Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
conardli avatar

Gpt Image 2

conardli/garden-skills

  • 3.2k installs
  • 10.1k repo stars
  • Updated July 12, 2026
  • conardli/garden-skills

gpt-image-2 is an agent skill that generates and edits images via GPT Image 2 or compatible APIs using mode-aware prompt templates and local or delegated execution.

About

gpt-image-2 is a Garden image generation and editing skill built around GPT Image 2 and OpenAI-compatible POST /images/generations and POST /images/edits endpoints. A check-mode script selects among Garden local mode when ENABLE_GARDEN_IMAGEGEN and OPENAI_API_KEY are set, host-native delegation when the agent already has an image tool, or advisor-only prompt writing when no image tool exists. The skill bundles 18 template categories and 79 structured prompt templates for posters, UI mockups, product visuals, infographics, and editing workflows, archiving prompts and images under garden-gpt-image-2 paths with task-slug timestamps. Mode A runs generate.js and edit.js locally; mode B delegates to host image tools; mode C saves prompts for external services. Developers reach for gpt-image-2 when agents must produce logos, marketing art, or iterative image edits with reproducible prompt engineering across Claude Code, Cursor, Codex, and other compatible hosts.

  • Detects runtime mode via check-mode.js across Garden local, host-native, and advisor paths.
  • Supports POST /images/generations and POST /images/edits with generate.js and edit.js scripts.
  • Ships 18 template categories and 79 structured prompt templates for common visual tasks.
  • Archives prompts and images under garden-gpt-image-2 with task-slug timestamp naming.
  • Mode A requires ENABLE_GARDEN_IMAGEGEN and OPENAI_API_KEY; mode C saves prompts only.

Gpt Image 2 by the numbers

  • 3,161 all-time installs (skills.sh)
  • +129 installs in the week ending Aug 5, 2026 (Skillselion tracking)
  • Ranked #134 of 1,335 Generative Media skills by installs in the Skillselion catalog
  • Security screen: LOW risk (skills.sh audit)
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
At a glance

gpt-image-2 capabilities & compatibility

Capabilities
mode aware image generation and editing · structured prompt template library · prompt and image archival workflow
Works with
openai
Use cases
image generation
From the docs

What gpt-image-2 says it does

A focused image-generation / editing skill for GPT Image 2, with a single SKILL definition that adapts to three runtime modes
SKILL.md
18 categories and 79 prompt templates covering posters, UI mockups, product visuals
SKILL.md
node skills/gpt-image-2/scripts/check-mode.js
SKILL.md
npx skills add https://github.com/conardli/garden-skills --skill gpt-image-2

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs3.2k
repo stars★ 10.1k
Security audit3 / 3 scanners passed
Last updatedJuly 12, 2026
Repositoryconardli/garden-skills ↗

How do I generate or edit images with consistent prompt templates whether the agent has a local API key or only a host image tool?

Generate and edit images consistently using GPT Image 2 or any OpenAI-compatible image API.

Who is it for?

Developers needing structured image generation for posters, UI mockups, product shots, or edits across multiple agent hosts.

Skip if: Skip when the task is vector SVG icon work or deterministic canvas code better handled without image APIs.

When should I use this skill?

User asks to generate, edit, or batch-produce images with GPT Image 2, DALL-E-compatible endpoints, or Garden prompt templates.

What you get

Rendered images on disk in Garden local mode or delegated host output, plus archived prompt files under garden-gpt-image-2 for reuse.

  • generated image files
  • edited image variants
  • structured image prompts

By the numbers

  • Version 1.0.3 with 18 visual categories and 80+ structured prompt templates
  • Three runtime modes: Garden local, host-native delegation, and advisor-only

Files

SKILL.mdMarkdownGitHub ↗

{ "name": "gpt-image-2", "version": "1.0.3", "category": "Image Generation / Prompt Engineering", "description": "Focused image generation and editing skill for GPT Image 2 and OpenAI-compatible image APIs. Supports three runtime modes — Garden local, host-native delegation, and advisor-only — with 18 visual categories and 80+ structured prompt templates.", "homepage": "https://github.com/ConardLi/garden-skills/tree/main/skills/gpt-image-2", "compat": [ "claude-code", "claude-ai", "cursor", "codex-cli", "gemini-cli", "opencode" ] }

GPT Image 2 Skill

A focused image-generation / editing skill for GPT Image 2, with a single SKILL definition that adapts to three runtime modes — local generation, host-native delegation, and pure prompt advisor.

中文文档 · Back to collection root

GPT Image 2 Skill
GPT Image 2 Skill

---

What it does

This skill is a structured prompt-engineering and image-generation pack built around the GPT Image 2 model (and OpenAI-compatible image endpoints). It only does two image tasks — POST /images/generations and POST /images/edits — but it does them in three different runtime environments without changing user-facing behavior.

It bundles:

  • A mode-aware workflow so the same skill works whether the agent itself owns the image API key, the host has its own image tool, or there is no image tool at all.
  • A structured template library of 18 categories and 79 prompt templates covering posters, UI mockups, product visuals, infographics, academic figures, technical diagrams, comics, avatars, and editing workflows.
  • Reproducible prompt + image archival under garden-gpt-image-2/prompt/ and garden-gpt-image-2/image/ with task-slug + timestamp naming.

---

The three runtime modes

The very first thing this skill does on any task is run a tiny detection script:

node skills/gpt-image-2/scripts/check-mode.js
# or for structured output:
node skills/gpt-image-2/scripts/check-mode.js --json

The output picks one of three modes:

ModeTriggerBehavior
A — Garden localENABLE_GARDEN_IMAGEGEN truthy AND OPENAI_API_KEY presentEnd-to-end: pick template → render prompt → call generate.js / edit.js → image lands on disk
B — Host-nativeGarden disabled, but the host agent already has an image tool (image_generation, dalle, nano_banana, image MCP, etc.)Render the prompt, then delegate image generation to the host's own tool
C — AdvisorGarden disabled, host has no image toolSkill degrades into a high-quality prompt writer — saves the rendered prompt to garden-gpt-image-2/prompt/ and instructs the user to paste it into ChatGPT / Midjourney / DALL·E / Sora / Nano Banana / their own gateway

In all three modes, prompt files are saved (mode A & C must save, mode B is recommended for reuse). Only mode A produces an image file; mode B leaves that to the host, mode C cannot.

---

Quick start

0. Detect the mode (always step 0)

node skills/gpt-image-2/scripts/check-mode.js

The commands below (1–4) only apply in Mode A.

1. Text-to-image

node skills/gpt-image-2/scripts/generate.js \
  --prompt "A cute baby sea otter" \
  --size 1024x1024 \
  --quality high

2. Generate from a saved prompt file

node skills/gpt-image-2/scripts/generate.js \
  --promptfile garden-gpt-image-2/prompt/poster-20260424-153045.md

3. Edit an existing image

node skills/gpt-image-2/scripts/edit.js \
  --image assets/source.png \
  --prompt "Replace the background with a clean studio scene"

4. Mask-based local edit

node skills/gpt-image-2/scripts/edit.js \
  --image assets/source.png \
  --mask  assets/mask.png \
  --prompt "Replace only the masked area with a glass vase"

For Mode B / C there is no CLI

Related skills

remotion-devRemotion Best PracticesGet Remotion-specific coding guidance that prevents common video rendering mistakes when creating animated React videos.451k4.2k101-skillsAi Video GenerationGenerate videos using 40+ AI models including Veo, Seedance, and others via inference.sh442k665101-skillsAi Image GenerationGenerate images using 50+ AI models including FLUX, Gemini, and Replicate via inference.sh441k665101-skillsAi Avatar VideoGenerate videos featuring AI avatars for product demos, tutorials, marketing, or explainers441k665101-skillsRemotion RenderRender videos programmatically using React components and Remotion framework441k665halt-catch-fireRemotion RenderGenerate high-quality MP4 videos from React code using Remotion inside an AI coding agent.363k665

How it compares

Pick gpt-image-2 when you need categorized prompt libraries and editing workflows inside agent sessions rather than a single generic image-generation tool call.

FAQ

How does gpt-image-2 choose its runtime mode?

node skills/gpt-image-2/scripts/check-mode.js selects Garden local, host-native delegation, or advisor-only prompt writing.

When does mode A produce image files locally?

When ENABLE_GARDEN_IMAGEGEN is truthy and OPENAI_API_KEY is present so generate.js or edit.js can call the API.

What happens in advisor mode?

The skill writes rendered prompts to garden-gpt-image-2/prompt/ for the user to paste into external image services.

Is Gpt Image 2 safe to install?

skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

Generative Mediaautomation
Browse by category
AI & AgentsFrontend & DesignBackend & DataDev ToolsAutomationTesting & ReviewSecurityMonitoring & CloudDocs & Planning
Design & frontend
Design systemsAnimation & motionAccessibility (a11y)CSS & TailwindUI designUXDesign to codeshadcn/uiLanding pagesBest design skills
Most searched skills
find-skillscavemanfrontend-designbrainstormingsystematic-debuggingstop-slopemil-design-engui-ux-pro-maxkarpathy-guidelinesweb-design-guidelinesreact-best-practicesgrill-meimprovemicrosoft-foundryagent-browser
Browse all listings
All agent skillsAll MCP serversAll marketplacesAll plugins

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.