← 返回 Skills 市场
口播视频剪辑
作者
fischerlam
· GitHub ↗
· v1.0.12
· MIT-0
222
总下载
1
收藏
1
当前安装
5
版本数
在 OpenClaw 中安装
/install talking-head-editor-zh
功能描述
面向 talking-head / presenter 场景的 Sparki skill 变体，沿用最新版官方 Sparki 安装、API key、上传和命令说明，同时保留口播场景定位。
安全使用建议
This skill appears to be a legitimate Sparki-based talking-head video editor: it needs your Sparki API key, will upload videos to Sparki's API (agent-api.sparki.io), and will store config/history under ~/.openclaw. Before installing, verify you trust the Sparki service and are comfortable with videos being uploaded to it. Note two small inconsistencies: the package contains source code (so it's not purely instruction-only) and it reads an optional SPARKI_UPLOAD_TG_LINK env var that isn't listed in the metadata—if you rely on that feature, set it explicitly. Also ensure the required 'uv' binary is trusted on your system.
功能分析
Type: OpenClaw Skill
Name: talking-head-editor-zh
Version: 1.0.12
The skill is a standard CLI wrapper for the Sparki AI video editing service, providing functionality to upload, edit, and download videos. The code in `cli.py` and `client.py` implements a clean, structured interface using `httpx` for network requests and `typer` for the CLI, with no evidence of shell execution, obfuscation, or unauthorized data access. Permissions defined in `SKILL.md` are appropriately restricted to the application's configuration directory and the legitimate service domain (agent-api.sparki.io).
能力评估
Purpose & Capability
Name/description match the code and declared network domain (agent-api.sparki.io). Requiring SPARKI_API_KEY is appropriate for a Sparki client. Declared FS reads/writes map to the config and workspace paths used by the CLI.
Instruction Scope
SKILL.md instructs proactive use for video-editing queries and forbids direct Telegram file uploads (it relies on local file paths or the Telegram upload link). The runtime code reads/writes only the local config, history, and output directories and talks only to Sparki endpoints. However, SKILL.md/code reference an optional SPARKI_UPLOAD_TG_LINK environment variable (used for upload link) that is not listed in requires.env/metadata.
Install Mechanism
The skill was presented as 'instruction-only' with no install spec in the registry summary, but SKILL.md metadata includes an install step ('uv sync') and the package contains Python CLI source files. No external downloads from untrusted URLs are present; the install appears to expect a local 'uv' tool to synchronize files.
Credentials
Only SPARKI_API_KEY is declared as the primary credential and is justified. The code also checks for SPARKI_UPLOAD_TG_LINK (optional) but that env var is not declared in the metadata; otherwise no unrelated secrets or excessive env access are requested.
Persistence & Privilege
always:false and normal autonomous invocation. The skill writes only to its own config and workspace paths ($HOME/.openclaw/config and workspace/sparki/videos) as declared; it does not request system-wide privileges or modify other skills.
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 talking-head-editor-zh - 安装完成后，直接呼叫该 Skill 的名称或使用
/talking-head-editor-zh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
v1.0.12
Improved engagement-oriented positioning with a stronger result-focused summary, one-copy quick start command, prompt templates, and related-skill cross-links while keeping the official shared Sparki core workflow.
v1.0.11
Polished the Chinese copy so this scene skill reads more like a native Chinese product page instead of a structural translation, while keeping the official shared Sparki core workflow.
v1.0.10
Refreshed this Chinese scene skill to align its shared setup, API-key, upload, and command guidance with the latest official sparki-video-editor skill while preserving its scenario-specific positioning.
v1.0.9
Refreshed this Chinese scene skill so its shared setup, API-key, upload, and command guidance now matches the latest official sparki-video-editor skill while preserving scene-specific positioning.
v1.0.8
Published a Chinese-localized scene skill for talking-head video editing, aligned to the official Sparki API domain.
元数据
常见问题
口播视频剪辑 是什么？
面向 talking-head / presenter 场景的 Sparki skill 变体，沿用最新版官方 Sparki 安装、API key、上传和命令说明，同时保留口播场景定位。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 222 次。
如何安装 口播视频剪辑？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install talking-head-editor-zh」即可一键安装，无需额外配置。
口播视频剪辑 是免费的吗？
是的，口播视频剪辑 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
口播视频剪辑 支持哪些平台？
口播视频剪辑 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（darwin, linux）。
谁开发了 口播视频剪辑？
由 fischerlam（@fischerlam）开发并维护，当前版本 v1.0.12。
推荐 Skills