What does Cuti-Harness do?
Overlay words and titles onto videos. After transcription, you write HyperFrames HTML and pass it to media.hyperframes_caption for rendering.
Overlay words and titles onto videos. After transcription, you write HyperFrames HTML and pass it to media.hyperframes_caption for rendering.
The VideoVerses/Cuti-Harness skill enables you to dynamically overlay textual content—such as captions, titles, or annotations—onto video frames. It integrates with a transcription pipeline: once the source video transcript is available, you craft a custom HyperFrames HTML document that defines where and how each text element appears. This HTML is then consumed by the media.hyperframes_caption tool, which renders the final composited video. The skill is particularly useful for adding synchronized subtitles, motion graphics titles, or callout text in a programmable, frame-accurate manner. It supports any video processing environment that can invoke the HyperFrames rendering engine, making it suitable for automated video production workflows, content repurposing, and post-production captioning tasks.
npx skills add https://github.com/VideoVerses/Cuti-Harness/tree/main/services/video-runtime/skills/builtin/sound/hyperframes-captionsOverlay words and titles onto videos. After transcription, you write HyperFrames HTML and pass it to media.hyperframes_caption for rendering.
Extract frames or short clips from videos using ffmpeg.
Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.
Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.
Obra superpowers agent skills.
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio...
End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.