One-tap video creation using CapCut (Jianying) on Android. Clears the 'A_latest' album, retrieves images by time or content, copies them to 'A_latest', and automates CapCut with multi-tap interactions.
X-OmniClaw is an AI agent skill designed for automated one-tap video creation on Android using the CapCut (Jianying) app. It streamlines the workflow by first ensuring a clean slate: it clears the 'A_latest' album using the `copy_images_to_album` command with a clear-only flag. Then, it retrieves images either chronologically via `list_gallery_images` or semantically through `image-memories` (content-based search). The chosen images are copied to the 'A_latest' album, after which the skill automates CapCut by navigating to 照片视频 (Photos & Videos), selecting 'A_latest' album, then 全部 (Select All), and performing multi-tap interactions repeated N times (where N = K). This skill is particularly useful for developers and power users who need to rapidly generate video compilations without manual intervention. It supports Android platforms and integrates with CapCut and the device's gallery via ADB or automation APIs.
npx skills add OPPO-Mente-Lab/X-OmniClawOne-tap video creation using CapCut (Jianying) on Android. Always clear 'A_latest' first (using copy_images_to_album with clear-only flag), then retrieve images by time (list_gallery_images) or by content (image-memories). Copy them to 'A_latest' (with clear_album_first), then in CapCut navigate to 照片视频 (Photos & Videos) → A_latest → 全部 (Select All), perform multi-tap, N = K times.
This repo contains 1 individual skill — each has its own dedicated page.
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.