← Back to Skills Marketplace
129
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install p
Description
提供图片加载、尺寸调整、裁剪、格式转换、增强、滤镜、拼接、背景移除和文字添加等多功能创意图片处理能力。
Usage Guidance
This skill appears coherent and limited to local image processing. Before installing/running: (1) run it in a virtualenv or sandbox if you prefer isolation, (2) note it will read/write image files (example writes to an 'output' directory) and access system font files, and (3) the only dependency is Pillow. If you need network-isolation, run without network access — the code contains no networking but isolating untrusted code is a good practice.
Capability Analysis
Type: OpenClaw Skill
Name: p
Version: 1.0.0
The p-skill bundle is a legitimate image processing toolkit providing features like resizing, filtering, stitching, and text addition using the Pillow library. Analysis of the source code (src/p_skill/*.py) and the agent instructions (SKILL.md) shows no evidence of data exfiltration, malicious execution, or prompt injection; all functions align with the stated purpose of creative image manipulation.
Capability Assessment
Purpose & Capability
Name/description match the included Python modules (core, filters, enhance, composite, background, text). All requested capabilities (resize, filters, background removal, text, stitching) are implemented in the code; no unrelated credentials or binaries are requested.
Instruction Scope
SKILL.md only documents usage and a pip install of requirements.txt. The runtime instructions and code operate on image files and local fonts; they do not read arbitrary config files, environment variables, or send data to external endpoints.
Install Mechanism
No special install spec; dependency is only pillow>=10.0.0 via requirements.txt. There are no downloads from untrusted URLs, no extracted archives, and no nonstandard installation locations.
Credentials
The skill declares no environment variables or credentials. Code accesses local filesystem for images and system font paths (to render text), which is proportionate to its purpose.
Persistence & Privilege
always is false and the skill does not modify other skills or system-wide config. It does not request elevated or persistent privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install p - After installation, invoke the skill by name or use
/p - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
p-skill 1.0.0 首个版本发布！
- 提供丰富的图片处理功能，包括加载、保存、裁剪、尺寸调整和格式转换
- 内置亮度、对比度、清晰度调节与一键智能增强
- 支持多种滤镜：黑白、复古、模糊、轮廓、反色、像素化
- 实现水平/垂直/网格拼接及多种对齐模式
- 简单背景移除和指定颜色背景删除，支持边缘平滑处理
- 添加支持自定义字体、位置、颜色及旋转的文字功能
Metadata
Frequently Asked Questions
What is P图?
提供图片加载、尺寸调整、裁剪、格式转换、增强、滤镜、拼接、背景移除和文字添加等多功能创意图片处理能力。 It is an AI Agent Skill for Claude Code / OpenClaw, with 129 downloads so far.
How do I install P图?
Run "/install p" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is P图 free?
Yes, P图 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does P图 support?
P图 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created P图?
It is built and maintained by bittao (@hgta23); the current version is v1.0.0.
More Skills