Skip to content
store
taste-design

Self-hosted alternatives to taste-design

5 self-hosted AI Skills apps to use instead, best rated first.

Top picks

  1. C

    claude-to-deerflow

    Launch

    claude-to-deerflow is an agent skill that lets an assistant send messages and questions to a running DeerFlow instance through its HTTP API. DeerFlow is an AI agent platform built on LangGraph that orchestrates sub-agents for research, code

    Self-hosted

  2. O

    open-notebook

    Launch

    open-notebook is an agent skill for organising research with Open Notebook, a self-hosted alternative to NotebookLM. It arranges sources, notes and AI conversations into research notebooks. Sources can be PDFs, web pages, audio, video and O

    Self-hosted

  3. R

    Reactive Resume

    Launch

    Reactive Resume is a free and open-source resume builder for writing resumes and cover letters, checking the work, and tracking job applications. You create a free account, import an existing resume or start from scratch, and see the finish

    Open sourceSelf-hosted

  4. S

    self-hosted-funnel-launch

    Launch

    Self-hosted funnel launch is an agent skill that takes a funnel from an empty install to published on infrastructure you control, using the Autonnel funnel builder, which is licensed Apache-2.0. The result covers a landing page, checkout, a

    Self-hosted

  5. G

    get-convex/convex-backend

    Launch

    Convex is an open-source reactive database for web app developers. It combines a database, a place to write server functions in pure TypeScript, and client libraries that keep the app's data live, so screens update as the data changes. Beca

    Self-hosted

About taste-design

T

taste-design

Generates semantic design system files

taste-design is an agent skill that generates DESIGN.md files for Google Stitch, so that the screens Stitch generates follow a premium, non-generic visual style. The skill translates a set of frontend design rules into the natural-language and value-based format that Stitch's AI agent can interpret. A generated file describes the visual atmosphere, color calibration, typography rules, component behavior, layout principles and motion philosophy, and it pairs each description with precise values such as colors, type specifications and component behaviors. The file then acts as the single source of truth for prompting Stitch, so each new screen fits the same design language. Stitch interprets design through visual descriptions supported by those specific values, which is why the skill writes both. The prerequisites are access to Google Stitch through labs.google.com/stitch, and optionally the Stitch MCP server for use with Cursor, Antigravity or Gemini CLI. The skill is part of the Google Labs stitch-skills collection. The skills.sh listing shows Gen Agent Trust Hub, Socket and Snyk all passed.

View taste-designAll AI Skills apps
Price
Free
Made by
google-labs-code
Category
AI Skills
Website
github.com/google-labs-code/stitch-skills/taste-design