视频剪辑助手

The name and description (video scripts, subtitles, titles, tags) align with the SKILL.md content. The skill declares no binaries, no env vars, and no install — which is coherent for an instruction-only text-generation helper. Minor note: the usage example shows a CLI invocation (video-editor-helper ...) even though no binary or install is provided; this is likely illustrative rather than an actual executable dependency.

SKILL.md contains only high-level functionality and a usage example; it does not instruct the agent to read local files, access credentials, or call external endpoints. That keeps its runtime scope narrow and consistent. The file is somewhat vague about how user content (video transcripts, raw video) should be supplied or handled — no instructions to upload data or use third-party APIs are present.

No install specification or code files are included, so nothing is written to disk or fetched at install time. This is the lowest-risk install posture.

No environment variables, credentials, or config paths are requested. The absence of required secrets is proportionate to a text-generation helper.

always is false and autonomous invocation is allowed (the platform default). The skill does not request persistent or elevated privileges and does not attempt to modify other skills or system-wide settings.