Scenario-focused Sparki skill for turning long videos into short-form clips while using the latest official Sparki setup, API-key, and upload workflow guidance.

This skill appears to implement a Sparki video CLI and mostly behaves as advertised, but take these precautions before installing or running it: - Ask the publisher what the 'uv' binary is and why it's required; avoid running 'uv sync' unless you trust that tool. 'uv' could run arbitrary commands depending on its implementation. - The bundle includes Python source and a pyproject, but no clear pip/install step for dependencies (typer, httpx, pydantic). Run in a controlled environment (container or VM) and install dependencies from the official registries if you want to execute it. - Limit the API key you provide (use a key with minimal scope/quota) and rotate it if you test the skill. - Review the included source (already bundled) yourself or have someone you trust review it—pay attention to any networking or file writes beyond the declared paths. - If you cannot validate 'uv' or the install behavior, run the tool only in an isolated sandbox and avoid providing high-privilege or long-lived credentials.

Type: OpenClaw Skill Name: long-to-short Version: 1.0.12 The 'long-to-short' skill is a legitimate CLI tool for the Sparki AI video editing service. It manages API authentication, video uploads to agent-api.sparki.io, and project status tracking. File system access is appropriately limited to ~/.openclaw/config for settings and ~/.openclaw/workspace/sparki/videos for output. The code follows standard Python practices using typer and httpx without any signs of obfuscation, data exfiltration, or unauthorized execution.