OpenParable
Skip to content
← Back to skills

Suggest Improvements

Design
suggest-improvements

Suggest Improvements is an Agent Skill for design published in the kapishdima/fonttrio repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Analyze your project and suggest the best font pairing

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/kapishdima/fonttrio/blob/HEAD/skills/suggest-improvements/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/suggest-improvements, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

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