← 返回 Skills 市场
272
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install smart-image-to-pdf
功能描述
Combine multiple image screenshots into a paginated A4 PDF. Intelligently handles page breaks to avoid cutting through text. Use when the user wants to combi...
安全使用建议
This skill appears coherent and safe for its stated purpose: it reads image files, uses Pillow/numpy to lay them out and writes a PDF. Before installing/running: (1) confirm you trust the source of the skill (the package has no homepage and an unknown owner), (2) ensure you run it in an environment with Pillow and numpy (or use `pip install Pillow numpy`), and (3) supply only image directories/files you trust, since the script will read them and write the output PDF in the same filesystem. If you need stricter isolation, run the script in a sandbox/container.
功能分析
Type: OpenClaw Skill
Name: smart-image-to-pdf
Version: 0.1.0
The skill is a legitimate utility for merging images into a paginated PDF with whitespace-aware page breaks. The Python script (scripts/combine.py) uses standard libraries (Pillow, numpy) for image processing and contains no evidence of data exfiltration, network calls, or malicious command execution. The instructions in SKILL.md are consistent with the tool's stated purpose and do not attempt to manipulate the AI agent into performing unauthorized actions.
能力评估
Purpose & Capability
Name/description (stitch images into a printable A4 PDF) align with the included script and instructions. The script only reads image files, processes them with Pillow/numpy, and writes a PDF; these actions are expected for the stated purpose.
Instruction Scope
SKILL.md instructs the agent to run the bundled Python script on a directory or list of image paths and to report counts and the output path. The instructions do not request unrelated files, environment variables, or outbound network endpoints.
Install Mechanism
No install spec is provided (instruction-only), and the code is included. SKILL.md suggests using `uv run --with Pillow --with numpy ...` to handle dependencies; this is unusual but not inherently malicious. If `uv` is unavailable, the equivalent safe alternatives are `pip install Pillow numpy` or running in an environment with those packages already installed.
Credentials
The skill requests no environment variables, no credentials, and no config paths. The script also does not read environment variables or attempt to access unrelated credentials — its filesystem access is limited to the provided input files and the output PDF.
Persistence & Privilege
Skill is not marked always:true and does not attempt to modify other skills or system-wide settings. Autonomous invocation is allowed by default but is not combined with other concerning privileges.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install smart-image-to-pdf - 安装完成后，直接呼叫该 Skill 的名称或使用
/smart-image-to-pdf触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v0.1.0
- Initial release of the image-to-pdf skill.
- Combines multiple image screenshots (e.g., exam papers) into a paginated, print-ready A4 PDF.
- Automatically trims image borders and intelligently places images to avoid splitting text across pages.
- New Python script `scripts/combine.py` added for image processing and PDF creation.
- Simplified usage: one command handles directory or file inputs; options include margins, trimming, and DPI.
- Obsolete file `clawhub.json` removed.
元数据
常见问题
Smart Image to PDF 是什么？
Combine multiple image screenshots into a paginated A4 PDF. Intelligently handles page breaks to avoid cutting through text. Use when the user wants to combi... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 272 次。
如何安装 Smart Image to PDF？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install smart-image-to-pdf」即可一键安装，无需额外配置。
Smart Image to PDF 是免费的吗？
是的，Smart Image to PDF 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Smart Image to PDF 支持哪些平台？
Smart Image to PDF 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Smart Image to PDF？
由 wxttt（@wxttt）开发并维护，当前版本 v0.1.0。
推荐 Skills