生成本地或可选的OpenAI旁白，准备音乐和音效，并为技术视频混合音频。
Video Forge 是一个专注于技术视频音频工作流的智能技能，帮助开发者高效处理旁白生成、音乐和音效准备以及最终混音。它支持三种旁白模式：本地Kokoro合成、文件导入和OpenAI付费语音调用（需设定每字符费率及云预算），并强调在完整导出前验证符号、名称、缩写和代码的发音。该技能对时长有严格逻辑——旁白不能超过场景时间线，短旁白会保留剩余视觉时长——并自动对生成的人声进行两遍响度归一化，而导入的人声则保持原始电平。音乐以设定音量循环播放，并在时间戳字幕活动时自动衰减，确保清澈的语音表现。此外，技能要求披露生成的旁白、保留音频信用，并遵循节拍驱动短片的FPS/BPM时钟来匹配动效与重音，同时避免使用未授权的商业曲目。
npx skills add https://github.com/Sanidhya14321/video-forge/tree/HEAD/skills/video-audio请阅读音频工作流程。优先使用已审核音频或本地 Kokoro。在完整导出前，验证符号、名称、缩写和代码的发音。一篇读起来顺畅的脚本，说出来可能并不顺畅。
使用 narration.provider: file 表示提供的音频，kokoro 表示本地合成，或 openai 表示明确选择的付费语音调用。OpenAI 需要预先验证的每字符费率以及云预算；支持的模型记录在项目合同中。凭证应放在环境变量中。
运行器拒绝时长超过场景时间线的旁白。短旁白会保留剩余的视觉时长。音乐以设定的音量循环播放，并在时间戳字幕词活动时被衰减。生成的语音在混音前会经过测量到的两通响度归一化处理。提供的语音电平保持不变。检查实际音频，不要声称未测量到的响度目标。
生成的旁白必须在发布文案中披露。自定义声音克隆和托管音乐生成是参考工作流程。将音频信用与工具包代码许可分开保留。
对于节拍驱动的短片，请遵循短片指导。从与动效相同的 FPS/BPM 时钟中推导出提示时间，有选择性地强调重要的转换，并保持语音清晰度。不要导入未经授权使用的流行商业曲目。
This repo contains 4 individual skills — each has its own dedicated page.
Transcribe audio locally, preserve word timestamps through edits, style readable captions, and prepare editable subtitle sidecars.
Export social video variants, inspect playable media, review thumbnails and caption placement, and prepare publishing assets.
Repurpose recordings with deliberate segment selection, silence removal, reframing, B-roll planning, and editable cut decisions.
Set up or diagnose Video Forge in an agent host, verify local rendering prerequisites, and choose a usable production or planning path.
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.