TC
Thumbnail Creator Skill (via Gemini)
🟡 Experimental🕐 updated 2026-06-08
🔷 SkillSpec L3
pm-writers
Generate article or newsletter thumbnail candidates using the Gemini API from inside Claude Code. Claude reads article copy, proposes composition concepts, writes image generation prompts incorporating brand specs, calls Gemini to generate the images, evaluates the results via computer vision, and returns ranked candidates with rationale. Use when asked to create thumbnails, generate cover images, or produce visual candidates for an article or newsletter.
🗣 Say this to your agent
“Create thumbnails for this article”“Generate cover image candidates for my newsletter”“Make me 4 thumbnail options for this post”“Can you generate some thumbnail ideas using Gemini?”“I need a featured image for this article — use my brand colours”
What to give it
▸Article copy or URL — Paste the full article text, or provide a URL to fetch. Used to extract themes, hooks, and key claims for composition.
▸Brand colours — Hex codes or descriptive names. E.g. `#1A1A2E` (navy), `#E94560` (coral). If not provided, Claude uses clean neutral defaults.
▸Fonts / type style — E.g. "bold sans-serif", "editorial serif", "Neue Haas Grotesk". Used in prompt to guide text treatment.
▸Style reference description — E.g. "flat illustration, minimal, like Stripe's marketing site" or "photorealistic, dark background, high contrast". A style image URL can also be provided.
▸Output dimensions (optional) — Defaults to `1792x1024` (landscape, standard article thumbnail). Options: `1024x1024` (square), `1024x1792` (portrait/mobile).
▸Number of candidates (optional) — Defaults to 4. Min 1, max 8 (API limits and cost).
▸Article title (if different from H1) (optional) — Used as the primary text element in image prompts.
▸Candidate selection (optional) — After proposing compositions, Claude asks which to generate. User can say "all" or pick by number.
✅ The bar it holds itself to
Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.
✓Before marking the task complete, verify each item:
✓`GEMINI_API_KEY` environment variable confirmed set before any API calls
✓`generate_image.py` script exists in project root — created from template if missing
✓All Python dependencies installed and verified (`google-generativeai`, `Pillow`)
✓Composition proposals were presented and user confirmed which to generate before any API calls
✓Each composition proposal is specific to this article's content — not generic placeholders
✓Brand colours (hex codes) are included in the image generation prompts
✓Negative prompt appended to every image generation prompt
⚠️ What it refuses to do
Do not generate thumbnails without incorporating brand colours and style specs when provided — off-brand outputs must be regenerated
Do not skip the evaluation step — all candidates must be scored before being presented to the user
Do not present only one thumbnail candidate — always generate multiple options for comparison
Do not include the full image generation prompts in a separate document — they must be included in the evaluation report for iteration reference
Do not claim a thumbnail is final without offering an iteration round
Install
npx pm-claude-skills add --agent claude # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcpStart with
Related skills
🔌 Embed this skill
Drop this on your blog, docs, or site — it renders a "Run this skill" card:
<div data-pm-skill="thumbnail-creator"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>💬 Discussion
Thumbnail Creator Skill (via Gemini) is one of 1174 open-source professional AI agent skills — all SkillSpec L3.
Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog