How do I install the Coze Image Gen skill?

Run npx skillmds@latest add full-aigc-skills/coze-image-gen in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Coze Image Gen safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Coze Image Gen?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Coze Image Gen free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Coze Image Gen?

full-aigc-skills (@full-aigc-skills) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Coze Image Gen by full-aigc-skills — Agent Skill

Name: Coze Image Gen
Author: full-aigc-skills

Coze Image Gen

Generate one or more images from text prompts using Coze image generation. Use when you need to create images from a natural-language prompt, produce multiple image variants, or generate sequential frames from the same prompt.

File contents

Coze Image Generation

Generate one or more images from a prompt using Coze.

This skill runs as a Node CLI wrapper around the backend SDK. Do not use the SDK from client-side code.

Quick start

node {skillDir}/scripts/gen.mjs --prompt "A futuristic city at sunset"
node {skillDir}/scripts/gen.mjs --prompt "A serene mountain landscape" --count 2 --size 4K
node {skillDir}/scripts/gen.mjs --prompt "A hero's journey through magical lands" --sequential --max-sequential 5
node {skillDir}/scripts/gen.mjs --prompt "Transform into anime style" --image "https://example.com/input.jpg"
node {skillDir}/scripts/gen.mjs --prompt "A modern office workspace" --response-format url

Options

--prompt <text> required prompt text
--count <n> number of independent generation requests, default 1
--size <size> image size: 2K, 4K, or WIDTHxHEIGHT, default 2K
--image <url> reference image URL; repeat the flag to pass multiple images
--response-format <format> only supports url
--watermark <true|false> whether to keep watermark
--optimize-prompt-mode <mode> prompt optimization mode passed through to the SDK
--sequential enable sequential image generation
--max-sequential <n> max sequential frames, default 15
--header <key:value> custom HTTP header; repeatable, alias -H

Notes

The skill runtime requires plugins.entries.coze-openclaw-plugin.config.apiKey.
{skillDir} means the directory containing this SKILL.md.
Successful runs print generated URLs directly.
Printed image URLs must be kept exactly intact, complete, and accurate. All URL parameters must be preserved without truncation, rewriting, omission, or reordering; in particular, parameters inside the query string such as sign must not be dropped, otherwise the image may be inaccessible.
Unless the user explicitly asks to download the URL content, only return the complete URL link to the user.
This skill does not expose base64 output.

---name: coze-image-gendescription: Generate one or more images from text prompts using Coze image generation. Use when you need to create images from a natural-language prompt, produce multiple image variants, or generate sequential frames from the same prompt.---# Coze Image GenerationGenerate one or more images from a prompt using Coze.This skill runs as a Node CLI wrapper around the backend SDK. Do not use the SDK from client-side code.## Quick start```bashnode {skillDir}/scripts/gen.mjs --prompt "A futuristic city at sunset"node {skillDir}/scripts/gen.mjs --prompt "A serene mountain landscape" --count 2 --size 4Knode {skillDir}/scripts/gen.mjs --prompt "A hero's journey through magical lands" --sequential --max-sequential 5node {skillDir}/scripts/gen.mjs --prompt "Transform into anime style" --image "https://example.com/input.jpg"node {skillDir}/scripts/gen.mjs --prompt "A modern office workspace" --response-format url```## Options- `--prompt <text>` required prompt text- `--count <n>` number of independent generation requests, default `1`- `--size <size>` image size: `2K`, `4K`, or `WIDTHxHEIGHT`, default `2K`- `--image <url>` reference image URL; repeat the flag to pass multiple images- `--response-format <format>` only supports `url`- `--watermark <true|false>` whether to keep watermark- `--optimize-prompt-mode <mode>` prompt optimization mode passed through to the SDK- `--sequential` enable sequential image generation- `--max-sequential <n>` max sequential frames, default `15`- `--header <key:value>` custom HTTP header; repeatable, alias `-H`## Notes- The skill runtime requires `plugins.entries.coze-openclaw-plugin.config.apiKey`.- `{skillDir}` means the directory containing this `SKILL.md`.- Successful runs print generated URLs directly.- Printed image URLs must be kept exactly intact, complete, and accurate. All URL parameters must be preserved without truncation, rewriting, omission, or reordering; in particular, parameters inside the query string such as `sign` must not be dropped, otherwise the image may be inaccessible.- Unless the user explicitly asks to download the URL content, only return the complete URL link to the user.- This skill does not expose base64 output.

Frequently asked questions