Skills for Real Engineers. Straight from my .agents directory.
gpt-image-skill
Agent skill fromfeiskyer/claude-code-settings
Generate or edit images using OpenAI GPT Image API (gpt-image-2, gpt-image-1, etc). Use ONLY when the user explicitly names OpenAI or GPT as the provider: "gpt image", "openai image", "generate image with openai", "用 openai 画图", "用 GPT 生成图片". For generic image requests without a provider, use nanobanana-skill instead. Do NOT use for diagrams (架构图/流程图) — draw those with Mermaid or code.
How to install gpt-image-skill
npx skills add feiskyer/claude-code-settings# or add only this skill to Claude Code: copy the folder
skills/gpt-image-skill/
# into
~/.claude/skills/gpt-image-skill/ (all projects)
.claude/skills/gpt-image-skill/ (one project)
1# GPT Image Skill23Generate or edit images using OpenAI's GPT Image models through a bundled Python script.45## Requirements671. **OPENAI_API_KEY**: Must be configured in `~/.gpt-image.env` or `export OPENAI_API_KEY=<your-key>`82. **OPENAI_API_BASE** (optional): Custom API base URL for compatible endpoints (e.g. Azure OpenAI, proxies). Set in `~/.gpt-image.env` or export it.93. **Python3 with dependencies**: openai, Pillow. Install via `python3 -m pip install -r ${CLAUDE_SKILL_DIR}/requirements.txt` if not installed yet.104. **Executable**: `${CLAUDE_SKILL_DIR}/gpt_image.py`1112## Instructions1314### For image generation15161. Ask the user for:17 - What they want to create (the prompt)18 - Desired size (optional, defaults to 1024x1024)19 - Output filename (optional, auto-generates UUID-based name if not specified)20 - Model preference (optional, defaults to gpt-image-2)21 - Quality (optional, defaults to auto)22 - Number of images (optional, defaults to 1)23242. Run the script:2526 ```bash27 python3 ${CLAUDE_SKILL_DIR}/gpt_image.py --prompt "description of image" --output "filename.png"28 ```29303. Show the user the saved image path when complete.3132### For image editing33341. Ask the user for:35 - Input image file(s) to edit (up to 3)36 - What changes they want (the prompt)37 - Output filename (optional)38392. Run with input images:4041 ```bash42 python3 ${CLAUDE_SKILL_DIR}/gpt_image.py edit --prompt "editing instructions" --input image1.png image2.png --output "edited.png"43…
Excerpt shown under the repository's MIT license.
More skills in claude-code-settings
Similar skill repositories
Public repository for Agent Skills
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
