Claude Skills by TerminalSkills

Build zero-trust networks with Tailscale — mesh VPN setup, ACLs, exit nodes, subnet routing, MagicDNS, Funnel, SSH, and API automation. Use when tasks involve connecting remote machines, securing internal services, replacing traditional VPNs, or exposing local services to the internet.

You are an expert in Tailwind CSS v4, the utility-first CSS framework. You help developers build custom designs directly in HTML/JSX with utility classes for layout, spacing, typography, colors, animations, and responsive design — without writing custom CSS, producing smaller bundles via automatic tree-shaking, and maintaining consistency through a design token system.

You are an expert in TanStack Query (formerly React Query), the data-fetching and server state management library. You help developers build React applications with automatic caching, background refetching, optimistic updates, pagination, infinite scroll, and offline support — replacing manual `useEffect` + `useState` patterns with declarative, type-safe data fetching hooks.

Type-safe routing for React with file-based routes, validated search params, loaders, and automatic code splitting. Use when someone asks to "set up routing for React", "type-safe router", "TanStack Router", "file-based routing", "search params validation", "replace React Router with something type-safe", or "add route-level data loading". Covers file-based routing, search params with Zod, route loaders, code splitting, and layouts.

Build full-stack React apps with TanStack Start. Use when a user asks to create a full-stack React application with type-safe server functions, set up file-based routing with SSR/SSG/SPA modes, build APIs with middleware and validation, implement server-side data fetching with TanStack Router, or deploy to Cloudflare/Netlify/Vercel/Node.

Build powerful data tables with TanStack Table — headless, framework-agnostic table library. Use when someone asks to "build a data table", "TanStack Table", "sortable table", "filterable data grid", "paginated table", "React table", or "headless table library". Covers sorting, filtering, pagination, column resizing, row selection, and virtualization.

Tauri builds desktop and mobile apps from a web frontend and a Rust backend, rendering the UI in the operating system's webview instead of a bundled Chromium. Use when creating or extending a Tauri v2 app: scaffolding with create-tauri-app, writing Rust commands and calling them with invoke, pushing events or channel data to the frontend, adding plugins, fixing "not allowed" permission errors in capabilities, bundling installers, or shipping signed auto-updates. Trigger words: tauri, tauri v2...

Self-hosted AI accounting tool that analyzes receipts, invoices, and bank transactions using LLMs. Use when: automating personal/business bookkeeping, categorizing expenses with AI, preparing tax documents, building self-hosted financial tools.

Guides building a feature or fixing a bug test-first with the red-green-refactor cycle: agree a list of behaviours, write one failing test, make it pass with the least code, tidy up while green, repeat. Covers reproducing bugs with a failing test, pinning down untested legacy code before changing it, and choosing what to replace with test doubles. Use when the user says "use TDD", "write the test first", "red-green-refactor", "test-drive this function", "add a regression test before fixing", ...

Lead teams effectively using proven frameworks — set clear intent, reduce communication overhead, create psychological safety, and use forcing functions to drive results. Use when: managing teams, improving team collaboration, setting goals and accountability.

Scans codebases for technical debt signals and prioritizes them by business impact. Finds TODO/FIXME/HACK comments, outdated dependencies, code duplication, and correlates with git history to identify high-churn debt hotspots. Use when someone asks about technical debt, code quality audit, refactoring priorities, or maintainability assessment. Trigger words: tech debt, code quality, refactoring, TODOs, maintainability, code health.

Configure Telegraf as a metrics collection agent for infrastructure and application monitoring. Use when a user needs to collect system metrics, set up input plugins for databases and services, configure output to InfluxDB or Prometheus, or build custom metric pipelines.

Builds Telegram bots using the Bot API (grammy/telegraf/python-telegram-bot). Use when the user wants to create a Telegram bot, handle commands, build inline keyboards, process callbacks, send media, build conversational flows, handle payments (Telegram Stars), or create Mini Apps. Trigger words: telegram bot, telegram integration, telegram commands, inline keyboard, telegram webhook, telegram polling, telegram mini app, telegram payments, BotFather, grammy, telegraf.

Exports and downloads Telegram chats, media, and channel content. Use when a user asks to export Telegram chat history, download media from Telegram channels or groups, archive Telegram conversations, backup Telegram messages, extract images, videos or links from Telegram, bulk download from Telegram channels, or migrate Telegram data. Covers Telegram Desktop's built-in export and Python scripts built on the Telethon library.

Auto-fill document templates with data. Use when a user asks to create a mail merge, fill templates with data, generate documents from a template, populate placeholders, bulk generate letters or invoices, or auto-fill forms from a spreadsheet. Supports any document format including DOCX, PDF, HTML, and plain text.

Build reliable distributed workflows with Temporal. Use when a user asks to orchestrate microservices, handle long-running workflows, implement saga patterns, build reliable background jobs, or create fault-tolerant distributed systems.

You are an expert in TensorFlow, Google's open-source machine learning framework. You help developers build, train, and deploy neural networks using Keras (TensorFlow's high-level API), custom training loops, TensorFlow Serving for production inference, TFLite for mobile/edge deployment, and TensorFlow.js for browser ML — from prototyping to production-scale distributed training.

Discover and install AI agent skills from terminalskills.io. Use when the user asks for a capability the agent does not already have a skill for — search the catalog by keyword, category, or tag; inspect a skill before installing; install for the current agent (Claude Code, Codex, Gemini CLI, Cursor); or browse via the public REST API or MCP server. Trigger words: "install skill", "find a skill for", "browse skills", "terminal-skills", "search the skill catalog".

Manages cloud infrastructure using Terraform (and OpenTofu). Use when the user wants to write Terraform configurations, provision cloud resources, manage state, create modules, set up multi-environment deployments, import existing infrastructure, debug plan/apply errors, migrate between providers, or implement IaC best practices. Trigger words: terraform, opentofu, infrastructure as code, IaC, tf, hcl, terraform module, terraform state, terraform plan, terraform apply, terraform import, cloud...

You are an expert in Terragrunt, the thin wrapper for Terraform and OpenTofu that provides extra tools for keeping configurations DRY, managing remote state, and orchestrating multi-module deployments. You help platform teams manage large-scale infrastructure across multiple environments and AWS accounts using Terragrunt's hierarchical configuration, dependency management, and before/after hooks.

Tesseract is an open-source OCR engine that reads printed text out of images (PNG, JPEG, TIFF) and writes plain text, searchable PDF, hOCR, TSV or ALTO XML. Use when someone asks to "extract text from an image", "OCR this scan", "make a scanned PDF searchable", "read a receipt or serial number from a photo", "get word bounding boxes and confidence", or names tesseract, pytesseract or tesseract.js. Covers the tesseract command line, language data, page segmentation modes, the pytesseract Pytho...

Generate unit, integration, and end-to-end tests for existing code. Use when a user asks to write tests, add test coverage, create unit tests, generate integration tests, build e2e tests, improve code coverage, write specs, or add testing to a project. Supports Jest, Vitest, Pytest, Playwright, React Testing Library, and Cypress. Analyzes code to produce meaningful assertions, edge cases, and mock setups.

When the user wants to run integration tests with real dependencies using Docker containers managed by Testcontainers. Also use when the user mentions "testcontainers," "integration testing with Docker," "database integration tests," "containerized tests," or "test with real database." For API mocking without containers, see mockoon or wiremock.

Test UI components the way users interact with them using Testing Library — query by role, text, and label instead of implementation details. Use when someone asks to "test React components", "Testing Library", "user-centric testing", "test accessibility", "test without implementation details", or "render and query components in tests". Covers React Testing Library, queries, user events, async testing, and accessibility assertions.

Deploy and configure Thanos for long-term Prometheus metric storage, global querying across multiple Prometheus instances, and data compaction. Use when a user needs durable metric storage in object storage, a unified query view across clusters, downsampling for historical data, or high-availability Prometheus with deduplication.

Passive email, subdomain, and IP harvesting from public sources using theHarvester. Use when: gathering corporate email lists, enumerating subdomains passively, pre-engagement recon, finding exposed employee contacts without triggering alerts.

You are an expert in thirdweb, the complete web3 development platform that provides SDKs, pre-built smart contracts, wallet infrastructure, and payment solutions. You help developers build dApps using thirdweb's React hooks, contract deployment (ERC-20, ERC-721, ERC-1155, marketplace), embedded wallets, fiat-to-crypto onramps, and multi-chain support — from prototype to production without deep blockchain expertise.

Three.js is a JavaScript library for building interactive 3D graphics in the browser with WebGL and WebGPU. Use it for 3D product configurators, data visualizations, games and creative sites: scenes, cameras, lighting, glTF model loading, performance tuning, and React Three Fiber. Trigger words: threejs, three.js, 3d, webgl, webgpu, react three fiber, r3f, glb, gltf.

Create, optimize, and automate TikTok content for brand awareness, audience growth, and conversions. Use when someone asks to "grow on TikTok", "create TikTok content", "TikTok marketing strategy", "TikTok API integration", "automate TikTok posting", "TikTok analytics", or "TikTok for business". Covers short-form video strategy, trending sounds, TikTok Content Posting API, analytics, and growth tactics.

Build and customize websites with Tilda — zero-code website builder with advanced customization. Use when someone asks to "build a website with Tilda", "Tilda Publishing", "customize Tilda site", "Tilda API", "landing page builder", "no-code website", "Tilda custom code", or "integrate Tilda with external services". Covers block-based building, custom HTML/CSS/JS, Tilda API, form handling, e-commerce, and integrations.

Tiled is a free, open-source 2D level editor for building tilemaps, placing game objects, and designing levels, exporting to JSON (.tmj) or TMX (.tmx) for engines like Phaser, Godot, and Unity. Use when a user wants to design a tile-based game level, set up tile and object layers, build auto-tiling terrain brushes, animate tiles, attach custom properties to tiles or objects, or load a Tiled map into a game engine.

Forecast time series data using Google's TimesFM foundation model with zero-shot prediction. Use when: forecasting sales or demand, predicting server metrics, financial time series analysis, anomaly detection without training custom models.

Expert guidance for TinaCMS, the open-source headless CMS that stores content in Git (Markdown/MDX/JSON) and provides visual editing capabilities. Helps developers set up TinaCMS with Next.js, define content schemas, and build visual editing experiences where editors can see changes in real time.

TinyBase is a reactive in-memory data store for local-first JavaScript and TypeScript apps, with tables, key-value data, queries, persistence and CRDT sync. Use when a user asks to build an offline-capable or local-first app, keep app state in a TinyBase store, persist it to localStorage, IndexedDB, SQLite or Postgres, sync data between devices or tabs with a MergeableStore and WebSockets, or bind a store to React with tinybase/ui-react.

Build real-time analytics APIs with Tinybird — ingest millions of events and query with SQL over HTTP. Use when someone asks to "build analytics API", "Tinybird", "real-time analytics", "event analytics", "ClickHouse as a service", "usage metering", or "product analytics backend". Covers data ingestion, SQL pipes, API endpoints, and real-time dashboards.

tldraw is a React SDK for building infinite-canvas apps — whiteboards, diagram editors, and visual tools — with a shape system, camera controls, snapshots, and real-time multiplayer. Use when embedding a collaborative canvas or whiteboard in a React app, defining custom shapes, driving the editor programmatically, exporting the canvas to an image, or adding multiplayer sync. Note: production use requires a tldraw license key.

You are an expert in Tokio, the asynchronous runtime for Rust that powers most of the Rust async ecosystem. You help developers build high-performance network applications, concurrent services, and I/O-bound systems using Tokio's task scheduler, async I/O primitives, channels, timers, and synchronization utilities — handling millions of concurrent connections with minimal memory overhead.

ToolJet is an open-source (AGPL-3.0) low-code platform for building internal tools such as admin panels, dashboards and CRUD apps with a drag-and-drop builder, SQL and REST queries, and JavaScript or Python. Use when a user asks to build an internal tool or admin dashboard, connect a database or API to a visual app, write ToolJet queries and event handlers, or self-host ToolJet with Docker or Helm.

You are an expert in Traceloop and its OpenLLMetry SDK, the open-source observability framework that extends OpenTelemetry for LLM applications. You help developers instrument AI pipelines with automatic tracing for OpenAI, Anthropic, Cohere, LangChain, LlamaIndex, vector databases, and frameworks — exporting to any OpenTelemetry-compatible backend (Grafana Tempo, Jaeger, Datadog, Honeycomb, Traceloop Cloud).

Build multi-agent LLM trading systems for financial analysis and automated trading decisions. Use when: building AI-powered investment research, automating financial analysis pipelines, creating multi-agent systems that analyze markets, news, and fundamentals.

Route traffic and manage TLS with Traefik reverse proxy. Use when a user asks to set up a reverse proxy, route traffic to Docker containers, auto-provision SSL certificates with Let's Encrypt, set up load balancing, configure HTTPS for multiple services, use a modern alternative to nginx for Docker, set up path-based or host-based routing, add middleware (rate limiting, auth, headers), or manage ingress for containerized applications.

Investigates a reported bug and turns it into a tracker issue that someone else can pick up: checks for duplicates, reproduces the problem, traces it to its cause in the code, rates severity, and writes a test-first fix plan. Use when someone says "triage this bug", "look into this error and file an issue", "why is this failing, write it up", "users report that...", or pastes a stack trace or a failing CI job and wants an issue rather than an immediate fix. Files on GitHub with the gh CLI, or...

Expert guidance for Trieve, the all-in-one search infrastructure that combines full-text, semantic, and hybrid search with built-in RAG capabilities. Helps developers implement production search with chunking, re-ranking, recommendations, and analytics without managing vector databases or embedding models.

You are an expert in Trigger.dev, the open-source background jobs platform for TypeScript. You help developers build reliable long-running tasks, scheduled jobs, webhook handlers, and event-driven workflows with automatic retries, concurrency control, real-time logs, and deployment to serverless infrastructure — replacing BullMQ/Redis setups with a fully managed or self-hosted solution purpose-built for modern TypeScript apps.

Serves trained machine-learning models over HTTP and gRPC with NVIDIA Triton Inference Server: one server for ONNX, TensorRT, PyTorch, TensorFlow, OpenVINO and Python models, with dynamic batching, model ensembles, versioning and Prometheus metrics, on GPU or CPU. Use when a user asks to deploy a model for production inference, write a config.pbtxt, batch requests for GPU throughput, chain preprocessing and a model, or call Triton from Python.

Trivy is an open-source scanner from Aqua Security that finds vulnerabilities, exposed secrets, misconfigurations and license problems in container images, filesystems, git repos and IaC files. Use when a user asks to scan a Docker image for CVEs, audit a repo for leaked secrets, check Terraform or Kubernetes manifests for misconfigurations, generate an SBOM, or add security scanning to CI.

You are an expert in tRPC, the framework for building type-safe APIs without schemas or code generation. You help developers create full-stack TypeScript applications where the server defines procedures and the client calls them with full type inference — no REST routes, no GraphQL schemas, no OpenAPI specs, just TypeScript functions that are type-safe from database to UI.

Bundle TypeScript libraries with tsup — zero-config, powered by esbuild. Use when someone asks to "bundle a TypeScript library", "build npm package", "tsup", "publish TypeScript to npm", "build ESM and CJS", "bundle with esbuild", or "library bundling with zero config". Covers ESM/CJS dual output, declaration files, tree-shaking, and npm publishing.

Turbopack is the Rust-based incremental bundler built into Next.js, the default for next dev and next build since Next.js 16. Use when someone asks to configure Turbopack, migrate a webpack config or loaders to the turbopack option in next.config, fix a Turbopack build error, or switch back to webpack with --webpack.

Assists with managing JavaScript/TypeScript monorepos using Turborepo. Use when configuring build pipelines, setting up caching, pruning workspaces for Docker, or optimizing CI/CD for monorepo projects. Trigger words: turborepo, turbo, monorepo, pipeline, workspace, remote cache, turbo.json.