tryproduck/produck-skills

Agent skills to help you build products your users love.

What it solves

Coding agents often struggle to translate vague user requests into high-quality, executable product requirements or to apply a professional "taste" to UI design. This project provides a collection of documentation-driven "skills" that teach agents how to handle product management and UX design tasks with a focus on user experience and product-market fit.

How it works

The project uses a standardized format of markdown files that act as instructions for AI coding agents (such as Claude Code, Cursor, and Copilot). These skills can be installed via a CLI tool (npx skills add) or as plugins. Some skills, like produck-feedback, integrate with the Produck MCP (Model Context Protocol) server to allow agents to search and retrieve real user feedback tickets, including session activity and design docs, to drive a build loop.

Who it’s for

Developers and product managers using AI coding agents to build and iterate on software products who want their agents to produce professional-grade PRDs and visually superior user interfaces.

Highlights

  • User Alignment: Converts messy user requests into structured, agent-executable PRDs with clear boundaries and acceptance criteria.
  • Taste Benchmark: Includes a rubric and verification loop to move agents from generic UI polish to high-quality visual hierarchy and trust.
  • Demo Studio: Enables agents to generate fully-animated product demo videos from a written brief using HTML, CSS, and GSAP.
  • MCP Integration: Provides tools for agents to pull in-context user feedback directly into the development workflow.

Related

  • Project
    BuilderIO/skills

    A collection of composable skills for coding agents that improve their autonomy, visual planning, and efficiency in software development tasks.

  • Project
    vibe-motion/skills

    A collection of specialized animation and motion graphics skills for AI agents to generate professional visual assets, ranging from 3D renders to brand promotional videos.

  • Project
    addyosmani/agent-skills

    Agent Skills is a library of 25 Markdown‑based engineering workflows (spec, plan, build, test, review, ship, etc.) that can be installed into many AI coding agents via a simple CLI. It provides slash commands, auto‑build mode, specialist personas, and reference checklists to make AI‑generated code follow senior‑engineer best practices across the entire development lifecycle.

  • Project
    MengTo/Skills

    A curated library of procedural agent skills and prompt playbooks designed to help AI coding agents build high-quality UIs, games, and frontend systems consistently.

  • Project
    RefoundAI/lenny-skills

    A library of 76 product management and engineering skills as markdown files that give AI agents specialized knowledge and workflows based on Lenny's Podcast and Newsletter.