image-anton-abyzov-specweave

npx skills add majiayu000/claude-skill-registry --skill image-anton-abyzov-specweave --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

# Image Generation Skill Generate images from text prompts using AI models. Uses a 3-tier fallback chain to maximize reliability. ## Provider Fallback Chain (Follow This Order) ``` Tier 1: Gemini Native (FREE) ─── gemini-2.5-flash-image ──┐ ↓ on error │ gemini-3-pro-image-preview ────────────────────────┤ ↓ on error │ Tier 2: Pollinations.ai (FREE, no key) ───────────────────┤ ↓ on error │ Tier 3: Imagen 4 (PAID, billing required) ────────────────┘ ``` **Key**: Gemini native models generate images via the same `generateContent` API used for text - they're FREE with a daily quota. Imagen 4 uses a separate paid `:predict` endpoint. ## Workflow ### Step 1: Parse User Request Extract from the user's prompt: - **Subject**: What to generate (e.g., "a sunset over mountains") - **Style**: Photorealistic, illustration, painting, etc. (default: photorealistic) - **Output path**: Where to save (default: `./generated-media/`) - **Count**: How many images (default: 1) ### Step 2: Prepare Output Directory ```bash mkdir -p ./generated-media ``` ### Step 3: Load API Key from .env ```bash # Source .env if it exists (for GEMINI_API_KEY) if [ -f .env ]; then export $(grep -E '^GEMINI_API_KEY=' .env |

mkdir -p ./generated-media
Source .env if it exists (for GEMINI_API_KEY)
if [ -f .env ]; then
export $(grep -E '^GEMINI_API_KEY=' .env | xargs)
fi
Also check parent dirs (monorepo support)
if [ -z "$GEMINI_API_KEY" ] && [ -f ../.env ]; then
export $(grep -E '^GEMINI_API_KEY=' ../.env | xargs)
if [ -n "$GEMINI_API_KEY" ]; then
for MODEL in "gemini-2.5-flash-image" "gemini-3-pro-image-preview"; do