Video & Animation

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

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.

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.

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.

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.

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 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

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)

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/.

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

Where to find and how to verify data for the MGT4897 DXB report — Dubai Airports newsroom releases, the DWC expansion page, ICAO and IATA statistics, ACI airport rankings and ASQ, UAE government statistics, and the academic journals that carry airport operations and air transport demand research. Includes the source-quality hierarchy, the data-log protocol, and the rules against fabricated figures. Use when sourcing any number, fact, or journal reference.

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

Call third-party AI services through ibl.ai's External Service Proxy — a platform-admin gateway that fronts ElevenLabs (TTS, voice management, dubbing, sound generation, audio isolation, history/quota) and HeyGen (avatar & template video, translation, photo avatars, assets, voices, quota, webhooks). Discover the available services and their endpoints, then POST a request envelope (body/query/headers/path_params, plus multipart files) to invoke one action — the provider API key is stored server-s

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.

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.

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.

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

Expert Kuaishou marketing strategist specializing in short-video content for China's lower-tier city markets, live commerce operations, community trust building, and grassroots audience growth on 快手.

Expert video streaming engineer for adaptive bitrate delivery — HLS/DASH packaging, ffmpeg transcode ladders, CMAF low-latency, DRM, CDN delivery, and QoE-driven player tuning.