Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Pixel Asset Pipeline

v1.0.0

AI pixel art sprite generation + processing pipeline for Godot games. Generate sprite sheets with Seedream, auto-process into Godot-ready assets (hframes, tr...

0· 112·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for muxueqingze/pixel-asset-pipeline.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Pixel Asset Pipeline" (muxueqingze/pixel-asset-pipeline) from ClawHub.
Skill page: https://clawhub.ai/muxueqingze/pixel-asset-pipeline
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Required binaries: python
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install pixel-asset-pipeline

ClawHub CLI

Package manager switcher

npx clawhub@latest install pixel-asset-pipeline
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
The skill's name/description (AI pixel-art -> Godot-ready assets) matches the behavior of the two included Python scripts, which perform background removal, frame-splitting, scaling, and sprite-sheet output. However, the batch generator is intended to call external generator backends (Seedream, wanx, Gemini) that are referenced in SKILL.md but are not present in the file manifest. The default generator path in batch_generate.py is an absolute Windows path (D:\the things of mine\...) pointing to a local 'lumi-work' script that is not included — this is inconsistent with the claimed out-of-the-box Seedream support.
!
Instruction Scope
The scripts operate only on local files and do not access environment variables or network themselves, which is appropriate. However, batch_generate.py uses subprocess.run to invoke an external generator script (by default an absolute path) and will execute whatever Python file the --generator argument points to. Because the referenced generator scripts are not bundled, the runtime behavior depends on external files the user must supply; running an unknown generator script could execute arbitrary code. The SKILL.md suggests running lumi-work/脚本/生图/seedream_generate.py but that file is absent.
Install Mechanism
No install spec is provided (instruction-only plus included scripts). The only declared runtime requirement is 'python' and the README instructs installing Pillow. Nothing is downloaded or extracted by the skill itself.
Credentials
The skill does not request any environment variables, credentials, or config paths. That is proportionate for a local image-processing pipeline.
Persistence & Privilege
always:false and no modifications to other skills or global agent settings. The scripts write output files to local directories only (game_assets/_raw, etc.), which is expected for this purpose.
What to consider before installing
This skill's image-processing code is consistent with its description and appears safe for local use, but it is incomplete: the generation backend scripts (seedream_generate.py, wanx_generate.py, etc.) are referenced but not included, and the default generator path is a hard-coded absolute Windows path to a user-local workspace. Before running batch generation: (1) inspect any generator script you point to (especially seedream_generate.py) so you know what it does and that it is trustworthy, (2) don't run the skill with an unreviewed --generator value, (3) adjust the DEFAULT_GENERATOR or pass --generator to a known-good script, and (4) run in a non-sensitive environment until you're confident with the generator's behavior. Installing Pillow locally (pip install Pillow) is required for processing. If you want an out-of-the-box generation workflow, ask the author for the missing backend scripts or include a documented, trusted backend.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

🎮 Clawdis
Binspython
latestvk971h9r4rg88nzgsts4hbt9ntd83vmpp
112downloads
0stars
1versions
Updated 4w ago
v1.0.0
MIT-0

🎮 Pixel Asset Pipeline

AI 生成像素游戏素材 → 自动处理为 Godot 可用格式。

Pipeline 概览

Prompt → AI生图(Seedream) → 去背景 → 切帧 → NEAREST缩放 → Godot sprite sheet + 单帧PNG

依赖

  • Python 3.8+ with Pillow (pip install Pillow)

Quick Start

# 1. 处理已有的大图
python scripts/process_sprite_sheet.py raw_sprite.png --output-dir ./out --target-size 48 --cols 4

# 2. 批量生成+处理
python scripts/batch_generate.py references/sample_config.json

支持的生成后端

后端脚本说明
Seedream (默认)lumi-work/脚本/生图/seedream_generate.py2048x2048,效果好
通义万相lumi-work/脚本/生图/wanx_generate.py备选
GeminiOpenClaw image_generate备选

输出格式

  • {name}_spritesheet.png — 横排 sprite sheet,Godot 设置 hframes=N 即可
  • frames/{name}_frame_00.png ~ _frame_XX.png — 单帧透明 PNG

Prompt 技巧

像素风 prompt 模板(英文效果最佳):

16-bit pixel art sprite sheet, [角色/物品描述], top-down RPG, [N] frames, white background, clean outline, no shading

示例:

  • 角色:16-bit pixel art sprite sheet, green slime monster, top-down RPG, 4 frames idle animation, white background
  • 物品:pixel art, silver sword with blue glow, 16x16 icon, white background, game asset
  • 瓦片:pixel art tileset, grass and dirt path, top-down RPG, seamless tiles, white background

关键后缀:加 white backgroundblack background 确保可去背景。

完整使用示例

  1. 用 Seedream 生成:

    python lumi-work/脚本/生图/seedream_generate.py "16-bit pixel art sprite sheet, red dragon, 4 frames, white background" dragon_raw.png ""
    
  2. 处理为 Godot 素材:

    python scripts/process_sprite_sheet.py dragon_raw.png --output-dir ./game_assets/dragon --target-size 64 --cols 4
    
  3. 在 Godot 中:Texture2D → Hframes = 4,搞定。

scripts/

  • process_sprite_sheet.py — 单图处理(去背景→切帧→缩放→输出)
  • batch_generate.py — 批量生成+处理(读JSON配置)

Comments

Loading comments...