agent-skills 是做什麼的？
OpenClip 字幕：將樣式化的動態字幕嵌入短影片中。
OpenClip 字幕：將樣式化的動態字幕嵌入短影片中。
這是一個 AI 代理技能，用於將 OpenClip 生成的樣式化動態字幕直接燒錄到短影片片段中。開發者可以利用此技能自動化字幕嵌入流程，無需手動操作影片編輯軟體。該技能支援多種影片格式，並提供可自訂的字幕樣式與動畫效果，非常適合社交媒體內容創作者、行銷團隊或任何需要快速為短影片添加專業字幕的場景。技能基於 OpenClip 的 API 或 CLI 工具運行，可無縫整合到現有的 CI/CD 或內容生成pipeline中。
npx skills add https://github.com/OpenClip-App/agent-skills/tree/main/skills/openclip-captionsOpenClip 字幕：將樣式化的動態字幕嵌入短影片中。
This repo contains 9 individual skills — each has its own dedicated page.
OpenClip clipping: long video → short vertical clips ranked by virality score.
OpenClip agent skill for clipping long-form into short-form social clips.
Convert and compress media from your agent with OpenClip - video to mp4, webm, mov, mkv, or gif, and audio to mp3, aac, wav, or flac. FREE with just an OpenClip account, no subscription. Use when asked to
Remove the background from an image with OpenClip and get back a transparent PNG. FREE with just an OpenClip account, no subscription. Use when asked to
Turn one long video into a full batch of platform-ready short clips for TikTok, Reels, and YouTube Shorts with OpenClip - find the moments, reframe to vertical, burn in captions, and write the post copy for each. Use when asked to
Pull still frames out of a video as thumbnail images with OpenClip, then compress, resize, crop, or reformat them to jpg, png, or webp. FREE with just an OpenClip account, no subscription. Use when asked for
Transcribe video or audio to JSON, SRT, and VTT with speaker diarization and time codes, using OpenClip. FREE with just an OpenClip account, no subscription. Use when asked to
Generate short vertical UGC-style ad clips from a structured creative brief with OpenClip, picking from a roster of AI creators. Use when asked to
Edit a video file from your agent with OpenClip - trim, crop, reframe to 9:16 or 1:1, resize, rotate, flip, compress to a target size, or mute the audio. FREE with just an OpenClip account, no subscription. Use when asked to
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.