← 返回 Skills 市场
Talking-head Editor
作者
fischerlam
· GitHub ↗
· v1.0.12
· MIT-0
206
总下载
0
收藏
0
当前安装
7
版本数
在 OpenClaw 中安装
/install talking-head-editor
功能描述
Scenario-focused Sparki skill for presenter-led and talking-head edits while using the latest official Sparki setup, API-key, and upload workflow guidance.
安全使用建议
This skill appears to do what it says: a Sparki CLI for uploading local videos and managing edit jobs on agent-api.sparki.io. Before installing, consider: (1) Only provide a Sparki API key (SPARKI_API_KEY) you trust — the key grants the skill access to your Sparki account and uploads video files to Sparki's servers. (2) The skill will create and update ~/.openclaw/config/sparki.json and save downloaded videos to ~/.openclaw/workspace/sparki/videos; if you want to control where files land, set the config or run in a sandboxed environment. (3) The install step invokes a local 'uv sync' command — ensure 'uv' is the expected sync tool in your environment. (4) If you need to avoid sending videos to the default host, override the base_url (the code supports configuring base_url). If any of these behaviors are unexpected, review the included source files or test in an isolated environment first.
功能分析
Type: OpenClaw Skill
Name: talking-head-editor
Version: 1.0.12
The skill is a legitimate CLI wrapper for the Sparki AI video editing service. It facilitates video uploads, project status tracking, and downloading processed files from 'agent-api.sparki.io'. The code (cli.py, client.py) follows standard practices, using well-known libraries like httpx and typer, and limits file system access to specific configuration and workspace directories (~/.openclaw) as declared in the SKILL.md permissions.
能力评估
Purpose & Capability
Name/description, included CLI code, and required network host (agent-api.sparki.io) all align with a Sparki-focused talking‑head video editor. The only mild oddity is the declared required binary 'uv' (used for a 'uv sync' install step) — this appears to be an environment/tooling step rather than core editing functionality but is reasonable for a skill that expects a sync tool.
Instruction Scope
Runtime instructions and the CLI code operate within the expected domain: validating an API key, uploading local video files, creating projects, polling status, and downloading results. File and network accesses are scoped to local project files and the Sparki API. The skill explicitly forbids accepting raw video attachments in chat and documents the supported upload flows.
Install Mechanism
No external downloads or extract steps are used. The SKILL.md lists a single install action invoking the local 'uv sync' command; this is low-risk compared to arbitrary URL downloads. The package includes Python source and a pyproject listing standard dependencies (typer, httpx, pydantic) — nothing pulls code from unusual hosts.
Credentials
Primary credential SPARKI_API_KEY is appropriate and used by the code. The code also optionally reads SPARKI_UPLOAD_TG_LINK for a Telegram upload link; that environment var is not explicitly listed in the skill's requires.env block (minor mismatch). No unrelated secrets or cloud credentials are requested.
Persistence & Privilege
always is false and the skill does not request global/other-skills config access. It reads/writes its own config file (~/.openclaw/config/sparki.json), saves history to the same config dir, and writes downloads to its workspace (~/.openclaw/workspace/sparki/videos) — these are proportional to its functionality.
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 - 安装完成后，直接呼叫该 Skill 的名称或使用
/talking-head-editor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
Tightened the opening trigger and example requests so this scene skill is more vertical and better aligned to user intent, while keeping the official shared Sparki core workflow.
v1.0.10
Refreshed this 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 scene skill to align its shared setup, API-key, upload, and command guidance with the latest official sparki-video-editor skill while preserving scene-specific positioning.
v1.0.8
Updated the default API endpoint to the official Sparki domain https://business-agent-api.sparki.io and aligned docs/scripts accordingly.
v1.0.7
Re-released as a cleaned English-only update. Fixed metadata alignment and standardized configurable API base usage.
v1.0.6
Published a scenario-specific skill focused on talking-head video editing, built on the cleaned Sparki video workflow.
元数据
常见问题
Talking-head Editor 是什么？
Scenario-focused Sparki skill for presenter-led and talking-head edits while using the latest official Sparki setup, API-key, and upload workflow guidance. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 206 次。
如何安装 Talking-head Editor？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install talking-head-editor」即可一键安装，无需额外配置。
Talking-head Editor 是免费的吗？
是的，Talking-head Editor 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Talking-head Editor 支持哪些平台？
Talking-head Editor 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 Talking-head Editor？
由 fischerlam（@fischerlam）开发并维护，当前版本 v1.0.12。
推荐 Skills