aravinds-wick/aravindhan-skills/article-thumbnails

Claude Code and agent skill by aravinds-wick/aravindhan-skills

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Generate article and newsletter thumbnail candidates using the Gemini API. Analyzes article copy, constructs image prompts matching brand specs, calls the model, and evaluates candidates. Use when the user runs /article-thumbnails, asks to create a newsletter/article thumbnail, or wants image candidates for an article.

Install

npx vskill@latest install aravinds-wick/aravindhan-skills/article-thumbnails

SKILL.md

The same SKILL.md was published earlier as aravinds-wick/aravindhan-skills/article-thumbnails.

Article Thumbnails (article-thumbnails)

Generates and evaluates brand-appropriate thumbnail candidates for articles or newsletters using Gemini models.

Prerequisites

  • Requires GEMINI_API_KEY to be set in the environment.

Step-by-Step Instructions

1. Analyze Article Copy
  • Read the article text or link provided by the user.
  • Identify the core theme, key concepts, tone (e.g. technical, casual, minimal), and metaphoric visual ideas.
2. Suggest Visual Concepts

Propose 3 distinct visual compositions based on the article's theme and your brand guidelines.

  • Concept 1 (Conceptual): Abstract representation of the core idea.
  • Concept 2 (Literal/Concrete): Showing a practical scenario or object.
  • Concept 3 (Minimalist/Graphic): Strong typography and simple icons/shapes.
3. Generate Image Candidates

Ask the user to select their preferred concept. Once selected:

  • Construct a detailed image generation prompt following Gemini best practices (specifying subject, style, lighting, composition, and color palette).
  • Call your Gemini image generation script or tool with the prompt:

``bash python3 scripts/call_gemini_image.py --prompt "{detailed_prompt}" --candidates 3 ``

  • Save the resulting images in a local assets/ folder.
4. Evaluate and Select
  • Use your Vision capabilities to inspect the generated candidate images.
  • Review each candidate against your brand specifications (correct logo colors, text alignment, and aesthetic appeal).
  • Present the best candidates to the user with a brief rationale for each.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/aravinds-wick/aravindhan-skills/article-thumbnails/badge)](https://verified-skill.com/skills/aravinds-wick/aravindhan-skills/article-thumbnails)

Something wrong with this skill or its page? Tell us.