All authors
Claude Skills by TerminalSkills
github.com/TerminalSkills1,048 skills95 installs4,524 views
- Ant DesignAnt Design (antd) is a React component library of 70+ enterprise UI components (tables, forms, date pickers, modals, menus) with design-token theming through ConfigProvider. Use it to build admin panels, back-office tools and data-heavy dashboards: server-paginated tables with filters and bulk actions, validated forms, dark or branded themes, and antd inside Next.js without a flash of unstyled content. Triggers: "antd table", "Ant Design form validation", "customize antd theme", "antd dark mo...Votes: 0GitHub stars: 155
- Context7Context7 fetches current, version-specific documentation and code examples for software libraries and hands them to an AI coding agent, so generated code matches the library version in use instead of stale training data. Use when someone says "use context7", "get the latest docs for this library", "look up the current API", "the agent keeps using a deprecated method", "set up Context7 in Claude Code or Cursor", or asks how to call a framework whose API changed recently. Covers the ctx7 CLI, t...Votes: 0GitHub stars: 155
- DifyDify is an open-source platform for building LLM apps such as chatbots, agents, workflows and RAG knowledge bases, and it exposes every published app as a REST API. Use when a user asks to self-host Dify with Docker Compose, configure Dify environment variables, call a Dify app or workflow API, upload documents to a Dify knowledge base, export or import a Dify DSL file, run a Dify app from the terminal with difyctl, or upgrade and back up a Dify instance.Votes: 0GitHub stars: 155
- FabricFabric is a command-line tool that runs a library of reusable AI prompts, called patterns, over any text you pipe in, such as summarize, extract_wisdom or analyze_claims. Use it to summarize articles, pull key ideas from YouTube talks and podcasts, fact-check claims, write custom prompt patterns, or chain patterns into a workflow, with OpenAI, Anthropic, Gemini or local Ollama models. Trigger phrases: "summarize this article with fabric", "extract wisdom from this YouTube video", "run a fabri...Votes: 0GitHub stars: 155
- FastmcpFastMCP is a Python framework for building Model Context Protocol (MCP) servers and clients: a decorated Python function becomes a tool, resource or prompt that an AI agent can call, with the schema generated from type hints. Use when someone asks to "build an MCP server in Python", "create a FastMCP server", "expose this function to Claude as a tool", "turn our OpenAPI spec into MCP tools", "test my MCP server", "call an MCP server from Python", or "install my server into Claude Code or Curs...Votes: 0GitHub stars: 155
- GhidraGhidra is an open-source reverse engineering suite from the NSA that disassembles and decompiles compiled programs so their behaviour can be read and scripted. Use when a user asks to analyze a binary with Ghidra from the command line, run analyzeHeadless, batch-import firmware or malware samples into a Ghidra project, decompile functions to C, write a Ghidra script in Java or Python, or automate analysis with PyGhidra. For authorized work only: malware analysis, vulnerability research, firmw...Votes: 0GitHub stars: 155
- GolangGo is Google's open-source programming language whose toolchain compiles programs into single static binaries and ships with built-in modules, testing, fuzzing, race detection and cross-compilation. Use when a user asks to set up a Go project, add or upgrade Go dependencies, run go test, go vet or benchmarks, fix a data race, write generic Go code, work across several modules with go.work, or build release binaries for Linux, macOS and Windows. Phrases: "init a go module", "go mod tidy", "cro...Votes: 0GitHub stars: 155
- Home AssistantHome Assistant is an open-source home automation server that controls lights, sensors, thermostats and other smart devices locally, without a cloud account. Use when a user asks to install Home Assistant with Docker, edit configuration.yaml, write or debug a YAML automation, check the configuration before a restart, call the Home Assistant REST API or WebSocket API with a long-lived access token, read sensor history, or run `ha` commands on Home Assistant OS.Votes: 0GitHub stars: 155
- HugoHugo is a static site generator that turns Markdown content and templates into a complete HTML website in seconds, with no database or server runtime. Use when a user asks to create a Hugo site or blog, add a theme, write posts with front matter, preview with hugo server, configure hugo.toml, build the site for production, find unpublished drafts, or deploy a Hugo site to GitHub Pages or a cloud bucket.Votes: 0GitHub stars: 155
- HypothesisHypothesis is a Python library for property-based testing: a test states a rule that must hold for all inputs, and Hypothesis generates hundreds of inputs, including edge cases, then reports the simplest one that breaks the rule. Use when a user asks to write property-based tests, fuzz a Python function, find edge cases, test a round trip such as encode and decode, write stateful tests, reproduce a failing Hypothesis example, or tune Hypothesis settings and profiles for pytest and CI.Votes: 0GitHub stars: 155
- ImpeccableImpeccable is a design skill pack for AI coding agents: one /impeccable skill with 24 commands (init, audit, critique, polish, typeset, layout and more) plus a CLI that scans HTML, CSS, JSX and live URLs for 61 deterministic anti-patterns of AI-generated UI. Use when a user says "my AI-generated UI looks generic", "install impeccable", "run /impeccable audit", "polish this page before launch", "stop the purple gradients and Inter everywhere", or wants a design lint for UI files in CI or as an...Votes: 0GitHub stars: 155
- Kilo CodeKilo Code is an open-source AI coding agent that runs in the terminal, VS Code and JetBrains, reads and edits a codebase, runs commands, and works with 500+ models from any provider, including local Ollama. Use it to script the `kilo` CLI: one-shot `kilo run` tasks, CI jobs with `--auto`, provider and model setup in `kilo.jsonc`, permission rules, and custom agents in `.kilo/agents/`. Triggers: "set up Kilo Code", "kilo run in CI", "use Kilo with Ollama", "Kilo custom agent", "open-source cod...Votes: 0GitHub stars: 155
- LangflowLangflow is a visual builder for AI agents and workflows that serves every flow as a REST API endpoint and as an MCP tool. Use when a user asks to install or run Langflow, deploy Langflow with Docker Compose and PostgreSQL, run a flow through the Langflow API, pass tweaks or a session id, export or import flow JSON, create a Langflow API key, run a flow file without the server using lfx, connect Langflow flows to an MCP client, or upgrade Langflow without losing flows.Votes: 0GitHub stars: 155
- Lazygitlazygit is a keyboard-driven terminal interface for Git that makes staging single lines, interactive rebase, cherry-picking, bisecting and undoing mistakes a matter of a few keypresses. Use when a user asks to install lazygit, configure its config.yml, add custom commands or change keybindings, set up delta as its diff renderer, or wants to know which keys to press to squash, amend, cherry-pick or undo commits in lazygit.Votes: 0GitHub stars: 155
- LibrechatLibreChat is a self-hosted, ChatGPT-style web chat that puts OpenAI, Anthropic, Google, OpenRouter, Ollama and other providers behind one login, with agents, MCP tools, file search and per-user spending budgets. Use when deploying LibreChat with Docker Compose, editing librechat.yaml or .env, adding a custom endpoint, connecting MCP servers, closing registration or adding SSO, creating users, or updating an instance. Trigger phrases: "set up LibreChat", "self-hosted ChatGPT for the team", "ad...Votes: 0GitHub stars: 155
- Llama Cppllama.cpp runs large language and vision models locally from GGUF files on CPUs, Apple Silicon and GPUs, and serves them over an OpenAI-compatible HTTP API. Use when a user asks to run a model locally with llama.cpp, start llama-server or "llama serve", download a GGUF model from Hugging Face, host a local OpenAI-compatible endpoint, offload layers to the GPU, get embeddings or schema-constrained JSON from a local model, quantize a model to Q4_K_M, or benchmark tokens per second.Votes: 0GitHub stars: 155
- MarkitdownConverts PDF, Word, Excel, PowerPoint, HTML, CSV, EPUB, ZIP and other files into Markdown text that language models and search indexes can read. Use when a user asks to convert a document to Markdown, turn a PDF or DOCX into text for an LLM, export spreadsheet tables as Markdown, prepare files for RAG ingestion, batch-convert a folder of office documents, or mentions MarkItDown, "markitdown", or "document to markdown".Votes: 0GitHub stars: 155
- Material UiMaterial UI (@mui/material) is a React component library that implements Google's Material Design, with ready-made buttons, forms, dialogs, tables, layout grids and a theming system. Use this skill to add MUI to a React or Next.js App Router project, build a brand theme with createTheme and ThemeProvider, style components with the sx prop, set up dark mode with CSS theme variables, or upgrade v5-v7 code to the current v9 API with the official codemods. Trigger phrases: "use Material UI", "set...Votes: 0GitHub stars: 155
- MineruConverts PDFs, scanned pages, images and Office files into Markdown or structured JSON with MinerU, keeping headings, reading order, tables and formulas. Use when a user asks to turn a complex or scanned PDF into Markdown, extract tables from a PDF report, OCR a document for an LLM, batch-convert a folder of papers or reports, or let an agent read a long document page by page with citable locators. Runs locally on CPU or GPU; cloud parsing only when explicitly requested.Votes: 0GitHub stars: 155
- NeovimNeovim is a terminal text editor configured in Lua, with a built-in LSP client, Treesitter parsing and, since 0.12, a built-in plugin manager (vim.pack). Use this skill to install Neovim, write or repair an init.lua, add plugins, wire up language servers with vim.lsp.config and vim.lsp.enable, set up format-on-save, or run Neovim headless for scripted edits. Trigger phrases: "set up neovim", "fix my init.lua", "neovim LSP not working", "lspconfig deprecated warning", "add a plugin to nvim", "...Votes: 0GitHub stars: 155
- Open WebuiOpen WebUI is a self-hosted web chat interface for local and cloud language models that connects to Ollama and any OpenAI-compatible API. Use when a user asks to install or deploy Open WebUI with Docker or pip, connect Open WebUI to Ollama, llama.cpp, vLLM or OpenAI, configure it with environment variables, create the admin account without a browser, call the Open WebUI API for chat completions or RAG, upload files to a knowledge base, export or sync custom models, or update and back up an Op...Votes: 0GitHub stars: 155
- OpencodeOpenCode is an open-source AI coding agent that runs in the terminal, reads a codebase, edits files and runs shell commands using any of 75+ model providers or a local model. Use it to set up OpenCode, write opencode.json, choose models and providers, restrict permissions, create custom agents and slash commands, add MCP servers, or script it with `opencode run` in CI. Trigger phrases: "install opencode", "configure opencode.json", "use opencode with Ollama", "opencode run in CI", "opencode p...Votes: 0GitHub stars: 155
- OpenhandsOpenHands is an open-source autonomous coding agent that edits files, runs shell commands and works through multi-step software tasks with any LLM, from a terminal UI, a headless CI mode, a self-hosted web control center (Agent Canvas) or a Python SDK. Use when a user wants a model-agnostic, self-hostable coding agent: "run OpenHands on this repo", "fix this bug with OpenHands headless in CI", "set up OpenHands with a local Ollama model", "script an agent with the OpenHands SDK", "add an MCP ...Votes: 0GitHub stars: 155
- OpenspecOpenSpec is a command-line tool plus a set of slash commands that make an AI coding agent write a reviewable plan — proposal, requirements with scenarios, design and task list — before it changes any code. Use when a user asks to set up spec-driven development, run openspec init, propose a change with /opsx:propose, write a spec before coding, validate or archive an OpenSpec change, or keep requirements in the repository for Claude Code, Codex, Gemini CLI or Cursor.Votes: 0GitHub stars: 155
- Pandas AiPandasAI lets you ask questions about pandas DataFrames and CSV files in plain English, using an LLM that writes and runs the analysis code. Use when a user wants to chat with a DataFrame, query several tables together, generate charts from a prompt, or run PandasAI 3 with OpenAI or a local Ollama model.Votes: 0GitHub stars: 155
- PaperclipPaperclip is a self-hosted Node.js server and web dashboard that runs a team of AI coding agents (Claude Code, Codex, Gemini CLI, OpenCode, OpenClaw) as a company, with an org chart, goals, tasks, monthly budgets and approval gates. Use when someone wants to install or run Paperclip, hire agents, assign tasks to them, cap agent spend, or script it through the paperclipai CLI or its REST API. Phrases: "set up Paperclip", "run my agents like a company", "too many Claude Code tabs", "give each a...Votes: 0GitHub stars: 155
- Playwright McpPlaywright MCP is a Model Context Protocol server that lets an AI agent drive a real browser: it reads each page as a structured accessibility snapshot and clicks, types, and fills forms by element reference instead of guessing at pixels. Use when someone asks to "let the agent use a browser", "add the Playwright MCP server", "open the site and check it", "log in and click through the app", "reproduce this UI bug in the browser", "fill out this web form", or "keep the browser logged in betwee...Votes: 0GitHub stars: 155
- PortkeyPortkey is an AI gateway that sits between an app and LLM providers, adding fallbacks, load balancing, retries, caching, guardrails and request observability behind one OpenAI-compatible API. Use when someone asks to "add fallbacks between OpenAI and Anthropic", "cache LLM responses", "load balance LLM providers", "log LLM costs and latency" or "set up Portkey".Votes: 0GitHub stars: 155
- ReactBuilds and debugs React user interfaces: components, state, effects, forms and data loading, written the way React 19 expects. Use when someone asks to "create a React app", "build a React component", "fix a useEffect bug", "stop unnecessary re-renders", "upgrade to React 19", "turn on the React Compiler", "use Server Components", "handle a form with Actions" or "test a React component". Covers Actions, use, useActionState, useOptimistic, ref as a prop, Server and Client Components, Suspense,...Votes: 0GitHub stars: 155
- RustRust is a compiled, memory-safe systems programming language whose toolchain (rustup, rustc, Cargo, Clippy, rustfmt) builds, tests, lints and packages code. Use this skill to install or pin a Rust toolchain, start a crate or a multi-crate Cargo workspace, add dependencies, fix borrow-checker errors, design error handling with Result, gate CI on clippy and fmt, migrate to the 2024 edition, or ship an optimized release binary. Triggers: "set up Rust", "cargo new", "cargo workspace", "fix this b...Votes: 0GitHub stars: 155
- ScraplingFetches web pages and extracts structured data from them with Python, from a single HTTP request to a full crawl, including pages rendered by JavaScript and selectors that keep working after a site redesign. Use when a user asks to scrape a website, build a crawler or spider, extract product or listing data, follow pagination, scrape a JavaScript-rendered page, save a page as Markdown, or mentions Scrapling, "scrape this URL", or "my scraper keeps breaking".Votes: 0GitHub stars: 155
- Spec KitSpec Kit is GitHub's open-source toolkit that installs a set of agent commands into a project so a coding agent builds features from a written specification: specify, plan, tasks, implement, then converge against the spec. It also ships optional processes for bug fixing and for assessing an idea. Use when someone asks to "set up Spec Kit", "run specify init", "use spec-driven development on this repo", "write the spec before the code", "run /speckit-specify or /speckit-plan", "fix this bug wi...Votes: 0GitHub stars: 155
- Stirling PdfStirling PDF is a self-hosted web application with an HTTP API that merges, splits, compresses, converts, OCRs, watermarks and password-protects PDF files on your own server. Use when a user asks to deploy Stirling PDF with Docker, configure it with environment variables or settings.yml, call the Stirling PDF API from curl or Python, batch-process PDFs without uploading them to a cloud service, or chain several operations with the pipeline endpoint.Votes: 0GitHub stars: 155
- TrafilaturaDownloads web pages and extracts the main article text and metadata (title, author, date) without menus, ads, footers or other boilerplate, as plain text, Markdown, JSON, CSV or XML. Use when a user asks to extract article text from a URL, get clean text from HTML, turn a web page into Markdown for an LLM, build a text corpus from a site, list URLs from a sitemap or RSS feed, scrape blog posts with their publication dates, or mentions Trafilatura.Votes: 0GitHub stars: 155
- TypescriptSets up and repairs TypeScript projects: picks tsconfig.json settings for a Node.js service, an npm library or a bundled web app, runs type-checking in CI, and replaces `any` and unsafe casts with types the compiler can verify. Use when someone asks to "set up TypeScript", "fix this tsconfig", "fix a TypeScript error", "upgrade to TypeScript 6 or 7", "migrate JavaScript to TypeScript", "publish types for a package", "run .ts files in Node" or "make this type-safe". Covers the changed defaults...Votes: 0GitHub stars: 155
- UnslothUnsloth fine-tunes open LLMs such as Llama, Qwen and Gemma with LoRA or QLoRA about twice as fast and with far less GPU memory than a stock Hugging Face setup, then exports the result to GGUF for Ollama and llama.cpp or to merged weights for vLLM. Use it when someone wants to train a model on their own data on a single GPU, a Colab notebook or a workstation. Trigger phrases: "fine-tune Llama on my data", "QLoRA on a 16 GB GPU", "train Qwen with Unsloth", "export my fine-tune to GGUF", "make a...Votes: 0GitHub stars: 155
- UvInstalls Python packages, creates virtual environments, locks dependencies and manages Python versions with one fast command-line tool that replaces pip, pip-tools, pipx, poetry, pyenv and virtualenv. Use when a user asks to set up a Python project, add or upgrade a dependency, create a lockfile, migrate from requirements.txt, run a script with inline dependencies, install a Python version, run a tool with uvx, or speed up installs in CI and Docker.Votes: 0GitHub stars: 155
- VercelVercel CLI deploys websites, web apps and serverless functions to the Vercel platform from a terminal or CI job, and manages their environment variables, domains and logs. Use when a user asks to deploy to Vercel, create a preview deployment, ship to production, promote or roll back a deployment, add or pull Vercel environment variables, write a vercel.json, read build or runtime logs, or deploy from GitHub Actions with a Vercel token.Votes: 0GitHub stars: 155
- VoltagentVoltAgent is an open-source TypeScript framework for building AI agents with typed tools, persistent memory, supervisor/sub-agent teams, MCP tools, guardrails and suspendable workflows, served over a local HTTP API. Use when someone asks to "build an AI agent in TypeScript", "add tools and memory to an agent", "set up a supervisor with sub-agents", "pause a workflow for human approval", "connect an agent to an MCP server", or mentions VoltAgent, @voltagent/core or create-voltagent-app.Votes: 0GitHub stars: 155
- PULL REQUEST TEMPLATEBefore submitting, ensure your skill meets these requirements:Votes: 0GitHub stars: 142
- 3dsmax RenderingScripts and configures production rendering in Autodesk 3ds Max with the V-Ray and Corona renderers: output size and files, render elements, denoising, light mix, batch and command-line rendering, and network rendering. Use when a user asks to set up a production render, render several cameras in one batch, render from the command line or on a render farm, add render passes for compositing, or cut render time for archviz and product shots.Votes: 0GitHub stars: 142
- 3dsmax ScriptingCovers scripting Autodesk 3ds Max, the 3D modeling and rendering application, with MAXScript and Python (pymxs): scene manipulation, object creation, material assignment, camera and light setup, batch operations, and file I/O. Use when tasks involve automating repetitive 3ds Max workflows, batch processing scenes, running scripts headless with 3dsmaxbatch, creating custom tools, or scripting scene setup for archviz, product visualization, or VFX.Votes: 0GitHub stars: 142
- 3proxy3proxy is a small open-source proxy server that runs HTTP/HTTPS, SOCKS4/5, SNI and TCP/UDP port-mapping proxies from one config file. Use when a user asks to set up an HTTP or SOCKS5 proxy, add proxy users and passwords, write 3proxy access rules, chain or rotate upstream (parent) proxies, limit bandwidth, connections or monthly traffic per user, run 3proxy in Docker, or fix a 3proxy.cfg that will not start.Votes: 0GitHub stars: 142
- A2a ProtocolBuilds Agent2Agent (A2A) servers and clients, the open protocol (originally from Google, now under the Linux Foundation) that lets AI agents from different frameworks call each other. Use when the user wants to create an A2A-compliant agent, build an Agent Card, implement task management, connect agents across frameworks, set up agent discovery, handle streaming responses, implement push notifications, or orchestrate multi-agent workflows. Trigger words: a2a, agent to agent, agent2agent, a2a ...Votes: 0GitHub stars: 142
- Ab Test SetupPlans a controlled experiment (A/B test) so its result can be trusted: writes the hypothesis, picks one primary metric and the guardrails, computes sample size and run time, specifies how visitors are assigned and when exposure is logged, and reads out the result with a confidence interval. Use when someone says "set up an A/B test", "split test this page", "how many visitors do I need", "how long should the experiment run", "is this result significant", "can I stop the test early", or wants ...Votes: 0GitHub stars: 142
- AblyAbly is a hosted realtime messaging service: clients publish and subscribe to named channels over WebSockets, see who is present, replay message history, and resume after a dropped connection. Use when a user asks to "add realtime updates", "push live notifications to the browser", "show who is online", "add a chat room with typing indicators", "publish from a serverless function", or "authenticate Ably clients without exposing the API key". Covers the ably 2.x JavaScript SDK (Realtime and RE...Votes: 0GitHub stars: 142
- Accessibility AuditorAudit web pages and components for WCAG 2.2 accessibility compliance. Use when a user asks to check accessibility, find a11y issues, audit for WCAG compliance, fix screen reader problems, check color contrast, ensure keyboard navigation works, or prepare for accessibility regulations like the European Accessibility Act or ADA.Votes: 0GitHub stars: 142
- Aceternity UiAceternity UI is a collection of animated React components (3D cards, spotlight, background beams, moving borders, wavy backgrounds) built with Tailwind CSS and the motion library, installed into your project as source through the shadcn CLI. Use when someone asks for "animated hero section", "3D tilt card", "spotlight effect", "moving border button", "Aceternity component", or "glowing background" in a React or Next.js app.Votes: 0GitHub stars: 142
- ActRuns GitHub Actions workflows on your own machine in Docker containers with act, so CI can be tested without pushing. Use when a user asks to test GitHub Actions workflows locally, debug a failing CI pipeline, pass secrets or inputs to a local run, or run workflows offline.Votes: 0GitHub stars: 142
- ActivepiecesActivepieces is an open-source workflow automation platform with a visual builder, 400+ integrations ("pieces"), code steps, branching, loops, and webhooks. Use when a user asks to self-host a Zapier or n8n alternative, automate workflows with a no-code builder, build a custom integration piece, or set up open-source business automation.Votes: 0GitHub stars: 142