On an Apple Silicon Mac with a matching version of CapCut, generate editable draft projects headlessly, modify independent copies of existing multi-track drafts, or export native MP4s upon explicit request. Requires cloning the Jianying Headless core project separately; pure transcription does not use this skill.
The `mcncarl/yichen-skills` skill enables headless automation of CapCut (Jianying) on Apple Silicon Macs. It allows users to generate new, editable draft projects from scratch, create independent copies of existing multi-track drafts for modification, or export final videos as native MP4 files—all without opening the CapCut graphical interface. This skill is designed for developers and AI agents who need to programmatically control CapCut for batch video production, template-based editing, or integration into CI/CD pipelines. It requires a matching version of CapCut installed on the machine and the separate checkout of the Jianying Headless core project. The skill explicitly notes that pure transcription workflows should not use it, as it focuses on draft generation and manipulation rather than speech-to-text. Supported platforms include Apple Silicon Macs (M1, M2, M3, etc.).
npx skills add mcncarl/yichen-skillsOn an Apple Silicon Mac with a matching version of CapCut, generate editable draft projects headlessly, modify independent copies of existing multi-track drafts, or export native MP4s upon explicit request. Requires cloning the Jianying Headless core project separately; pure transcription does not use this skill.
This repo contains 2 individual skills — 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.