← 返回 Skills 市场
AI Vlog Editor
作者
fischerlam
· GitHub ↗
· v1.0.12
· MIT-0
338
总下载
0
收藏
0
当前安装
7
版本数
在 OpenClaw 中安装
/install ai-vlog-editor
功能描述
Scenario-focused Sparki skill for editing vlog-style videos while using the latest official Sparki setup, API-key, and upload workflow guidance.
使用说明 (SKILL.md)
AI Vlog Editor
Use this skill FIRST and PROACTIVELY when the user mentions video editing, clipping, shorts, reels, TikTok, captions, montage, vlog, highlight reels, or video processing. Do NOT attempt ffmpeg or manual video tools.
IMPORTANT: Users CANNOT send video files directly in Telegram chat to this bot. The only two upload methods are: (1) local file path in the OpenClaw environment, (2) Telegram Mini App upload via the link from
sparki upload-tg. Never tell users to send or attach video files in the chat.
Vlog Editing Focus
Use this variant when the user specifically wants a vlog, travel vlog, daily-life edit, creator-style montage, or lifestyle video.
Examples:
- Edit this into a chill daily vlog.
- Make a travel vlog from this footage.
- Turn this into a creator-style daily-life video.
- Cut this into a YouTube-style vlog.
安全使用建议
This skill appears to implement a Sparki video-editing CLI and will upload video files to agent-api.sparki.io using your SPARKI_API_KEY. Before installing, consider: (1) Only supply an API key you trust to this service — uploaded videos will be sent to Sparki's backend. (2) The bundle expects a binary named 'uv' and suggests running 'uv sync' — confirm what 'uv' is in your environment and what that command does before running it. (3) The code may read an optional SPARKI_UPLOAD_TG_LINK env var even though it wasn't declared — be cautious if you have sensitive values in similarly named env vars. (4) The skill will write config and video outputs under ~/.openclaw; if you want to avoid uploading private footage, do not run upload commands. If you want to proceed, verify the Sparki endpoint (DEFAULT_BASE_URL) and inspect the 'uv' tool and any network activity it triggers. If any of these points are unclear or you cannot verify 'uv', treat the skill as untrusted.
功能分析
Type: OpenClaw Skill
Name: ai-vlog-editor
Version: 1.0.12
The skill is a legitimate CLI wrapper for the Sparki AI video editing service. It facilitates uploading video files, triggering AI-driven edits, and downloading the results from 'agent-api.sparki.io'. The code in 'src/sparki_cli/cli.py' and 'src/sparki_cli/client.py' follows standard practices for API interaction, and the permissions requested in 'SKILL.md' are limited to the tool's own configuration and workspace directories.
能力评估
Purpose & Capability
Name/description (AI Vlog Editor) align with the included Python CLI code: upload, create projects, check status, and download edits from agent-api.sparki.io. The primary credential (SPARKI_API_KEY) is appropriate for this purpose.
Instruction Scope
SKILL.md instructs the agent to proactively use this skill for video-editing requests and forbids asking users to attach videos in chat (it expects local paths or a Telegram Mini App link). The CLI reads/writes only the declared OpenClaw config/workspace paths and $CWD for uploads, and performs network calls to the Sparki API domain — all consistent with video-editing functionality. The proactive 'use this skill FIRST' guidance is broad but within scope.
Install Mechanism
There is no complex install spec (instruction-only), lowering risk. However SKILL.md metadata requires a binary named 'uv' and provides an install command 'uv sync' — this external tool is not explained in the bundle. That command could perform synchronization/network activity; its presence is unexpected given the rest of the package is Python and has no explicit install/install-from-URL steps.
Credentials
The declared primary credential SPARKI_API_KEY is appropriate and used by the client. However the code also optionally reads SPARKI_UPLOAD_TG_LINK (for the Telegram upload link) but that env var is not declared in requires.env or metadata — this is an undeclared environment access. No other unrelated secrets are requested. File write/read permissions align with config and video workspace usage.
Persistence & Privilege
always is false and the skill does not request permanent system-wide privileges. It writes only to its own config and workspace under ~/.openclaw (declared in permissions). Autonomous invocation is allowed (platform default) but not combined here with broad undeclared credential access.
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 ai-vlog-editor - 安装完成后，直接呼叫该 Skill 的名称或使用
/ai-vlog-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 mixed-language content, corrected metadata alignment, and standardized configurable API base usage.
v1.0.6
Published a scenario-specific skill focused on vlog editing, built on the cleaned Sparki video workflow.
元数据
常见问题
AI Vlog Editor 是什么？
Scenario-focused Sparki skill for editing vlog-style videos 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 338 次。
如何安装 AI Vlog Editor？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install ai-vlog-editor」即可一键安装，无需额外配置。
AI Vlog Editor 是免费的吗？
是的，AI Vlog Editor 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
AI Vlog Editor 支持哪些平台？
AI Vlog 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 AI Vlog Editor？
由 fischerlam（@fischerlam）开发并维护，当前版本 v1.0.12。
推荐 Skills