메뉴
Generate images using AI (OpenAI GPT Image or Stability AI). Use when the user asks to generate an image, create an AI image, make an illustration, or produce artwork from a text prompt.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | generate-image |
| description | Generate images using AI (OpenAI GPT Image or Stability AI). Use when the user asks to generate an image, create an AI image, make an illustration, or produce artwork from a text prompt. |
| argument-hint | ["prompt description"] |
| allowed-tools | Bash(*), Read, Write |
Generate images from text prompts using OpenAI GPT Image (gpt-image-2 / gpt-image-1 / variants) or Stability AI (SD 3.5 Large).
~/.agents/tools/generate-image.py~/.agents/tools/.env (contains OPENAI_API_KEY and STABILITY_API_KEY)/v1/models 2026-05-15)| Model ID | Notes |
|---|---|
gpt-image-2 | Flagship. Released 2026-04-21. Best prompt adherence, best photorealism. Default when image quality matters. |
gpt-image-2-2026-04-21 | Pinned dated variant of gpt-image-2 |
gpt-image-1.5 | Intermediate release between 1 and 2 |
gpt-image-1-mini | Smaller/cheaper gpt-image-1 variant — use for batch/draft generation where cost matters |
gpt-image-1 | Original gpt-image. Still works; superseded by gpt-image-2. |
chatgpt-image-latest | Always-current alias of the model ChatGPT.com uses (currently gpt-image-2-class). Use when you want "whatever ChatGPT uses today" |
dall-e-3 | Legacy fallback. Different quality semantics (standard/hd, not low/medium/high). |
Pass any of these to --model. The script branches on gpt-image* for the quality/format handling, so all gpt-image-* variants work out of the box.
Default in the script is now gpt-image-2 (the flagship) — pass --model gpt-image-1-mini for cheap batch/draft work.
python ~/.agents/tools/generate-image.py \
--prompt "a sunset over mountains, oil painting style" \
--output ./sunset.png \
--model gpt-image-2 \
--quality high
python ~/.agents/tools/generate-image.py \
--prompt "a sunset over mountains, oil painting style" \
--output ./sunset.png
python ~/.agents/tools/generate-image.py \
--prompt "modern logo design for a tech company" \
--output ./logo.png \
--size 1024x1024 \
--quality high
python ~/.agents/tools/generate-image.py \
--prompt "abstract digital art with blue tones" \
--output ./banner.png \
--size 1536x1024
python ~/.agents/tools/generate-image.py \
--prompt "portrait of a futuristic city" \
--output ./city.png \
--size 1024x1536
python ~/.agents/tools/generate-image.py \
--prompt "a minimalist cat icon, flat design" \
--output ./icon.png \
--background transparent
python ~/.agents/tools/generate-image.py \
--prompt "watercolor painting of a garden" \
--output ./garden.png \
--provider stability
| Option | Description |
|---|---|
--prompt, -p | (Required) Text prompt describing the desired image |
--output, -o | (Required) Output file path |
--provider | openai (default) or stability |
--size | Image size for OpenAI: 1024x1024 (default), 1536x1024 (wide), 1024x1536 (tall) |
--quality | OpenAI quality: low, medium (default), or high |
--background | OpenAI background: auto (default), transparent, or opaque |
--model | Override model (default: gpt-image-2 for OpenAI, sd3.5-large for Stability) |
| Feature | OpenAI gpt-image-2 | OpenAI gpt-image-1 | Stability AI SD 3.5 |
|---|---|---|---|
| Released | 2026-04-21 | 2025 | — |
| Prompt adherence | Best | Excellent | Good |
| Size options | 1024x1024, 1536x1024, 1024x1536 | 1024x1024, 1536x1024, 1024x1536 | 1024x1024 |
| Quality options | low, medium, high | low, medium, high | N/A |
| Transparent bg | Yes | Yes | No |
| Style | Photorealistic + artistic | Photorealistic + artistic | Artistic + photorealistic |
| Cost per image (high) | Higher than 1 | Baseline | N/A |
requests (for API calls)Install if needed:
pip install requests
The script prints:
Edit podcast audio — trim pre/post-show chat, remove filler words, cut silences, and enhance audio quality. Use when the user asks to edit a podcast, clean up audio, remove fillers, trim a recording, or improve voice quality.
Conduct full competitor strategy breakdowns across SEO, ads, social, email, pricing, and positioning. Use when the user asks to analyze competitors, benchmark against rivals, understand competitive landscape, find competitor weaknesses, or build a competitive matrix. Trigger phrases include "competitor analysis", "competitive analysis", "who are my competitors", "competitor research", "competitive landscape", "benchmark competitors", "competitor ads", "competitor SEO", "competitor pricing", "SWOT analysis", "competitive matrix".
Show a GitHub repo's star growth as CLI charts — by day and by hour, in any timezone. Use when the user asks to "check GitHub stars", "stars by hour/day for <repo>", "star growth", "how many stars did <repo> get today", or shares a repo name and wants its starring activity over time.
Fetch website traffic estimates (monthly visits, traffic sources, top countries, keywords, engagement, ranks) for any domain from SimilarWeb. Use when the user asks about a domain's traffic, monthly visits, traffic sources, audience countries, or wants to compare/benchmark sites against competitors.
Find which ChatGPT search queries mention a given brand. Tests long-tail queries against ChatGPT's web-search-enabled model and reports which ones surface the brand. Use when the user asks to "find queries for [brand]", "check GEO visibility", "which queries mention [brand]", "geo query finder", "find AI mentions", or "test ChatGPT queries for [brand]".
Fight Stripe disputes and chargebacks by gathering evidence (Stripe API + your app database + terms page), generating an activity-log PDF, and submitting a counter-dispute. Use when the user says "fight dispute", "stripe dispute", "chargeback", "counter dispute", "dispute evidence", or shares a Stripe dispute ID.