SkillAgentSearch skills...

kv-design

Generate professional Key Visual (KV) design proposals and images; use when you have a slogan/copy and a marketing scenario but need a clear visual direction and a ready-to-generate image prompt.

Install / Use

npx skills add aipoch/medical-research-skills --skill kv-design

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

82/100

Category

Marketing

Supported Platforms

Universal

Our assessment of kv-design

kv-design scores 82/100 on our quality scale, 557th of 642 Marketing skills we index.

Its SKILL.md is 3.8 KB long, well organised into 9 sections and no code examples: a solid amount of guidance for an agent.

With 1,916 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
26/30
Structure
13/20
Description
15/15
Adoption
14/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so kv-design is actively maintained.
  • Our last check on 2026-11-07 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-09-30. Automated pattern scan on 2026-09-30. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

kv-design compared with similar skills

All 4 of these similar skills score higher than kv-design; compare them before choosing.

SkillScoreStarsUpdatedFormat
kv-design (this skill)by aipoch821.9k2mo agoSKILL.md
taste-skillby Leonxlnx100116.8k8d agoCLAUDE.md
Agent-Reachby Panniantong100112.3k9d agoCLAUDE.md
Claude-Code-Game-Studiosby Donchitos10039.7k7d agoCLAUDE.md
LocalAIby mudler10050.4ktodayMCP Server

Frequently asked questions

How do I install kv-design?
Run npx skills add aipoch/medical-research-skills --skill kv-design. The install tabs above show the steps for each supported agent.
Which AI agents does kv-design work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is kv-design safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is kv-design still maintained?
The repository was last updated about 2 months ago, so kv-design is actively maintained.

name: kv-design description: Generate professional Key Visual (KV) design proposals and images; use when you have a slogan/copy and a marketing scenario but need a clear visual direction and a ready-to-generate image prompt. license: MIT author: AIPOCH

Source: https://github.com/aipoch/medical-research-skills

When to Use

  • Brand marketing campaigns where you need a hero visual that matches brand tone and supports headline/copy overlay.
  • Event promotions (e.g., seasonal sales, product launches) requiring a strong focal point and clear layout guidance.
  • Website/app banners that must fit specific aspect ratios and maintain readable negative space for text.
  • Social media hero creatives where you need fast iteration from vague requirements to a consistent visual direction.
  • Pitching multiple design directions to stakeholders (e.g., 2–3 KV concepts with distinct styles and compositions).

Key Features

  • Converts vague KV requirements into professional design directions (visual focus, layout suggestions, style details).
  • Produces image-generation-ready prompts optimized for KV composition and marketing readability.
  • Encourages negative space planning for copy placement and subject prominence for attention capture.
  • Supports common KV constraints: scenario-driven style, main color tone, and size/ratio intent.

Dependencies

  • Python 3.10+
  • Required Python packages:
    • zhipuai
    • requests
  • ZhipuAI API access via environment variable:
    • ZHIPUAI_API_KEY (required)

Example Usage

1) Collect KV Requirements

Prepare the following information:

  • Project/Brand Name
  • Core Slogan/Copy (the “soul” of the KV)
  • Usage Scenario (e.g., New Product Launch, Black Friday Sale, Website Banner)
  • Style Preference (e.g., 3D render, minimalist, illustration)
  • Main Color Tone
  • Size/Ratio Requirements (even if the script defaults to one, capture the user’s intent)

2) Analyze the Design Direction

Use the KV Design Analysis Prompts in:
references/design_prompts.md

Process:

  1. Open KV Design Analysis Prompts.
  2. Fill in the collected information into [KV Design Requirements].
  3. Generate:
    • Visual Focus
    • Layout Suggestions
    • Style Details

3) Generate the KV Image Prompt

Use the KV Image Prompt Generation Prompts in:
references/design_prompts.md

Process:

  1. Open KV Image Prompt Generation Prompts.
  2. Fill in:
    • [Basic Requirements]
    • [Design Proposal] (from Step 2)
  3. Generate the final optimized image prompt.

4) Generate the KV Image (Runnable)

  1. Ensure the API key is set:

    export ZHIPUAI_API_KEY="YOUR_KEY_HERE"
    
  2. Run the script with the generated prompt:

    python scripts/generate_kv.py "<generated_prompt>"
    
  3. After completion, return the generated image file path to the user.

Implementation Details

  • Two-stage prompting workflow

    1. Design analysis stage: transforms requirements into actionable design guidance (focus, layout, style).
    2. Prompt generation stage: converts the design guidance into a production-ready image prompt.
  • KV composition constraints

    • Negative space: reserve clean areas for headline/subcopy overlays; avoid overly busy backgrounds.
    • Subject prominence: ensure the primary subject (product/concept) is visually dominant and attention-grabbing.
  • Parameters to capture early

    • Scenario drives composition and tone (e.g., “sale” vs. “premium launch”).
    • Style preference constrains rendering approach (3D/illustration/minimal).
    • Main color tone ensures brand consistency.
    • Aspect ratio/size intent informs layout planning even if generation defaults to a preset.

Related Skills

View on GitHub
GitHub Stars1.9k
CategoryMarketing
Updated2mo ago
Forks175

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions