Video & Animation

Create and manage script- or audio-driven AI avatar videos from an official or saved presenter, an imported portrait, or a representative still prepared from video. Use for 数字人、数字分身、虚拟人、照片开口说话、人像口播、改稿不重拍, AI avatar, AI avatar video, avatar video, talking avatar, talking photo, photo avatar, video avatar, AI presenter, virtual presenter, virtual spokesperson, digital human, or a person's digital twin, including choosing or creating the avatar and deciding its voice, script, aspect ratio, and outp

Dub a video into another language (default English) with free open-source Kokoro TTS — translate each segment (Claude-in-the-loop), synth speech on the render host, fit it to the timeline, burn synced translated captions, and swap the audio. Use when the user says "make an English version," "dub this to English," "port this to my English channel."

Synthesizes target-language speech from text using Kokoro TTS, with speed/duration control to fit precise time windows. Handles SRT parsing, text extraction, and produces WAV segments.

Muxes normalized TTS audio segments into the original video at precise time offsets using FFmpeg, and generates the JSON report with timing, drift, and loudness metadata.

Handles audio resampling, loudness normalization per ITU-R BS.1770-4, and LUFS measurement for TTS segments to ensure broadcast-quality output.

诊断 Windows Codex shell 已出现的 helper/helper_unknown_error,外部工具启动失败,sandbox 执行或写入结果不确定及 Git dubious ownership;也用于用户明确要求的 Junction/reparse point 等特殊文件只读核对或复杂目录操作风险评估.不用于普通读取,搜索或 Git 查询.

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, v

Create, revise, review, and export Envitefy marketing videos using the local campaign engine, brand preferences, real product demonstrations, and saved campaign history. Also prepare captions and social copy for those videos.

Join a Google Meet call, transcribe live captions, optionally speak in realtime, and do the followup work afterwards. Use when the user asks the agent to sit in on a meeting, take notes, summarize, respond in-call, or action items from it.

Muxes per-shot storyboard video with Chinese and English voice-over by retiming video to match VO duration (setpts), writing Video-Chinese/ and Video-English/ (matched by shot id 01, 02, …). Use when the user wants storyboard A/V mix, storyboard A/V mix, VO dubbing mix, video retime to audio, Video-Chinese, Video-English, bilingual VO on cut video, or batch mux Video/ + Chinese/ + English/.

Design consultation: understands your product, researches the landscape, proposes a complete design system (aesthetic, typography, color, layout, spacing, motion), and generates font+color preview... (gstack)

Manage Dub short links, track conversions, and read link attribution analytics through the superagnt unified API.

Control audio generation requests before execution. Use this when the user asks for TTS, persona voice, voice change, translated dub, cloned voice take, podcast audio, or lip-sync audio handoff and the skill must classify the request before handing execution to voice-batch-runner or a video workflow.

Route generative media requests before any creative planning or provider execution. Use this when the user asks to generate, modify, dub, animate, or assemble image, video, audio, workflow, or analysis-derived media and the first decision is which generation controller should own the job.

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, la

Produce reproducible offline CSV reports with missing-value and duplicate checks, exact decimal totals, input hashes and per-claim provenance. Use when users need auditable spreadsheet summaries or data-quality reports rather than unsupported numeric narratives.

Use when a new product, collection, restock or category is being introduced and needs a marketing plan — deciding who hears about it first, how the announcement is sequenced, which channels carry it, and how the launch converts into ongoing demand rather than a single spike.

Portable checklist for gating public-facing copy before release. Use when captions, posts, manifests, topics, titles, or launch copy must be checked for generic AI wording, leaked internal labels, forbidden experiment or tool names, platform topic allowlists, CTA spam, and unsupported overclaims.

Severity-weighted BLOCK, WARN, OK reviewer method for technical and research posts. Use when reviewing X threads, announcements, captions, or launch copy for hook strength, thread arc, generic AI vocabulary, source fidelity, claim support, numeric-claim verification, and thread format before recommending publish.

Turn video and audio into text — full transcripts, timestamped segments, SRT and VTT subtitles, and the first-3-seconds hook — from one YouTube video, Short or live VOD, a whole YouTube channel in a single run, a creator's Instagram reels, a podcast episode, a Loom or a Twitch VOD, or any direct media file link. Captions are used where they exist and speech-to-text runs where they do not, in ~90 languages, with no third-party API key and no charge when a video has nothing to say. Use when the us

Turn a GitHub pull request (a PR URL, owner/repo#N, or 'this PR' in a checked-out repo) into a code-change explainer video — changelog, feature reveal, fix, or refactor walkthrough built from the diff, commits, and files: the input is a code change, not a website. Not a product promo (/product-launch-video) or a no-PR topic explainer (/faceless-explainer). Unclear → /hyperframes.

Turn arbitrary text — an article, notes, a topic, a brief — into a faceless explainer video: there is no site or footage to capture, so the visuals are invented per scene (typography, abstract graphics, diagrams, data-viz). Use for topic explainers, concept breakdowns, how-tos, listicles. Not a video built from a website (/product-launch-video — promo or tour). Unclear → /hyperframes.

Produce publication-quality product and marketing images with the bundled Creative Studio toolkit — background removal (matting) with quality tiers, white-background e-commerce main images, local object removal / retouching (inpainting), headline/caption text, logo and watermark placement, multi-layer compositing, batch platform-size exports, contact sheets, colour palettes and image QA. Use proactively for any task involving product photos, 主图/白底图/详情页/海报/广告图/素材图, 抠图、换背景、改图、去杂物、加文字、贴 logo、加水印、批量

Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet `anchor` rail is the default; embed every word only when the user explicitly wants a fully cinematic treatment. The workflow runs locally end to end, including transcription and subj