Ai Image Generation

Generate AI images with FLUX, Gemini, Grok, Seedream, Reve and 50+ models via SkillBoss API Hub. Models: FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image...

Security Scan

The skill appears to do what it claims (call the SkillBoss image API with an API key), but the SKILL.md requires a SKILLBOSS_API_KEY while the registry metadata omitted that requirement and the external API domain is unfamiliar — verify before installing.

Purpose & Capability

The name/description and runtime instructions align: the skill calls SkillBoss API Hub (https://api.heybossai.com) to generate images and demonstrates text->image, image->image, upscaling, etc. However, the public registry metadata lists no required environment variables while SKILL.md clearly requires SKILLBOSS_API_KEY — an inconsistency that should be resolved by the publisher.

Instruction Scope

SKILL.md confines behavior to reading a single environment variable (SKILLBOSS_API_KEY) and making HTTPS requests to the SkillBoss API; it does not instruct the agent to read arbitrary files or other credentials. It does, however, expect network access to an external service and will transmit prompts and potentially image URLs to that service.

Install Mechanism

No install spec or code files are present (instruction-only), so nothing is written to disk by an installer. This is lower risk than download-and-extract install mechanisms.

Credentials

Requiring a single SKILLBOSS_API_KEY is proportionate to the stated purpose (calling a third-party API). The notable issue is the mismatch between SKILL.md (which declares the env var) and the registry metadata (which lists none). Also, the external domain (api.heybossai.com) is not documented in the registry homepage; confirm the API provider, what that key can do (billing, data access), and whether it has broad privileges.

Persistence & Privilege

The skill does not request always:true or any elevated persistence. Ordinary autonomous invocation is allowed by default but not by itself a red flag. The skill does not declare writing/modifying other skills or system-wide settings.

Scan Findings in Context

[no_regex_findings] expected: The static scanner found no code (this is an instruction-only skill). The runtime instructions in SKILL.md are the primary surface to review.

What to consider before installing

Before installing: (1) Confirm the SKILLBOSS_API_KEY requirement — the SKILL.md needs this but the registry metadata omitted it; don't provide high-privilege keys until you verify. (2) Verify the API provider (api.heybossai.com): find its privacy/billing/terms and confirm you trust where prompts and uploaded images will be sent and stored. (3) Use a scoped or test API key with limited billing and permissions, and monitor usage for unexpected calls. (4) Be cautious about sending sensitive images or prompts (they go to an external service). (5) If you need stronger assurance, ask the publisher for a homepage, documentation, or an official source for the SkillBoss API before enabling the skill.

Generate images with 50+ AI models via SkillBoss API Hub.

Quick Start

import requests, os

SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]
API_BASE = "https://api.heybossai.com/v1"

def pilot(body: dict) -> dict:
    r = requests.post(
        f"{API_BASE}/pilot",
        headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
        json=body,
        timeout=60,
    )
    return r.json()

# Generate an image (auto-routed to best model)
result = pilot({"type": "image", "inputs": {"prompt": "a cat astronaut in space"}, "prefer": "quality"})
image_url = result["result"]["image_url"]
print(image_url)

Available Models

SkillBoss API Hub 自动路由至最优图像生成模型，支持 50+ 模型，包括：

Model	Best For
FLUX Dev LoRA	High quality with custom styles
FLUX.2 Klein LoRA	Fast with LoRA support (4B/9B)
Gemini 3 Pro	Google's latest
Gemini 2.5 Flash	Fast Google model
Grok Imagine	xAI's model, multiple aspects
Seedream 4.5	2K-4K cinematic quality
Seedream 4.0	High quality 2K-4K
Seedream 3.0	Accurate text rendering
Reve	Natural language editing, text rendering
ImagineArt 1.5 Pro	Ultra-high-fidelity 4K
Topaz Upscaler	Professional upscaling

Browse All Image Models

# Discover 模式：查询所有支持的图像生成模型
result = pilot({"discover": True, "keyword": "image"})
print(result)

Examples

Text-to-Image (Quality)

result = pilot({
    "type": "image",
    "inputs": {"prompt": "professional product photo of a coffee mug, studio lighting"},
    "prefer": "quality"
})
image_url = result["result"]["image_url"]

Fast Generation

result = pilot({
    "type": "image",
    "inputs": {"prompt": "sunset over mountains"},
    "prefer": "balanced"
})
image_url = result["result"]["image_url"]

Photorealistic Landscape

result = pilot({
    "type": "image",
    "inputs": {"prompt": "photorealistic landscape with mountains and lake"},
    "prefer": "quality"
})
image_url = result["result"]["image_url"]

With Aspect Ratio

result = pilot({
    "type": "image",
    "inputs": {
        "prompt": "cyberpunk city at night",
        "aspect_ratio": "16:9"
    },
    "prefer": "balanced"
})
image_url = result["result"]["image_url"]

Text Rendering in Image

result = pilot({
    "type": "image",
    "inputs": {"prompt": "A poster that says HELLO WORLD in bold letters"},
    "prefer": "quality"
})
image_url = result["result"]["image_url"]

Cinematic Portrait (4K Quality)

result = pilot({
    "type": "image",
    "inputs": {"prompt": "cinematic portrait of a woman, golden hour lighting"},
    "prefer": "quality"
})
image_url = result["result"]["image_url"]

Image Upscaling

result = pilot({
    "type": "image",
    "inputs": {
        "prompt": "upscale",
        "image_url": "https://example.com/image.jpg"
    },
    "prefer": "quality"
})
image_url = result["result"]["image_url"]

Response 格式

# 标准 response 解析
result = pilot({"type": "image", "inputs": {"prompt": "..."}, "prefer": "quality"})
image_url = result["result"]["image_url"]
# 或（部分模型返回数组格式）
image_url = result["result"]["images"][0]["url"]

环境变量

变量	说明
SKILLBOSS_API_KEY	SkillBoss API Hub 统一密钥