When the user says they want to make a video, promotional video, product demo, animated short, TikTok/YouTube content, or wants to modify storyboards, adjust pacing, change shots, tweak subtitles, add voiceover, or alter transitions. Uses Socratic questioning to gather video requirements and proactively activates all rendering capabilities (TTS / subtitles / 3D / shaders / audio reactivity, etc.) to output a standardized video-spec.md for rendering.
The feicaiclub/video-spec-builder skill is designed for AI agents interacting with developers and content creators who want to produce or edit video content. It employs a Socratic questioning approach to systematically explore and clarify the user's video requirements, such as format, style, pacing, narrative structure, and technical specifications. The skill then proactively triggers the full range of rendering capabilities—including text-to-speech (TTS), subtitle generation, 3D elements, shaders, audio reactivity, and more—based on the gathered information. Its primary output is a standardized `video-spec.md` file, which serves as a comprehensive blueprint for rendering engines. This skill supports platforms like Claude Code, Cursor, Codex, and similar AI agent tools, making it invaluable for streamlining video production workflows from concept to specification.
npx skills add https://github.com/feicaiclub/video-spec-builder/tree/main/skills/video-spec-builderWhen the user says they want to make a video, promotional video, product demo, animated short, TikTok/YouTube content, or wants to modify storyboards, adjust pacing, change shots, tweak subtitles, add voiceover, or alter transitions. Uses Socratic questioning to gather video requirements and proactively activates all rendering capabilities (TTS / subtitles / 3D / shaders / audio reactivity, etc.) to output a standardized video-spec.md for rendering.
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.