Agent Skills › QuixiAI/Hexis › image-gen

image-gen

GitHub

基于文本描述生成图像的 AI 技能，支持 DALL-E。提供从需求澄清、提示词构建到参数设置和结果迭代的完整工作流，强调内容合规与成本控制。

skills/installed/image-gen/SKILL.md QuixiAI/Hexis

Trigger Scenarios

用户明确要求生成图像创意目标涉及视觉输出演示文稿需要快速配图

Install

npx skills add QuixiAI/Hexis --skill image-gen -g -y

More Options

Non-standard path

npx skills add https://github.com/QuixiAI/Hexis/tree/main/skills/installed/image-gen -g -y

Use without installing

npx skills use QuixiAI/Hexis@image-gen

指定 Agent (Claude Code)

npx skills add QuixiAI/Hexis --skill image-gen -a claude-code -g -y

安装 repo 全部 skill

npx skills add QuixiAI/Hexis --all -g -y

预览 repo 内 skill

npx skills add QuixiAI/Hexis --list

SKILL.md

Frontmatter

{
    "name": "image-gen",
    "aliases": [
        "image",
        "picture",
        "draw",
        "illustration",
        "generate",
        "visual",
        "art"
    ],
    "category": "creative",
    "contexts": [
        "heartbeat",
        "chat"
    ],
    "requires": {
        "env": [
            "OPENAI_API_KEY"
        ],
        "tools": [
            "generate_image"
        ]
    },
    "bound_tools": [
        "generate_image"
    ],
    "description": "Generate images from text descriptions using DALL-E or compatible providers"
}

Image Generation Workflow

Create images from natural language descriptions using AI image generation models (DALL-E 3 or compatible).

When to Use

When the user explicitly requests an image ("draw me", "generate a picture of", "create an image")
When a creative goal involves visual output (social media graphics, concept art, illustrations)
When a meeting or presentation needs a quick visual and the user asks for one
Never generate images speculatively during heartbeats unless a goal explicitly calls for it

Step-by-Step Methodology

Clarify the request: If the user's description is vague, ask a follow-up before generating. A clear prompt produces vastly better results than a guess. Key dimensions to clarify: subject, style, mood, aspect ratio, and any text that should appear.
Craft the prompt: Translate the user's intent into a detailed image generation prompt. Good prompts include:
- The primary subject and its pose or arrangement
- Art style or medium (photorealistic, watercolor, vector illustration, etc.)
- Lighting and color palette
- Composition notes (close-up, wide shot, centered, rule of thirds)
- What to exclude (negative prompt elements phrased positively, e.g., "clean background" instead of "no clutter")
Set parameters: Choose the appropriate size and quality setting. Default to standard quality unless the user requests high quality. Respect the cost implications -- high-quality, large images are more expensive.
Generate: Call generate_image with the crafted prompt. The tool returns a URL or local path to the generated image.
Present and iterate: Show the result to the user. If they want adjustments, refine the prompt and regenerate. Keep the previous prompt as a starting point to maintain continuity.
Store if valuable: If the generated image is tied to a goal or project, store a memory noting what was generated and the prompt used, so it can be reproduced or iterated on later.

Quality Guidelines

Always respect content policies. Do not generate images of real people, violent content, or anything the user has not explicitly requested.
Be transparent about cost. Image generation consumes API credits; inform the user if they are making many requests.
Do not generate images during heartbeats unless an active goal specifically requires visual output. Image generation is expensive.
When the user asks for a specific style, honor it precisely rather than defaulting to photorealistic.
If generation fails (API error, content policy rejection), explain the failure clearly and suggest prompt modifications.
Store the successful prompt alongside the image reference so the user can reproduce or refine the result later.