Image Generation
Image generation mega skill for all AI image creation. Supports Nano Banana Pro (Gemini API), Higgsfield Soul ID, and reference-image workflows. Three modes: generate (from scratch), reference (match a screenshot's style), style-lock (use a saved client style config). Client style configs for Claudia, Ryan Magin, and all Viral Editz clients. Every video script gets image gen + video gen prompts for clone era. Triggers: "generate image", "make an image", "create a photo", "thumbnail", "style like", "match this style", "Claudia style", "podcast photo", image request for any client, reference ima
Install
npx skills add Dreydrey9000/claude-skills --skill image-generationgit clone --depth 1 https://github.com/Dreydrey9000/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/content-creation/image-generation ~/.claude/skills/image-generationPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Image Generation Mega Skill ## Models Supported | Model | Access Method | Best For | Resolution | |-------|-------------|----------|------------| | **Nano Banana Pro** | Gemini API (`gemini-3-pro-image-preview`) via Claude Code | Daily image gen, client content, thumbnails | 1K-4K | | **Higgsfield Soul** | Higgsfield web UI | Character consistency (Soul ID trained) | Up to 2K | | **Higgsfield Soul ID** | Higgsfield web UI | Training persistent characters | N/A (training) | | **Flux** | Higgsfield web UI | Alternative aesthetics | Up to 2K | **Default: Nano Banana Pro via Gemini API** — this is what we use in Claude Code. --- ## Three Modes ### Mode 1: GENERATE (From Scratch) Create an image from a text description. No reference needed. **When to use:** Client needs a new image for a scene that doesn't exist yet. **Prompt Formula (Nano Banana Pro):** ``` [Identity Anchor] + [Scene Description] + [Wardrobe] + [Action/Pose] + [Lighting] + [Background] + [Framing] + [Style/Mood] ``` **The Six Variables (Higgsfield Official):** 1. **Subject** — Who/what specifically (not generic) 2. **Composition** — Camera angle, lens, framing 3. **Action** — What's happening (movement, gesture, expression) 4. **Location** — Where, with atmospheric detail 5. **Style** — Art direction (cinematic, editorial, raw UGC, etc.) 6. **Negative guidance** — What to exclude (blur, artifacts, distortion) ### Mode 2: REFERENCE (Match a Screenshot)
Details
- Skill name
image-generation- Repository
- Dreydrey9000/claude-skills
- Path
content-creation/image-generation/SKILL.md- Repo updated
- 18 March 2026
FAQ
What does the Image Generation skill do?
Image generation mega skill for all AI image creation. Supports Nano Banana Pro (Gemini API), Higgsfield Soul ID, and reference-image workflows. Three modes: generate (from scratch), reference (match a screenshot's style), style-lock (use a saved client style config). Client style configs for Claudia, Ryan Magin, and all Viral Editz clients. Every video script gets image gen + video gen prompts for clone era. Triggers: "generate image", "make an image", "create a photo", "thumbnail", "style like", "match this style", "Claudia style", "podcast photo", image request for any client, reference ima
How do I install the Image Generation skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add Dreydrey9000/claude-skills --skill image-generation. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Image Generation popular?
It lives in Dreydrey9000/claude-skills, which has 5 GitHub stars and 0 forks.
Related skills
Podcast Generation
5Dreydrey9000/claude-skills
Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket. Use when building text-to-speech features, audio narrative generation, podcast creatio...
Autonomous Agents
5Dreydrey9000/claude-skills
Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable - it'...
Stripe Integration
5Dreydrey9000/claude-skills
Implement Stripe payment processing for robust, PCI-compliant payment flows including checkout, subscriptions, and webhooks. Use when integrating Stripe payments, building subscription systems, or ...
Polisher Skill
5Dreydrey9000/claude-skills
Your Viral Editz VES Director guiding polishers through clean, minimal, data-backed visual polishing for high-level personal brands. Analyzes scripts to identify exactly where to add visuals, enhance hooks, and format subtitles using proven viral patterns—no effects, no music, just custom client visuals.
Clipper Skill
5Dreydrey9000/claude-skills
Transform timestamped video transcripts into precise editing directions for viral short-form content. Analyzes existing footage using Viral Editz NR framework (Narrative + Retention), provides timestamp-specific cuts/reorders/text overlays, and optimizes for maximum views using proven viral psychology.
Video Intelligence
5Dreydrey9000/claude-skills
Autonomous video editing using AI-powered video intelligence. Combines Hume AI (emotion detection), Twelve Labs (video understanding), PySceneDetect (scene boundaries), and MediaPipe (face tracking auto-reframe) to automatically find viral moments, detect energy peaks, and edit videos without manual scrubbing. Use when the user wants to automate video editing, find viral clips autonomously, or process videos end-to-end.
Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.