skill-stack-thumbnails
Generate blog post thumbnails for Skill Stack using the brand aesthetic. Follows an iterative workflow - brainstorm concepts, get approval, generate with Gemini API.
Best use case
skill-stack-thumbnails is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Generate blog post thumbnails for Skill Stack using the brand aesthetic. Follows an iterative workflow - brainstorm concepts, get approval, generate with Gemini API.
Teams using skill-stack-thumbnails should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/images/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How skill-stack-thumbnails Compares
| Feature / Agent | skill-stack-thumbnails | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Generate blog post thumbnails for Skill Stack using the brand aesthetic. Follows an iterative workflow - brainstorm concepts, get approval, generate with Gemini API.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Skill Stack Thumbnail Generator Generate on-brand thumbnails for Skill Stack blog posts using Google's Gemini API. ## Brand Identity **Skill Stack** is a curated repository of SKILL.md files for content creators. The aesthetic is: - **Clean and minimal** - Anthropic-adjacent sophistication - **Paper/document metaphor** - Skills as stackable knowledge artifacts - **Terracotta accent** - Single warm pop of color - **Editorial quality** - Think publishing meets productivity ### Logo Reference The logo is 4 stacked paper documents: - 3 gray layers (light → medium → darker) - 1 terracotta top layer with folded corner - Warm cream background - Subtle shadows for depth ## Color Palette | Role | Color | Hex | |------|-------|-----| | **Primary Accent** | Terracotta/Coral | `#D4654A` | | **Background** | Warm Cream | `#F5F3EE` | | **Paper Light** | Light Gray | `#E8E6E1` | | **Paper Medium** | Medium Gray | `#DEDBD5` | | **Paper Dark** | Darker Gray | `#D4D1CB` | | **Text/Line** | Near-Black | `#2D2D2D` | **Rule**: Terracotta appears on ONE element only per image. --- ## Workflow ### Step 1: Understand the Post Read the post title and content to understand: - What's the core concept? - What metaphor would resonate? - What visual would make someone click? ### Step 2: Brainstorm Concepts (APPROVAL REQUIRED) Generate 4-5 visual concepts. Each should be: - **One sentence** describing the visual - **Concrete** - you can picture it instantly - **Non-generic** - no lightbulbs, handshakes, arrows - **On-brand** - fits the paper/document aesthetic **Format for presenting concepts:** ``` ## Thumbnail Concepts for "[Post Title]" 1. **[Short label]** - One sentence visual description. Why it works. 2. **[Short label]** - Description... 3. **[Short label]** - Description... 4. **[Short label]** - Description... Which direction resonates? I can refine from there. ``` **Wait for user approval before proceeding.** ### Step 3: Develop the Prompt Once user selects a concept, expand into full prompt: ``` Create a minimal editorial thumbnail for a blog post about [TOPIC]. CONCEPT: [Expand the selected concept into 2-3 sentences] STYLE: Clean, flat editorial illustration with paper-like shapes and subtle shadows. Think Anthropic brand guidelines meets publishing design - sophisticated, minimal, intentional. NOT photorealistic. NOT glossy AI aesthetic. NOT busy. COMPOSITION: - Focal element offset to [left/right third] - Generous negative space (40%+ of frame empty) - Single clear focal point - Asymmetrical balance COLOR PALETTE: - Background: warm cream, almost off-white (like #F5F3EE) - Primary accent: terracotta/burnt coral (like #D4654A) on ONE key element only - Supporting: light gray and medium gray tones for layered paper shapes - Shadows: soft, subtle, not harsh drop shadows TEXTURE: Matte paper quality. Flat shapes with slight edge shadows. No glossy renders. No gradients. No photorealism. AVOID: - Busy compositions - More than 2-3 distinct elements - Photorealistic rendering - Cliche imagery (lightbulbs, gears, arrows) - Neon or saturated colors - Gradients - Glossy AI aesthetic - Text or words in the image FORMAT: 16:9 landscape aspect ratio for blog thumbnails ``` ### Step 4: Generate Run via Gemini API: ```bash cd scripts/images export GEMINI_API_KEY=$(grep GEMINI_API_KEY ../../.env.local | cut -d= -f2) python3 generate_image.py "PROMPT" --output ../../public/images/thumbnails --name "post-slug" ``` Or use the `/gemini-imagegen` skill if available. ### Step 5: Review & Iterate After generation: - **80% good?** Request specific edits - **Composition off?** Adjust framing language - **Wrong vibe?** Simplify further or try different concept - **Too busy?** Remove elements --- ## Concept Templates by Post Type ### Framework Posts (CODER, 4S, etc.) - Stacked/layered shapes representing steps - Flow diagrams with paper elements - Numbered paper cards in sequence ### Philosophy/Thesis Posts - Transformation metaphors (rough → polished) - Contrast/juxtaposition of two elements - Single powerful symbol ### Tool/Technical Posts - Tool icon + paper document interaction - Simple geometric representation - Integration/connection visual ### How-To/Practical Posts - Action in progress (folding, stacking, organizing) - Before/after implied through arrangement - Single focused action --- ## Example Concepts **For "The 4S Framework":** 1. **Four stacked squares** - Four paper squares arranged diagonally ascending, each labeled S1-S4, top one terracotta 2. **Funnel of papers** - Four documents funneling into one polished output 3. **Compass with 4 points** - Vintage compass where N/E/S/W are replaced by the 4 S's 4. **Building blocks** - Four cube shapes stacking, architectural quality **For "Transform Don't Generate":** 1. **Crumpled to crisp** - Crumpled paper ball on left, crisp folded document on right, terracotta accent on the crisp one 2. **Rough cut to gem** - Raw stone transforming into faceted shape 3. **Sketch to blueprint** - Messy sketch evolving into clean technical drawing --- ## Output Location Save thumbnails to: `public/images/thumbnails/[post-slug].png` Reference in frontmatter: `image: "/images/thumbnails/[post-slug].png"` --- *Always get concept approval before generating. The thinking is as important as the image.*
Related Skills
skill-stack-newsletter-writer
Format and structure skill for Skill Stack weekly newsletter. Handles frontmatter, sections, skill packages, and calls-to-action. REQUIRES writing-style skill for prose quality.
x-viral-template-miner
When the user wants to find proven-to-travel post templates in their niche and adapt them to their own product. Also use when the user mentions "what's going viral in my space", "what are competitors posting", "copy a viral post", "trending on X", "post ideas", "template mining", or "what to post this week". This is trend hunting, not plagiarism — the output is a template the user fills with their own assets.
x-linkedin-content-relay
When the user has X (Twitter) content that performed well and wants to relay it to LinkedIn 1-2 weeks later with reframing. Also use when the user mentions "repost to LinkedIn", "LinkedIn version of my tweet", "X to LinkedIn", "delayed repost", "LinkedIn for non-tech audience", or "LinkedIn relay". Also use when the user's ICP is non-tech and X is secondary — LinkedIn is the primary channel and this skill produces the content.
x-launch-video-structure
When the user is planning, scripting, or editing a product launch video for X (Twitter) and needs the structure. Also use when the user mentions "launch video", "demo video", "product launch on X", "60 second demo", "how to structure a launch", or "my launch video isn't working". Produces a beat-by-beat timing sheet, not copy.
x-account-warmup
When a user wants to grow an X (Twitter) account from zero before a product launch, or asks how to get first followers, warm up the algorithm, hit ~500-1,000 followers, or prepare an account to make a launch video land. Also use when the user mentions "new X account", "warm up my Twitter", "first 1000 followers", "building in public strategy", "X growth", or "engagement before launch".
youtube-ingest
Transcribe YouTube videos and playlists using Gemini Flash
web-scrape
Scrape web pages to clean markdown with optional AI summaries
voice-tyler-cowen
Write in Tyler Cowen's style - matter-of-fact, understated, treats enormous ideas as obvious observations. Read the passages. Absorb the flatness. Channel the HOW, not the content.
voice-trung-phan
Generate tweets and threads in the style of Trung Phan. Not just voice — captures his humor mechanics, format taxonomy, topic selection filter, and structural patterns. Use for trend-reactive tweets, meme commentary, and business/culture threads.
voice-levine-berry
Write in a combined Matt Levine + Wendell Berry voice. Levine's dry logic-walking and parenthetical humor for the analytical sections. Berry's meditative patience for the human ones. Read the passages. Absorb the rhythm. Channel the HOW, not the content.
voice-dan-koe
Write long-form essays and newsletters in Dan Koe's voice — philosophical depth made accessible, staccato rhythm with expansive passages, confident authority, zero hedging. Structured as a teaching conversation with bad-AI/correction/good-version rounds reverse-engineered from his actual articles. Use for newsletters, X articles, blog essays, or any long-form content that needs to blend philosophy with practical frameworks.
skill-extractor
Extract actionable Claude Code skills from raw source material — transcripts, conversations, workflows, expertise dumps. This skill identifies repeatable, promptable workflows embedded in content and scores them by leverage. Use when processing a corpus (podcast transcripts, blog posts, course material) to discover what skills could be built from it.