Video & Animation

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 subject matting; split multi-shot footage before applying it.

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.

用代码做讲解视频的完整方法,不限话题(科普、AI 用法、历史、评测……):选题→事实表→文案与台词检查→配音字幕→按「片型 × 场景 × 画风」做画面(字体与对话框随场景走,可选生图角色表演)→渲染混音→封面竖版→验收。含片型库、场景库、画风库、设计库(字体/色板/组件/动效)与频道配置,均留新增口子。用户说「做新一期」「换个场景/画风」「加一种片型/场景/画风」「做角色动画段」时使用。

End-to-end multi-tenant brand explainer/promo-video pipeline. Generates a complete branded video from a URL — extracts brand identity, writes script, generates voice + AI avatar + B-roll images + music underbed, assembles in HyperFrames, and renders. Trigger phrases include "Hyper Frames for <url>", "make a Hyper Frames video for <brand>", "Hyper Frames promo for <url>", "explainer video for <brand>", or just "Hyper Frames <url>".

Make a narrated, captioned explainer video from anything — a blog post or article URL, a paper, one or more pull requests, a branch or diff, a repo, or rough notes — or revise an existing one. Triggers on "make a video of…", "/video <link|PRs|repo>", "explain this as a video", "video walkthrough of these PRs", or changes to a previous video (fix a scene, shorten, change voice, re-render).

Produce word-level timed subtitles from the final audio with faster-whisper and burn them in. Use after the final cut renders.

Build diagrams, equations, and kinetic type for explainers with Manim, Motion Canvas, or Hyperframes. Use for any shot of kind manim or html.

Make narrated, animated explainer videos (3Blue1Brown-style Manim diagrams, real app screenshots, ElevenLabs voice, synced captions). Use when asked to create an explainer or walkthrough video, re-cut or shorten an existing one, or change its narration voice.

Generate expressive narration audio with Gemini TTS, steering emotion per paragraph. Use whenever narration, voiceover, or spoken audio is needed for a video.

Use when the talent's recording arrives for a reelkit episode — transcribing it locally with Whisper, correcting captions to the script, re-timing scenes, reviewing the changes with the user and applying them.

Turn approved keyframes into short generated video shots with Veo or Seedance through OpenRouter. Use only after the animatic is approved.

Coordinate the build of one or more signed videos of the current product with subagents (source recon, product truth, UI specs, voice, one builder per video), re-run QA itself, then deliver. A light coordinator that never builds itself. Run only when the user types /video-build.

Say where this session stands in the Product Video Skills workbench (setup state, which product and video the current folder belongs to, the stage of every video) and the exact next command to type. Also answers "how do I..." questions about the workbench from its docs.

Turn a product's real frontend code into 1:1 rebuild specs for a video, one read-only subagent per screen, each returning static HTML, CSS with every variable resolved to its literal value and cited (role/path:line@sha), every state, transitions with exact durations and easings, icons from the code's own icon sets, and the exact i18n strings; plus resolve_tokens.py to write the product's design tokens to kit/tokens.css. Use it whenever a screen of the product has to appear in a video, when writing or fixing video/src/app.css or the template markup, when someone asks for exact sizes, colors, fonts, paddings, animations or icons of a screen, when a rebuilt screen "looks off" next to the real app, and when the design tokens or theme of a product need extracting. Framework adapters cover Angular with PrimeNG (proven), React, Vue, Tailwind and plain HTML (unproven).

Use when being asked to create an explainer video.

Start a new video of the current product - create videos/<video>/, write BRIEF.md, the feature coverage matrix (COVERAGE.md) and the claims sheet (CLAIMS.md), propose chapters, then stop for the reviewer's sign-off. Never builds. Run only when the user types /video-new.

Turn a batch of reviewer feedback on the product's videos into one table per video, fix every video that got notes in parallel (one subagent each) while keeping approved parts, re-run QA and parity, bump versions and deliver. Run only when the user types /video-review.

Compose a narrated product demo in HyperFrames: the stage (the product UI rebuilt at its real viewport and scaled to 1080p, camera, rack focus with veil, chapter titles, cursor and clicks, typing, streaming text, pop-ups, toasts, scrolls, end screen and lockup) and the build.py that anchors every beat to a word of the narration. Use it whenever you write or edit a video's video/build.py, src/template.tpl or src/app.css, place a beat on a word, add a chapter, a click, a pop-up or a push-in, frame a screen, build the end screen or lockup, snapshot setup beats, or render a draft or delivery MP4 of a product video in this workbench. Also use it when someone says "the cursor is off", "too zoomed in", "too fast", "it feels chaotic", "the title flashes", "sync the UI to the voice", or asks for a walkthrough, demo or pitch video of a UI.

Check this machine and install the pinned video toolchain of the Product Video Skills workbench (HyperFrames CLI, its rendering Chrome and its agent skills from the same release, the Python environment, the speech model for QA), then run the self-check. Safe to run again. `/video-setup check` only reports.

Pin a product's source code (read-only exports in sources/ plus sources.lock), confirm that the pinned commit is what runs in production, and map every screen of a video brief to its route, components, i18n strings and state, written to the video's SOURCES.md. Use it whenever a video needs to know where a screen lives in the code, when sources/ is missing or stale, before ui-spec-from-code or product-truth start on a video, after the product's frontend changed ("what changed", "which videos are affected", "refresh the sources", "is this checkout current", "which commit is in prod"), and when there is no code and you need an inventory of the no-code references (recordings, recovered captures, docs) a screen can be rebuilt from.

Write a product video's narration and turn it into voice clips with word timings, pronunciation fixes, sound effects and even loudness. The script becomes a table of moments and then audio/lines.tsv (one clip per sentence, with role and speed columns); tts.py voices it with ElevenLabs or the free macOS say voice, maps brand respellings back to the on-screen spelling, normalizes every clip and writes audio/timings.json for the composer; make_sfx.py builds typing tracks from real keystrokes and places recorded click and pop sounds. Use it whenever a video needs a script, narration, voice-over, lines.tsv, timings.json, TTS, a new take, a voice or casting choice, a pronunciation fix ("it says the name wrong"), a changed sentence, a tone note ("too hype", "sounds cut off"), audio levels, a click at the end of a clip, typing or click sounds, or when the build stage asks for the voice. Also use it for silent loops, which still need a moment table and SFX.

The animation rules that keep HyperFrames' parallel render workers from dropping, flashing or flickering elements, plus a static lint (lint_motion.py) that finds the violations in a video's template before it costs a render. Use it whenever you write or edit GSAP tweens, timelines, cursors, camera moves, typing, scrolls or pop-ups in a HyperFrames composition or a video's src/template.tpl, whenever a render shows flicker, stutter, an element that vanishes on some frames, a title that flashes, or a "WORKER PATTERN" line from scan_render.py or qa.py, and whenever the preview looks right but the MP4 does not. Also use it to review someone else's timeline code before rendering.

TikTok竞品洞察分析工具，实时监测竞品流量效果、快速拆解对标竞对作品、精准拆解透视竞品流量及策略、高效搭建关键词库，适用于TikTok品牌方、创作者等进行竞品分析、流量优化和关键词研究。提供3个能力①关键词搜索（可按点赞/相关度排序、发布时间筛选）②博主作品获取，按主页链接或用户名批量获取公开作品列表，支持最新/最热排序 ③视频评论抓取，按视频链接或作品 ID 获取评论内容、评论者与互动数据，输出结构化 JSON（含作者、互动数据、标签、链接）。

Check a rendered product video before anyone else sees it: worker-pattern flicker, black frames, loudness and true peak, clipping, clicks at clip edges, overlapping narration, speech to text against the script, banned terms and legacy names, camera zoom, contact sheets, frame strips at transitions and parity against the approved version; then write qa/REPORT.json, the only thing deliver.py accepts. Use it after every HyperFrames render, whenever someone asks "is the render clean", "QA this", "check the video", "check the audio", "why does it flicker", "there is a click", "compare v3 with v2", "did the approved part change", or before showing, sending, uploading or delivering any MP4, even when the request does not say QA. Also use it to triage a defect a reviewer reported in a render.