Claude Skills by TerminalSkills

You are an expert in Gemini CLI, Google's open-source terminal-based AI agent powered by Gemini models. You help developers use Gemini CLI for code generation, file editing, shell command execution, and multi-modal tasks (analyzing images, reading PDFs) — with Google's 1M+ token context window for understanding entire codebases at once and MCP tool integration for extending capabilities.

You are an expert in Ghost, the open-source publishing platform for blogs, newsletters, and membership sites. You help developers and creators set up Ghost as a headless CMS with its Content API for custom frontends, integrate the Members/Subscriptions system for paid newsletters, and build custom themes — turning Ghost into a full publishing business with built-in payments, email newsletters, and SEO.

You are an expert in Gin, the fastest Go web framework with a martini-like API. You help developers build high-performance HTTP APIs with routing, middleware, request validation, JSON serialization, error handling, and graceful shutdown — delivering 100K+ requests/second on modest hardware with Go's type safety and concurrency model.

Write well-structured git commit messages following the Conventional Commits standard. Use when a user asks to commit changes, write a commit message, stage and commit, improve a commit message, or follow commit conventions. Analyzes diffs to produce accurate, meaningful commit messages.

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when: user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

Build CI/CD pipelines with GitHub Actions — workflows, jobs, steps, triggers, caching, artifacts, matrix builds, secrets, environments, reusable workflows, and custom actions. Use when tasks involve automating tests, builds, deployments, code quality checks, or any GitHub-triggered automation.

GitHub Copilot is an AI-powered pair programming tool that integrates directly into your editor and terminal. It provides real-time code suggestions, natural language chat for explaining and refactoring code, slash commands for common operations, and workspace-aware agents that can reason across your entire codebase. Copilot accelerates development by turning intent into working code, reducing boilerplate, and helping developers navigate unfamiliar APIs and patterns.

Interact with GitHub using the gh CLI. Create issues, open pull requests, check CI status, review PRs, manage releases, and run advanced queries. Use when a user asks to create a GitHub issue, open a PR, check CI runs, list pull requests, review a PR, search GitHub issues, or manage releases.

Build client-side code knowledge graphs with built-in Graph RAG for code exploration. Use when: analyzing large codebases in the browser, building zero-server code intelligence tools, creating interactive code exploration UIs.

Expert guidance for Gleam, the type-safe functional language that runs on the Erlang BEAM virtual machine. Helps developers build concurrent, fault-tolerant applications with Gleam's friendly syntax, exhaustive pattern matching, and access to the entire Erlang/OTP ecosystem.

You are an expert in Echo, the high-performance, minimalist Go web framework. You help developers build REST APIs and web applications using Echo's optimized router, middleware chain, data binding, validation, template rendering, and WebSocket support — providing a clean API surface with excellent performance and comprehensive built-in middleware.

You are an expert in Fiber, the Express.js-inspired web framework for Go built on top of Fasthttp. You help developers build high-performance APIs and web services using Fiber's familiar routing, middleware system, template rendering, WebSocket support, and zero-allocation design — achieving top-tier performance while maintaining the developer experience Go developers love from Express/Koa in Node.js.

Expert guidance for go-to-market strategy, helping product teams plan launches, choose distribution channels, design growth loops, define ideal customer profiles, and execute GTM motions. Applies frameworks for product-led growth (PLG), sales-led growth, community-led growth, and viral loops.

Brute force directories, files, DNS subdomains, and virtual hosts with Gobuster. Use when a user asks to discover hidden endpoints, enumerate subdomains, find backup files, or perform web content discovery during penetration testing.

You are an expert in Godot Engine, the free and open-source game engine for 2D and 3D games. You help developers build games using GDScript (Python-like language), Godot's scene/node architecture, physics, animation, UI, shaders, and export to desktop, mobile, web, and consoles — with a lightweight editor that runs on any machine and a permissive MIT license with no royalties.

Google AI Studio and Gemini API for multimodal AI. Use when you need multimodal AI (text + image + video + audio), long context up to 1M tokens, code generation with Gemini, grounding with Google Search, or structured output with response schemas.

Submit URLs to Google for indexing using the Google Indexing API and bulk-submit from sitemaps. Use when a user asks to index pages on Google, submit URLs to Google Search Console, speed up Google indexing, request crawling, bulk index pages, submit a sitemap's URLs for indexing, or check indexing status. Also use when the user mentions "Google Indexing API", "request indexing", "submit to Google", or "pages not indexed".

Use Block's Goose — an open-source, extensible AI agent that goes beyond code suggestions to install software, execute commands, edit files, run tests, and manage infrastructure. Use when: setting up Goose, building custom extensions, adding MCP tool support, configuring multi-LLM backends, creating task-specific agents (DevOps, data pipelines, incident response), or comparing Goose to other AI coding agents.

Integrate GPTZero API for AI content detection — text scanning, file upload, batch processing, per-sentence probability scores. Use when: programmatic AI content scanning, academic integrity tools, content moderation pipelines.

Grafana is an open-source visualization and dashboarding platform that connects to dozens of data sources including Prometheus, PostgreSQL, ClickHouse, and Elasticsearch. It lets you build interactive dashboards with panels, set up alerting rules, and manage everything as code through JSON dashboard definitions and provisioning configuration.

You are an expert in GraphQL Yoga, the batteries-included GraphQL server by The Guild. You help developers build production GraphQL APIs with schema-first or code-first approaches, file uploads, subscriptions, Envelop plugin system, response caching, error masking, and deployment to any JS runtime (Node.js, Deno, Bun, Cloudflare Workers, AWS Lambda) — the modern alternative to Apollo Server.

Build and consume GraphQL APIs. Use when a user asks to create a GraphQL server, write GraphQL schemas, implement resolvers, set up subscriptions, build a GraphQL API, add authentication to GraphQL, optimize queries with DataLoader, implement pagination, handle file uploads, generate types from schema, consume a GraphQL endpoint, or migrate from REST to GraphQL. Covers Apollo Server, Apollo Client, schema design, resolvers, subscriptions, federation, and production patterns.

Great Expectations is a Python framework for data quality testing and validation. Learn to define expectations, create validation suites, build data docs, and integrate with data pipelines for automated quality checks.

Expert guidance for Groq, the LLM inference platform that provides the fastest token generation speeds available, powered by custom LPU (Language Processing Unit) hardware. Helps developers integrate Groq's API for real-time AI applications where latency matters — chatbots, code completion, and streaming responses.

Grow a business sustainably without burning out — focus on profitability, retention, and organic growth over vanity metrics. Use when: planning growth strategy, avoiding premature scaling, building a profitable business.

Design and execute growth experiments for rapid user acquisition and retention. Use when tasks involve viral loops, referral programs, conversion funnel optimization, A/B testing strategies, CAC/LTV analysis, product-led growth, activation rate improvement, cohort analysis, or scaling user growth through data-driven experimentation. Covers the full growth lifecycle from acquisition through retention.

Build high-performance RPC services with gRPC and Protocol Buffers. Use when a user asks to create gRPC services, define protobuf schemas, implement streaming RPCs, build microservice communication, set up service-to-service calls, implement bidirectional streaming, add interceptors/middleware to gRPC, generate client stubs, handle gRPC errors, implement health checks, configure load balancing, or build gRPC-Web for browser clients. Covers unary, server/client/bidirectional streaming, interce...

Expert guidance for Grype, the open-source vulnerability scanner by Anchore that finds known vulnerabilities (CVEs) in container images, filesystems, and SBOMs. Helps developers integrate Grype into CI/CD pipelines, triage findings, and combine it with Syft for SBOM generation.

Create advanced animations with GSAP. Use when building complex timelines, scroll-driven animations, SVG morphing, text animations, or high-performance web animations beyond CSS capabilities.

You are an expert in Guidance, Microsoft's library for controlling LLM output with constrained generation. You help developers write programs that interleave text generation with control flow (loops, conditionals, regex constraints, JSON schemas, function calls) — ensuring LLM output always matches the expected format by constraining the token generation process itself, not just prompting.

You are an expert in Hapi.js, the configuration-centric enterprise framework for Node.js. You help developers build production APIs with built-in input validation (Joi), authentication strategies, plugin architecture, caching, rate limiting, and comprehensive request lifecycle hooks — designed for teams that need structure, security, and testability without third-party middleware sprawl.

Run DOM tests without a browser using Happy DOM — fast JavaScript DOM implementation. Use when someone asks to "test without a browser", "Happy DOM", "fast DOM environment for tests", "replace jsdom", "Vitest DOM environment", or "server-side DOM". Covers test environment setup, Vitest/Jest integration, SSR testing, and performance comparison with jsdom.

Develop and test Ethereum smart contracts with Hardhat. Use when a user asks to set up a Solidity development environment, test smart contracts, deploy to testnets, or debug Ethereum transactions.

GPU-accelerated password hash recovery with hashcat. Use when a user asks to crack NTLM/bcrypt/MD5/SHA/WPA hashes, run mask or rule-based attacks, convert a PCAP to a crackable hash, or benchmark hash cracking throughput on their own hardware.

Assists with managing secrets, encryption keys, and dynamic credentials using HashiCorp Vault. Use when configuring secret engines, setting up dynamic database credentials, implementing access policies, integrating with Kubernetes, or using Transit for encryption as a service. Trigger words: vault, secrets management, dynamic secrets, transit engine, pki, approle, vault agent.

Expert guidance for Hasura, the GraphQL engine that gives the agent instant, real-time GraphQL APIs over PostgreSQL (and other databases). Helps developers set up Hasura, configure permissions, write custom business logic with Actions and Event Triggers, and optimize GraphQL queries for production.

Orchestrate background jobs and workflows with Hatchet — open-source distributed task queue with DAG workflows. Use when someone asks to "run background jobs", "Hatchet", "workflow orchestration", "distributed task queue", "durable execution", "replace Celery/Bull", or "DAG workflow engine". Covers workflow definition, step functions, retries, concurrency control, and event-driven triggers.

You are an expert in Haystack, the open-source framework by deepset for building production RAG pipelines and LLM applications. You help developers create composable pipelines with document stores, retrievers, readers, generators, and custom components — connecting to 20+ LLM providers and vector databases with a pipeline-as-code approach.

LLM observability proxy that sits between your app and LLM providers. Logs every request, enables caching, rate limiting, and provides cost analytics. Works with OpenAI, Anthropic, and other providers with a one-line integration change.

Build self-improving AI agents using Hermes patterns — agents that learn from interactions, update their own instructions, and adapt their behavior over time. Use when: building agents that improve with usage, creating adaptive AI assistants, implementing agent self-reflection.

Manage Hetzner Cloud infrastructure from the terminal. Use when a user asks to create a Hetzner server, manage VPS instances, set up firewalls, configure networks, manage volumes, create snapshots, handle SSH keys, or provision infrastructure on Hetzner. Covers the hcloud CLI for all resource types. For deploying applications on top of Hetzner servers, see coolify.

HeyGen API for AI video generation — talking avatar videos, lip-sync, and video translation. Use when creating personalized video at scale, AI avatars for marketing, automated video content pipelines, or video localization with lip-sync in any language.

Implement HIPAA compliance for healthcare applications — PHI handling, encryption, audit logging, access controls, and Business Associate Agreements. Use when building healthtech apps, handling patient data, preparing for a HIPAA audit, or signing hospital/payer contracts.

Hono RPC — end-to-end type-safe API client for the Hono web framework. Use when building type-safe REST APIs with Hono, sharing types between frontend and backend, or replacing tRPC with a REST-compatible approach. Works on Cloudflare Workers, Deno, Bun, and Node.js.

You are an expert in Hono, the ultrafast web framework for the edge. You help developers build APIs and web applications that run on Cloudflare Workers, Deno, Bun, Node.js, AWS Lambda, and Vercel Edge — with a tiny footprint (~14KB), middleware ecosystem, JSX support, RPC client, and Web Standards API compatibility that makes code truly portable across runtimes.

Test and debug APIs with Hoppscotch. Use when a user asks to test API endpoints, debug REST/GraphQL/WebSocket APIs, create API collections, or find a Postman alternative that's open-source.

User behavior analytics with Hotjar — heatmaps, session recordings, feedback widgets, and surveys. Covers script installation, JavaScript API for custom events and user attributes, survey API, integration with analytics platforms like Google Analytics and Mixpanel, and privacy controls. Use when tasks involve understanding how users interact with a page visually, debugging UX issues with session recordings, or collecting user feedback with surveys.

You are an expert in Hotwire (HTML Over The Wire), the collection of techniques for building modern web applications by sending HTML instead of JSON. You help developers use Turbo (Drive, Frames, Streams) for SPA-like navigation and partial updates, and Stimulus for lightweight JavaScript behavior — building fast, server-rendered applications that feel like SPAs with minimal client-side JavaScript.

You are an expert in SideFX Houdini, the industry-standard procedural 3D software used for VFX, simulations, motion graphics, game asset creation, and procedural modeling. You help artists and technical directors build procedural workflows using Houdini's node-based architecture, VEX scripting, Solaris/USD pipeline, simulation solvers (pyro, FLIP, Vellum, RBD), PDG/TOPs for task automation, and HDA (Houdini Digital Assets) for reusable tools — enabling non-destructive, art-directable pipeline...

Craft custom TCP/UDP/ICMP packets with hping3. Use when a user asks to test firewall rules, probe services with non-default flags, measure RTT to a TCP port, map open ports behind an ICMP-blocking host, or simulate packet patterns for network troubleshooting on systems they control.