← 返回 Skills 市场
325
总下载
6
收藏
0
当前安装
9
版本数
在 OpenClaw 中安装
/install sparki-video-editor
功能描述
AI video editor for creators. Transform raw footage into polished vlogs, talking-head videos, or social media content (TikTok/Shorts/Reels). Control the work...
安全使用建议
This skill appears to do what it claims, but before installing or using it consider: 1) You will need to provide a SPARKI_API_KEY and the skill will store it in the agent's config — do not paste that key into chat messages. 2) The skill will install a third-party CLI ('sparki-cli') via the 'uv' tool — verify you trust that package source (review sparki-cli on PyPI or the vendor). 3) Videos and metadata will be uploaded to Sparki's service (network access declared for agent-api.sparki.io) and outputs are written to $HOME/.openclaw/workspace/sparki/videos; if your videos contain sensitive information, confirm Sparki's privacy/storage policy first. 4) The SKILL.md requires you to run sparki doctor and to check version consistency — follow that step to avoid running commands from a stale skill description. If you want extra assurance, request the sparki-cli package provenance (PyPI link or GitHub repo) and confirm the network domain and data retention policy before proceeding.
功能分析
Type: OpenClaw Skill
Name: sparki-video-editor
Version: 1.1.0
The sparki-video-editor skill provides a structured interface for an AI video editing service. It installs the 'sparki-cli' tool via 'uv' and communicates with 'agent-api.sparki.io'. The requested filesystem permissions are limited to specific workspace and configuration directories, and the instructions in SKILL.md are focused on operational reliability, version consistency, and user workflow. No evidence of malicious intent, data exfiltration, or unauthorized execution was found.
能力标签
能力评估
Purpose & Capability
Name/description (AI video editor) align with what the skill does: it runs a sparki CLI, uploads local or Telegram-mini-app videos, polls for tasks, and downloads results. The declared primaryEnv (SPARKI_API_KEY), required binary (uv), and declared FS/network permissions match expected needs for invoking a remote video-editing service and storing outputs.
Instruction Scope
SKILL.md instructs the agent to run sparki CLI commands (doctor, setup, upload-tg, assets list, edit, status, download) and to check CLI version before running commands. It also instructs reading local files ($CWD) and writing to agent config and its workspace for video outputs. Those actions are reasonable for local-file upload and CLI configuration, but they do grant the skill access to the working directory and to writing into $HOME/.openclaw; users should be aware that videos and related metadata will be transmitted to Sparki's service.
Install Mechanism
This is instruction-only but includes an installation step using the 'uv' tool: 'uv tool install --upgrade sparki-cli'. That will install the sparki-cli tool (likely from PyPI) into uv's tool bin. Installing a third-party CLI at runtime is expected for this skill but is a moderate-risk action because it executes code obtained from external package repositories; this is proportional to the skill's functionality but worth noting.
Credentials
Only one credential is declared: SPARKI_API_KEY (the primary credential). The SKILL.md explicitly guides obtaining the key from the Sparki Telegram bot and using 'sparki setup --api-key <KEY>'. No unrelated secrets or high-privilege env variables are requested. The skill will store config under $HOME/.openclaw, which is expected for CLI auth storage.
Persistence & Privilege
always is false and the skill does not request permanent platform-wide presence. It writes to its own agent config/workspace paths (permitted) and does not modify other skills or system-wide settings. Autonomous invocation is allowed by default (not flagged by itself).
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 sparki-video-editor - 安装完成后，直接呼叫该 Skill 的名称或使用
/sparki-video-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
v1.1.0
sparki-cli now installs from PyPI.
New commands: sparki doctor, sparki assets delete.
upload / edit / run accept positional files / object-keys, plus --dir for directory scans.
Style catalog restructured to 4 categories (Vlog / Clips / Narrative / Tools).
Error handling information updated.
v1.0.8
Support update.
v1.0.7
Updated metadata.
v1.0.6
New Features
Style-Clone mode — clone editing styles from a reference video.
v1.0.5
Sparki AI Video Editor
v1.0.4
- Updated API domain in skill metadata from agent-api-dev.aicoding.live to agent-api.sparki.io
- No user-facing command or flow changes
- Internal metadata adjustment to production API endpoint
v1.0.3
AI-powered video editing — turn raw footage into polished vlogs, highlight reels, TikTok/Shorts/Reels, montages, and more. Control the editing flow through Telegram chat, or let your ClawBot handle it automatically. Pick a style and let Sparki handle the rest, or describe what you want in your own words.
v1.0.1
Sparki AI Video Editor
v1.0.0
First release of the Sparki Video Editor skill for OpenClaw.
Features
- CLI with full command set: setup, upload, upload-tg, assets, edit, status, download, history, run
- End-to-end workflow (sparki run): upload, edit, poll, download in a single command
- Two editing modes: Style-Guided (pick from style catalog) and Prompt-Driven (natural language description)
- Style catalog: 20 styles across 7 categories (Vlog, Montage, Commentary, Talking Head, Long-to-Short, AI Caption, Video Resizer)
- Telegram Mini App integration: upload-tg command returns the Mini App upload link for uploading via Telegram
- Structured JSON output: all commands return {"ok": true/false, "data": ..., "error": ...} for reliable AI parsing
- Configuration management: API key stored in ~/.openclaw/config/sparki.json with environment variable override (SPARKI_API_KEY)
- Local project history: tracks recent task IDs for quick history lookups
- SKILL.md dispatch document: complete instructions for OpenClaw bot to guide users through video editing workflows
元数据
常见问题
Video Editor Sparki 是什么？
AI video editor for creators. Transform raw footage into polished vlogs, talking-head videos, or social media content (TikTok/Shorts/Reels). Control the work... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 325 次。
如何安装 Video Editor Sparki？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install sparki-video-editor」即可一键安装，无需额外配置。
Video Editor Sparki 是免费的吗？
是的，Video Editor Sparki 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Video Editor Sparki 支持哪些平台？
Video Editor Sparki 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（darwin, linux, windows）。
谁开发了 Video Editor Sparki？
由 Sparki（@sparki-io）开发并维护，当前版本 v1.1.0。
推荐 Skills