Auto Shorts Repurposer
v1.0.0Repurpose long-form video or audio into short-form clip plans with timestamps, hooks, captions, and packaging notes. Use when a user asks to turn a long video, podcast, or stream into Shorts, Reels, TikTok-style outputs, or highlight clips without publishing.
⭐ 8· 1.7k·5 current·5 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the actual instructions: the skill takes a long-form media source and produces clip plans, captions, and packaging notes. It does not request unrelated capabilities (no cloud creds, no publishing).
Instruction Scope
Runtime instructions are narrowly scoped to segmentation, timestamping, captioning, and packaging. Required inputs (media path/URL, transcripts, platform constraints, tone) are reasonable for this task. The docs explicitly forbid requesting posting credentials and publishing, and recommend local processing when possible.
Install Mechanism
No install spec and no code files — this is instruction-only, so nothing is written to disk or pulled from external URLs by the skill itself.
Credentials
The skill declares no required environment variables, credentials, or config paths. Mentions of optional transcription APIs are advisory and the docs instruct using user-managed API keys and not storing them, which is proportionate to the stated function.
Persistence & Privilege
always is false, user-invocable is true. The skill does not request permanent presence or system-wide changes. Autonomous invocation is allowed (platform default) but the skill contains no privileged operations that would exploit that.
Assessment
This skill appears coherent and low-risk, but take these common-sense precautions before using it: 1) Only provide media and transcripts you have the rights to repurpose and avoid sending private conversations or minors' content. 2) If you choose to run a third-party transcription service, supply your own API key to the tool (if required) and do not paste credentials into chat; prefer local transcription when privacy is important. 3) Be careful with private or pre-signed URLs — treat them as sensitive. 4) Confirm the agent does not actually publish or post content; the skill forbids publishing but verify outputs before any manual upload. 5) If the skill ever asks for social-login or posting credentials, do not provide them. These checks will keep the expected workflow private and proportional to the task.Like a lobster shell, security has layers — review code before you run it.
latestvk97apvjxe79cj1jmxkg9h6zya580tvth
License
MIT-0
Free to use, modify, and redistribute. No attribution required.