← 返回 Skills 市场
漫剧
作者
treelounge
· GitHub ↗
· v1.0.0
· MIT-0
495
总下载
0
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install libtv
功能描述
将《寻秦记》小说文本转换为带文字说明的漫画（web-toon）格式，每章生成指定数量的漫画格图片。
使用说明 (SKILL.md)
libtv-qunqin\r
\r
描述\r
使用 libtv 后端把《寻秦记》改造成漫画（web‑toon）形式。 \r 接受 JSON payload，返回每一页的 PNG 图片路径及文字说明。\r \r
Entry Point\r
libtv_qunqin.py\r
\r
参数\r
story_file(string) – 书籍或章节文本文件路径（UTF‑8）。\rpanel_count(int, optional) – 每章生成的漫画格数（默认 6）。\rfont(string, optional) – 文字字体（默认 “Noto Serif SC”）。\routput_dir(string, optional) – 输出目录（默认./output/寻秦记）。\r \r
运行示例\r
{\r
"story_file": "novel/寻秦记.txt",\r
"panel_count": 8,\r
"font": "Noto Serif SC",\r
"output_dir": "output/寻秦记"\r
}
安全使用建议
This skill appears to do exactly what it says: read a local UTF-8 text file and produce PNG web‑toon pages using a WebtoonCreator class. The main risk is the external dependency 'libtv' (libtv==0.3.2) referenced in requirements.txt — PyPI packages can execute arbitrary code at install/runtime. Before installing or running this skill: 1) inspect the libtv package source (e.g., pip download + unpack or check its repository) to ensure it doesn't perform network exfiltration or other unexpected actions; 2) run the script in a sandboxed environment (container or VM) with no access to sensitive files/credentials; 3) prefer running it on sample data first and review output files; and 4) if you cannot audit libtv, avoid installing it on systems with sensitive data.
功能分析
Type: OpenClaw Skill
Name: libtv
Version: 1.0.0
The skill bundle contains a potential arbitrary file read vulnerability in `libtv_qunqin.py`. The script accepts a user-provided `story_file` path and reads its full content without any path validation or sanitization, which could be exploited to exfiltrate sensitive local files if the agent is misdirected. Additionally, it relies on a non-standard third-party dependency `libtv` (version 0.3.2) specified in `requirements.txt`, which performs the core logic and should be verified for safety.
能力评估
Purpose & Capability
Name/description, SKILL.md, README, requirements.txt and the included libtv_qunqin.py are consistent: the skill reads a local story file, configures panel count/font/output_dir, calls WebtoonCreator from the libtv package, and writes PNG output. No unrelated capabilities or credentials are requested.
Instruction Scope
Runtime instructions and the script only read JSON from stdin and the referenced local story_file, create the output directory, invoke WebtoonCreator, and print a JSON result. The SKILL.md does not ask the agent to read other system files, env vars, or contact external endpoints directly.
Install Mechanism
There is no install spec included (instruction-only), but requirements.txt pins libtv==0.3.2 (plus Pillow and tqdm). Installing from PyPI is moderately risky because packages can contain arbitrary code; the skill itself does not include a source for libtv, so verify that libtv is a trustworthy package before pip installing.
Credentials
The skill requests no environment variables, credentials, or config paths—appropriate for a local file-to-image converter.
Persistence & Privilege
The skill does not request always:true or any elevated/persistent platform privileges; it runs only when invoked and does not write or modify other skill configurations.
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 libtv - 安装完成后，直接呼叫该 Skill 的名称或使用
/libtv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
v1.0.0
libtv 1.0.0
- Initial release.
- Converts the novel 《寻秦记》 into web-toon style comic pages using the libtv backend.
- Accepts JSON input specifying source text file, panel count, font, and output directory.
- Returns PNG image paths for each comic page along with text descriptions.
元数据
常见问题
漫剧 是什么？
将《寻秦记》小说文本转换为带文字说明的漫画（web-toon）格式，每章生成指定数量的漫画格图片。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 495 次。
如何安装 漫剧？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install libtv」即可一键安装，无需额外配置。
漫剧 是免费的吗？
是的，漫剧 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
漫剧 支持哪些平台？
漫剧 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 漫剧？
由 treelounge（@treelounge）开发并维护，当前版本 v1.0.0。
推荐 Skills