A generic CapCut draft generation and AI video inspection skill. Used to apply local AI videos to existing CapCut draft templates, generate new drafts that can be displayed and edited on the CapCut homepage, extract template styles, validate draft structures, perform frame sampling to check for AI traces, plan repair windows, and execute local RIFE frame interpolation.
This skill provides a comprehensive workflow for integrating locally generated AI videos into CapCut's draft ecosystem. It allows users to take any AI-generated video output and automatically apply it to a pre-existing CapCut draft template, producing a new, editable draft that appears directly on the CapCut homepage—no manual import or template setup required. Beyond draft generation, the skill includes advanced AI video forensics: it can extract template styling parameters (like transitions, effects, and text overlays) for reuse, validate the internal structure of CapCut draft files to ensure compatibility, and perform frame-by-frame sampling to detect subtle AI artifacts (e.g., inconsistent motion or texture anomalies). It also plans optimal repair frames based on detected issues and supports local RIFE (Real-Time Intermediate Flow Estimation) frame interpolation to smooth out jittery or low-frame-rate sequences. This tool is essential for developers and creators who want to automate CapCut project creation from AI pipelines, while also maintaining quality control through automated AI trace detection and video smoothing. It works directly on local files and does not require cloud services, ensuring privacy and speed.
npx skills add https://github.com/binggandata/bggg-skills/tree/main/bggg-tiktok-capcutGeneric CapCut draft generation and AI video inspection skill. Used to apply local AI videos to existing CapCut draft templates, generate new drafts that can be displayed and edited on the CapCut homepage, extract template styles, validate draft structures, perform frame sampling to check for AI traces, plan repair windows, and execute local RIFE frame interpolation.
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.