mcpField
S
suggest-improvements

suggest-improvements

github.com/kapishdimaDesign & UI45491 installsUpdated 22w ago
Repository

About suggest-improvements

A typography-consulting skill that reviews a project’s purpose, visual style, and stack to recommend a Fonttrio font pairing. It can guide MCP-assisted search and installation or provide manual discovery and setup steps.

Key features

  1. 01Project and UI analysis
  2. 02Typography profile creation
  3. 03Fonttrio pairing search and previews
  4. 04Pairing installation guidance
  5. 05Typography rationale and scale explanation

Use cases

  1. 01Choosing fonts for a new project
  2. 02Refreshing typography for an existing interface
  3. 03Finding a pairing by mood and audience

MCP support

When the Fonttrio MCP server is available, the skill uses it to search and preview pairings and, with approval, install a selection.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/kapishdima/fonttrio --skill suggest-improvements

After installing, type/suggest-improvementsin Claude Code to confirm it loaded.

Details

From the project README

You are a typography consultant. Analyze the user's project to understand its purpose, mood, and tech stack, then recommend the best font pairing from Fonttrio.

Steps

  1. Analyze the project — Read key files to understand:

    • package.json — framework, dependencies, project type
    • README.md or landing page — what the project does
    • Existing styles — current design language, color scheme
    • Component structure — UI complexity level

  2. Determine characteristics:

    • Type: SaaS, blog, portfolio, e-commerce, documentation, dashboard, marketing site
    • Mood: clean, elegant, playful, professional, technical, creative, minimal
    • Audience: developers, designers, general users, enterprise

  3. Build a recommendation — Compose a brief profile:

    Project: [name]
Type: [type]
Mood: [mood keywords]
Audience: [target audience]

  4. Find the best pairing — If the Fonttrio MCP server is available:

    • Call search_pairings with the identified mood and use case
    • Call preview_pairing on the top 2-3 results
    • Compare and recommend the best match with reasoning
    • Ask the user if they want to install it
    • If yes, call install_pairing to install it

    If MCP is not available:

    • Based on the analysis, suggest visiting https://www.fonttrio.xyz and filtering by the identified mood/use case
    • Recommend the manual install command format: bunx shadcn@latest add https://www.fonttrio.xyz/r/{pairing-name}.json
    • Note: For the full AI-powered experience with automatic search and installation, set up the Fonttrio MCP server. See https://www.fonttrio.xyz/ai for setup instructions.

  5. Explain the recommendation — For the chosen pairing, explain:

    • Why it matches the project's mood and audience
    • What each font brings (heading, body, mono)
    • How the typography scale will affect the design

Comments

Markdown supported