Tools

Drives a Next.js route to instant navigation under Cache Components: writes a failing @next/playwright instant() e2e test, pushes Suspense boundaries down to grow the static shell until it passes, and keeps the test as a regression guard. Requires Next.js 16.3+ with cacheComponents.

GitHub's official spec-driven development toolkit: the specify CLI sets up spec, plan and task workflows for Copilot, Claude Code, Codex and other agents so the spec comes before the code, plus bug-fix and idea-evaluation flows. Needs Python 3.11+ and uv.

UI design knowledge base skill: looks up UI styles, palettes, font pairings, charts and UX guidelines by product type and generates a full design system, covering 22 stacks including React, SwiftUI and Flutter. Needs Python 3 locally.

YC office hours skill from gstack: startup mode tests real demand, the narrowest wedge and future fit with six probing questions; builder mode brainstorms side projects, hackathons and open source. Ends with a design doc. Maintained by Garry Tan.

Skill pack from YC president Garry Tan: slash commands such as /office-hours, /plan-ceo-review, /review, /qa and /ship play CEO, engineering manager, designer, QA and release engineer. Needs Git and Bun; clone the repo and run ./setup as the README describes.

Local LLM inference engine in plain C/C++ with a command-line chat and an OpenAI-compatible HTTP server; pulls and runs GGUF models straight from Hugging Face. Supports Apple Silicon, CUDA, Vulkan and other hardware, plus low-bit quantization.

MCP server built into the official shadcn CLI: lets agents browse and search components, blocks and templates in any configured registry, including private ones, and install them into your project in plain language. The project needs a components.json.

Official shadcn/ui CLI: initializes projects and adds component source to your codebase on demand, with switchable presets. Since v4 it offers --dry-run and --diff so agents can preview changes, and it comes with an agent skill.

Official shadcn/ui skill: uses the shadcn CLI to read project config and component docs, then adds, searches, composes and fixes components following styling, form and accessibility rules. Can also start new projects from presets.

Local MCP server built into Browser Use: lets agents navigate, click, type and extract page content, or hand multi-step tasks to the built-in browser agent. Bring your own OpenAI or Anthropic API key.

Minimal, extensible terminal AI agent that can write its own prompt templates, skills, extensions and themes. Offers print, JSON and RPC modes for scripting, plus a TypeScript SDK. Needs Node.js 22.19+.

Makes the agent answer in terse 'caveman' style to cut output tokens, compressing only prose while leaving code, commands and errors intact. Includes a local proxy that compresses logs, test output and other input. Works with Claude Code, Codex and 30+ other agents.

Makes the agent reply in terse 'caveman' style, compressing only prose while keeping code, commands and errors intact, which cuts output tokens significantly. Comes with skills for short commit messages, code review and memory file compression; supports 30+ agents.

Multi-agent investment research framework where fundamental, sentiment, news and technical analysts, bull and bear researchers, a trader and risk managers debate a stock and produce a report and rating. Covers US, Hong Kong and A-shares. Needs Python and an LLM API key; not investment advice.

OpenAI's open-source general-purpose speech recognition model. The whisper command transcribes many languages, translates foreign speech into English and writes subtitle files. Needs FFmpeg; faster with a GPU.

JavaScript, TypeScript and WebAssembly runtime with built-in formatting, linting, testing and compilation. Scripts get no file, network or environment access unless granted with --allow-* flags, making agent-generated scripts safer to run.

For fuzzy requirements: the agent asks one question at a time with its own guess, clarifying users, motivation, success criteria and constraints, and restates the intent for your confirmation before planning. Needs you answering live, so not for unattended runs. From Addy Osmani's agent-skills.

Addy Osmani's production-grade engineering skill pack covering spec, planning, implementation, testing, review and shipping, with commands like /spec, /plan, /build, /test, /review and /ship. Supports both Claude Code and Codex.

Engineering skill collection spanning define, plan, build, verify, review and ship, with /spec, /plan, /build, /test, /review and /ship commands, including TDD, code review and web performance audits. By Addy Osmani.

Reviews code changes before merge across five axes: correctness, readability, architecture, security and performance. Works on code and PRs from you, other agents or other people, judged by whether they improve overall code health. Part of Addy Osmani's agent-skills.

Google's official open-source terminal agent using Gemini models with a 1M-token context. Built-in Google Search, file and shell tools, plus MCP support. Personal Google accounts get a free quota.

Helps agents build frontends that don't look templated: picks a design direction first, then tunes layout variance, motion intensity and information density. Also includes redesign audits, minimalist and brutalist styles, and design reference generation.

Microsoft's cross-browser end-to-end testing framework: one API drives Chromium, Firefox and WebKit, npx playwright test runs tests in parallel and isolation, with auto-waiting and trace replay for debugging failures.

All-in-one JavaScript and TypeScript toolchain: a single bun binary is a Node.js-compatible runtime, package manager, test runner and script runner, with noticeably faster installs and test runs.