it.
tools
polars
High-performance DataFrame library written in Rust with Python bindings for blazingly fast data manipulation, lazy evaluation, and analytical queries. MANDATORY TRIGGERS: polars, pl.DataFrame, pl.LazyFrame, pl.col, pl.scan_csv, polars dataframe. Also trigger when user wants to process large datasets, replace pandas with faster alternative, do data engineering in Python, work with Parquet/CSV files at scale, or perform analytical queries on structured data. When in doubt about whether to use this skill for data processing tasks, use it.
development
remotion-prompt-generator
Generate detailed, production-ready prompts for the Remotion Dev skill to create programmatic React-based videos. MANDATORY TRIGGERS: remotion prompt, video prompt, generate video prompt, remotion video, create video prompt, video brief, video specification, make a video, create a video. Also trigger when user wants to create any kind of video using Remotion, needs help describing a video project, wants a prompt for a video generation tool, or asks for a video brief/spec. When in doubt, use it.
tools
zod
TypeScript-first schema validation with static type inference (Zod v4). MANDATORY TRIGGERS: zod, schema validation, z.object, z.string, z.infer, zod schema. Also trigger when building TypeScript form validation, API input parsing, runtime type checking, JSON Schema conversion, or data validation pipelines. When in doubt about whether to use this skill for TypeScript validation tasks, use it.
development
design-engineering
Comprehensive frontend design engineering system covering the full design lifecycle — planning, building, styling, reviewing, refining, hardening, and upgrading interfaces. MANDATORY TRIGGERS: design, UI, UX, frontend, interface, component, layout, typography, color, animation, responsive, accessibility, critique, audit, polish, redesign, design system, onboarding, micro-interactions, visual design. Also trigger when user asks to build a page, create a component, review a design, improve typography, add animation, fix layout, audit accessibility, redesign an existing project, add delight, make it look professional, or any frontend visual/interaction task. When in doubt about whether to use this skill for any design or frontend task, use it.
development
agno
Build AI agents, multi-agent teams, and agentic workflows using the Agno framework. MANDATORY TRIGGERS: Agno, agno-agi, AgentOS, any mention of the Agno framework. Also trigger when the user wants to build AI agents with tools/memory/knowledge, create multi-agent systems, RAG pipelines, reasoning agents, agentic workflows, or deploy agents to production. Trigger even if the user just says 'build me an agent', 'create an AI assistant', or 'make a chatbot' — if Agno is anywhere in their stack or project dependencies. When in doubt about whether to use this skill for agent-building tasks, use it.
tools
dspy
Programming (not prompting) framework for building and optimizing LLM pipelines with declarative Python modules, typed signatures, and automatic prompt/weight optimization. MANDATORY TRIGGERS: dspy, dspy.Predict, dspy.ChainOfThought, dspy.ReAct, dspy.Signature, dspy.Module, dspy.Optimize, BootstrapFewShot, MIPRO, MIPROv2, dspy.Evaluate, dspy.Retrieve, dspy compile, dspy optimizer. Also trigger when user wants to replace hand-written prompts with structured modules, automatically tune few-shot examples, build typed LLM pipelines with assertions, optimize a pipeline against a metric, compile a DSPy program, or build multi-hop RAG with declarative modules. When in doubt about whether to use this skill for any DSPy or LLM-pipeline-compiling task, use it.
development
opentelemetry
Vendor-neutral observability framework for traces, metrics, and logs. MANDATORY TRIGGERS: opentelemetry, otel, otlp, distributed tracing, observability, telemetry, span, tracer, meter, opentelemetry-sdk, opentelemetry-api. Also trigger when user wants to instrument applications, set up distributed tracing, collect metrics or logs, configure an OTel Collector, implement context propagation, or use semantic conventions. When in doubt about whether to use this skill for observability tasks, use it.
development