Ui2v
illli-studio/ui2v
A skill your agent uses when helping users discover, install, publish, share, sync, or update UI2V video motion assets and HyperFrames motion packages.
为 HyperFrames 口播或旁白项目创建、修复并验证固定舞台，锁定数字人 PIP 的区域、裁切、人物安全区和不透明背景，归档输入，生成 manifest 与 template handoff，并在就绪后按“字幕驱动的全镜头静态审核→动效”门禁路由到 hyperframes-scene-animator。适用于“新建 HyperFrames…
Install Talking Head Hyperframes
$ npx skills add bozhouDev/video-skills-toolkit --skill talking-head-hyperframes -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install bozhouDev/video-skills-toolkit talking-head-hyperframes --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/bozhouDev/video-skills-toolkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/talking-head-hyperframes .claude/skills/talking-head-hyperframes && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "talking-head-hyperframes" agent skill from https://github.com/bozhouDev/video-skills-toolkit/tree/main/skills/talking-head-hyperframes into .claude/skills/talking-head-hyperframes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "talking-head-hyperframes", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/bozhouDev/video-skills-toolkit/tree/main/skills/talking-head-hyperframesType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add bozhouDev/video-skills-toolkit --skill talking-head-hyperframes -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install bozhouDev/video-skills-toolkit talking-head-hyperframes --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bozhouDev/video-skills-toolkit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/talking-head-hyperframes .agents/skills/talking-head-hyperframes && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "talking-head-hyperframes" agent skill from https://github.com/bozhouDev/video-skills-toolkit/tree/main/skills/talking-head-hyperframes into .agents/skills/talking-head-hyperframes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "talking-head-hyperframes", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add bozhouDev/video-skills-toolkit --skill talking-head-hyperframes -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install bozhouDev/video-skills-toolkit talking-head-hyperframes --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bozhouDev/video-skills-toolkit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/talking-head-hyperframes .cursor/skills/talking-head-hyperframes && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "talking-head-hyperframes" agent skill from https://github.com/bozhouDev/video-skills-toolkit/tree/main/skills/talking-head-hyperframes into .cursor/skills/talking-head-hyperframes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "talking-head-hyperframes", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/bozhouDev/video-skills-toolkit.git --path skills/talking-head-hyperframes--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add bozhouDev/video-skills-toolkit --skill talking-head-hyperframes -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install bozhouDev/video-skills-toolkit talking-head-hyperframes --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bozhouDev/video-skills-toolkit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/talking-head-hyperframes .gemini/skills/talking-head-hyperframes && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "talking-head-hyperframes" agent skill from https://github.com/bozhouDev/video-skills-toolkit/tree/main/skills/talking-head-hyperframes into .gemini/skills/talking-head-hyperframes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "talking-head-hyperframes", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install bozhouDev/video-skills-toolkit talking-head-hyperframesInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add bozhouDev/video-skills-toolkit --skill talking-head-hyperframes -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/bozhouDev/video-skills-toolkit.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/talking-head-hyperframes .github/skills/talking-head-hyperframes && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "talking-head-hyperframes" agent skill from https://github.com/bozhouDev/video-skills-toolkit/tree/main/skills/talking-head-hyperframes into .github/skills/talking-head-hyperframes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "talking-head-hyperframes", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add bozhouDev/video-skills-toolkit --skill talking-head-hyperframes -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install bozhouDev/video-skills-toolkit talking-head-hyperframes --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bozhouDev/video-skills-toolkit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/talking-head-hyperframes .opencode/skills/talking-head-hyperframes && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "talking-head-hyperframes" agent skill from https://github.com/bozhouDev/video-skills-toolkit/tree/main/skills/talking-head-hyperframes into .opencode/skills/talking-head-hyperframes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "talking-head-hyperframes", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
talking-head-hyperframes- GitHub stars
- 150
- Token cost
- ~927 tokens
- SKILL.md length
- 213 words
- Files
- 90 (incl. scripts, references, assets)
- Skills in repo
- 12
- Repo updated
- First seen
- Licence
- MIT
At a glance
为 HyperFrames 口播或旁白项目创建、修复并验证固定舞台，锁定数字人 PIP 的区域、裁切、人物安全区和不透明背景，归档输入，生成 manifest 与 template handoff，并在就绪后按“字幕驱动的全镜头静态审核→动效”门禁路由到 hyperframes-scene-animator。适用于“新建 HyperFrames…
- Works in 4 steps: 主 Agent… → 方案锁定后，互不冲突的单镜头实现尽量委派给快速子 Agent；子 Agent… → 依据对齐字幕为全片划分镜头，先生成每个镜头“信息完全呈现时”的最终静态页，组成可连… → …
- Tasks that involve Motion graphics
- SKILL.md covers 先路由意图, 唯一职责, 就绪状态 and 脚手入口, plus 2 more sections
- Calls npm and node
What it does
Talking Head Hyperframes is an agent skill from bozhouDev/video-skills-toolkit. 为 HyperFrames 口播或旁白项目创建、修复并验证固定舞台，锁定数字人 PIP 的区域、裁切、人物安全区和不透明背景，归档输入，生成 manifest 与 template handoff，并在就绪后按“字幕驱动的全镜头静态审核→动效”门禁路由到 hyperframes-scene-animator。适用于“新建 HyperFrames 口播模板”“准备或修复数字人/PIP”“导入音频字幕和制作资料”“检查模板能否开工”等请求；不负责镜头导演、内容场景、整片渲染或审片整改。
Its SKILL.md is about 930 tokens, which your agent loads only when the skill is triggered. The skill folder holds 96 other files, including scripts, reference files and assets (for example `agents/openai.yaml`, `assets/hyperframes-project/DESIGN.md` and `assets/hyperframes-project/caption-overrides.json`).
It sits in Media & Creative, covering Motion graphics. It works with HeyGen and npm. The repository describes itself as: Video skills toolkit for Remotion talking-head, sketch story, and audio-to-subtitles workflows. The licence is MIT.
When your agent uses it
- Tasks that involve Motion graphics
Example prompts
- “字幕驱动的全镜头静态审核→动效”
- “新建 HyperFrames 口播模板”
- “准备或修复数字人/PIP”
- “/talking-head-hyperframes”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- 主 Agent 保持唯一导演与集成所有权：它负责字幕分段、镜头规划、画面层级、文字与素材取舍、每个镜头具体怎么写、动效语义与最终审查。
- 方案锁定后，互不冲突的单镜头实现尽量委派给快速子 Agent；子 Agent 只按逐镜确定稿编码，不得重做导演、改文案、改镜头数量或改全局转场语言。
- 依据对齐字幕为全片划分镜头，先生成每个镜头“信息完全呈现时”的最终静态页，组成可连续审阅的联系表。
- 只有用户明确批准整套静态镜头后，下游才能写入进场、语义动效、转场、声音 cue 或整片预览。修改期间仍停留在静态阶段，不得用技术 proof 代替人的创意审核。
What it can do on your machine
Read from SKILL.md and the folder at commit 4766a16. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
npmnode
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Talking Head Hyperframes loads about 927 tokens when it runs, and up to ~4.9k if it reads all its reference files. Until then it costs about 67 tokens; SKILL.md has 213 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from bozhouDev/video-skills-toolkit at commit 4766a16, republished under its MIT licence (© bozhouDev). 213 words, ~927 tokens.
Download SKILL.mdSave it as
.claude/skills/talking-head-hyperframes/SKILL.md (or your agent's skills folder). This skill also uses 89 other files; get the full folder from GitHub.- name
- talking-head-hyperframes
- description
- 为 HyperFrames 口播或旁白项目创建、修复并验证固定舞台，锁定数字人 PIP 的区域、裁切、人物安全区和不透明背景，归档输入，生成 manifest 与 template handoff，并在就绪后按“字幕驱动的全镜头静态审核→动效”门禁路由到 hyperframes-scene-animator。适用于“新建 HyperFrames 口播模板”“准备或修复数字人/PIP”“导入音频字幕和制作资料”“检查模板能否开工”等请求；不负责镜头导演、内容场景、整片渲染或审片整改。
Talking Head HyperFrames · Template Factory
只产出经过舞台证明的固定模板和可审计交接。内容执行属于 hyperframes-scene-animator。
先路由意图
- 只建或修复固定舞台、归档输入、检查就绪状态：由本 Skill 执行。
- 用户要求制作镜头，而工程尚无合格模板：先完成本 Skill 的职责，再按交接状态停止或路由。
- 工程已经
READY_FOR_EXECUTION，且用户只要求镜头实现、语义动效、转场、声音、proof 或整改：直接路由到hyperframes-scene-animator，不要复制其流程。 - 用户明确调用本 Skill 做内容场景时，仍按上述边界路由，不能越权代做。
生成或验证工程前，必须读取当前启用的 hyperframes 与 hyperframes-cli skills。不要复制它们的运行时规则；所有 scaffold、校验和舞台 proof 都通过生成项目公开的 package scripts 复现。若这些脚本或实现资源尚未提供，明确报告缺少的能力并停止，不要临时发明替代工程。
唯一职责
本 Skill 负责：
- 创建或修复固定模板与稳定根 composition；
- 归档用户已经提供的锁定输入，保留源路径、项目相对路径、大小与 SHA-256；
- 校验媒体可解码性和时长、字幕 schema/时间、motion contract 覆盖与 source hash；
- 写 manifest 和 template handoff；
- 运行只证明固定舞台的结构检查与 stage proof；
- 根据就绪状态停止或路由下游。
本 Skill 不导演镜头，不写内容场景，不选择语义动效或转场，不做 SFX/BGM 设计，不渲染整片，不审片，也不整改内容实现。不得为了演示而加入标题页、三卡片、流程图、TopBar、通用 enterStyle 或全局 crossfade。
就绪状态
允许缺少正式输入时创建固定模板，但必须把状态写成 TEMPLATE_ONLY。manifest 与 handoff 应逐项列出每个缺失或无效输入，并给出期望路径、实际路径以及可获得的 hash/校验结果；不得伪造占位输入或假装就绪。
只有以下各项全部有效且相互一致时才写 READY_FOR_EXECUTION：
- 可解码且有精确时长的锁定完整人声音频；
- 非空、时间有效、与音频时长一致的对齐字幕；
- 用户已确认的导演脚本与制作规格；
- 素材计划；
- 覆盖整片、字段完整的 motion contract；
- 上述锁定输入的源路径、项目相对路径和 SHA-256，以及 contract source hash 比对结果。
口播视频、录屏、截图和字体按实际提供情况归档并记录；缺少可选媒体不冒充必填失败。输入矛盾、导演未确认或 source hash 不一致时保持 TEMPLATE_ONLY 并停止升级状态。
脚手入口
生成前读 references/project-layout.md 确认固定层与下游所有权，再读 references/input-handoff.md 执行输入、hash 和就绪门。
只要挂载数字人或 PIP 占位，还必须完整读取 references/pip-contract.md。PIP 不是一个可随手摆放的视频：模板必须锁定外圈、媒体区、层级、裁切、人物安全区、不透明背景和审查证据。当前 Bozhou Digital Twin 的默认裁切是 object-fit: cover; object-position: 66.7% 50%；更换人物时允许用脚手参数覆盖，但覆盖值必须进入 manifest 并通过静态页与成片放大审查。
node scripts/scaffold_talking_head_hyperframes_project.mjs --project-dir /absolute/path/to/project [input flags]
node scripts/validate_inputs.mjs /absolute/path/to/project
node scripts/validate_fixed_stage.mjs /absolute/path/to/project生成后必须在项目内运行 npm run check:inputs 和 npm run check:fixed-stage；需要完整 HyperFrames 静态/运行门时运行 npm run check:template。任何调用 HyperFrames 的 package script 必须保持精确版本 0.7.65。
固定舞台的背景像素证明运行 npm run check:stage-parity。它在隔离副本里把节目时长扩展到 10 秒，只显示真实固定背景，在 0s、4s、9s 截图，先校验三张用户确认的窄中心光斑网格 golden 的 SHA-256，再按 yuv420p 计算 SSIM；任一时刻低于 0.995 即失败。这个命令对 TEMPLATE_ONLY 和 READY_FOR_EXECUTION 都可运行，不实现内容镜头。
挂载数字人时，npm run check:fixed-stage 还必须拒绝以下状态：媒体层不在 190×190px 固定区、人物裁切未写入 manifest、PIP 背景没有不透明底色、媒体层与圆框层级反转、视频未静音、或回退到未校准的 CSS 默认。技术检查通过仍不能替代视觉批准：动效前的全镜头静态联系表必须包含 PIP；正式发布前必须从实际编码文件抽取至少一个 PIP 区域，裁成 300×300px 并放大 3 倍，确认圆内无舞台网格穿透且人物满足安全区。
--force 是原子修复：已有项目与其中所有路径必须不是软链接；完整模板在同级临时目录中生成和校验后才替换原目录。无参数修复会从既有 manifest 的项目内锁定文件恢复输入、时长、PIP 和来源记录，不能把 READY 项目降级。任何后期碰撞或失败都必须保持原项目逐字节不变。
舞台证明与交接
舞台 proof 只证明固定层、空的透明内容 composition、字幕/PIP 安全关系与稳定根挂载；不得借 proof 实现或渲染内容镜头。
- 用户只要模板：交付项目路径、manifest、handoff、stage proof 和完整缺失清单后停止。
- 用户还要求继续制作且状态为
READY_FOR_EXECUTION：把同一项目交给hyperframes-scene-animator，由它实施下面的制作门禁。 - 状态为
TEMPLATE_ONLY：不得调用下游执行；明确列出阻塞项和修复方式。
下游制作门禁
路由下游时，明确交接并不得稀释以下约束：
- 主 Agent 保持唯一导演与集成所有权：它负责字幕分段、镜头规划、画面层级、文字与素材取舍、每个镜头具体怎么写、动效语义与最终审查。
- 方案锁定后，互不冲突的单镜头实现尽量委派给快速子 Agent；子 Agent 只按逐镜确定稿编码，不得重做导演、改文案、改镜头数量或改全局转场语言。
- 依据对齐字幕为全片划分镜头，先生成每个镜头“信息完全呈现时”的最终静态页，组成可连续审阅的联系表。
- 只有用户明确批准整套静态镜头后，下游才能写入进场、语义动效、转场、声音 cue 或整片预览。修改期间仍停留在静态阶段，不得用技术 proof 代替人的创意审核。
完成条件是固定舞台已证明，输入记录可审计，状态判断可复现，且没有任何内容场景、整片渲染或审片产物。
© bozhouDev, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 89 other files (scripts, references, assets) in skills/talking-head-hyperframes of bozhouDev/video-skills-toolkit.
- SKILL.md
- agents/openai.yaml
- assets/golden-backgrounds/narrow-center-grid-t000.png
- assets/golden-backgrounds/narrow-center-grid-t004.png
- assets/golden-backgrounds/narrow-center-grid-t009.png
- assets/hyperframes-project/.npmrc
- assets/hyperframes-project/DESIGN.md
- assets/hyperframes-project/assets/fonts/NotoSansSC-400.ttf
- assets/hyperframes-project/assets/fonts/NotoSansSC-500.ttf
- assets/hyperframes-project/assets/fonts/NotoSansSC-700.ttf
- assets/hyperframes-project/assets/fonts/SpaceGrotesk-400.ttf
- assets/hyperframes-project/caption-overrides.json
- assets/hyperframes-project/compositions/caption-overlay.html
- assets/hyperframes-project/compositions/content.html
- … and 76 more
Open the folder on GitHubat commit 4766a16
Compare with similar skills
Talking Head Hyperframes next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Talking Head Hyperframes this skillbozhouDev/video-skills-toolkit | 150 | — | ~927 | Automated safety check: Pass | MIT | |
| Ui2villli-studio/ui2v | 105 | 1 repos | ~1.5k | Automated safety check: Pass | GPL-3.0 | |
| Create VideoCuongyd196/auto-compare-video | 210 | — | ~2.8k | Automated safety check: Notes | Custom licence | |
| Session Story Filmheygen-com/hyperframes-community-skills | 178 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| HyperFrames Animationheygen-com/hyperframes | 59k | 3 repos | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| HyperFrames Video Entry Pointheygen-com/hyperframes | 59k | 3 repos | ~5.2k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Create Video
Cuongyd196/auto-compare-video
Tạo một video MỚI cho series "so sánh / phân biệt kiến thức" của repo này — clip dọc TikTok/Reels/Shorts 30-40s, layout 3-zone cố định theo DESIGN.md, voiceover tiếng Việt sinh bằng VieNeu TTS…
Session Story Film
heygen-com/hyperframes-community-skills
Turns one typical session between you and your agent into a short animated film built from your real messages, with a composed score, after you approve every line.
HyperFrames Animation
heygen-com/hyperframes
Collects motion rules, scene blueprints, transitions and runtime adapters for HyperFrames video compositions, with GSAP as the default animation runtime.
HyperFrames Video Entry Point
heygen-com/hyperframes
Entry point for making, editing and rendering videos from HTML compositions with HyperFrames, routing each request to the right workflow.
Remotion to HyperFrames Porter
heygen-com/hyperframes
Ports an existing Remotion (React) composition to HyperFrames HTML with GSAP, one way, and grades the result against a tiered set of reference fixtures.
More from bozhouDev/video-skills-toolkit
All 12 skills in this repoMedia To Transcript
bozhouDev/video-skills-toolkit
Convert audio/video URLs or local media into corrected Markdown transcripts through Volcengine recording-file ASR 2.0.
Audio To Subtitles
bozhouDev/video-skills-toolkit
Convert local audio/video files or public media URLs into subtitle files by uploading local files to Cloudflare R2 and calling Volcengine AI MediaKit ASR subtitles API.
Music
bozhouDev/video-skills-toolkit
Generate music using ElevenLabs Music API. An agent skill from bozhouDev/video-skills-toolkit.
Viral Video Benchmark
bozhouDev/video-skills-toolkit
判断、扫描、拆解并归档抖音视频、小红书图文或小红书视频。实时读取用户同平台粉丝数并划分主对标池/跨级灵感池，用已登录浏览器读取目标作品和作者主页公开指标，再用确定性代码判定普通、小爆、爆款、现象级并扫描作者近 20 条候选；只对用户选中的爆款和现象级先构建可追溯证据包，再调用子 Agent…
Douyin Cover
bozhouDev/video-skills-toolkit
生成抖音、视频号、小红书等短视频封面图、视频标题图和合集封面，也能诊断和改版已有封面。用户说做封面、生成封面、抖音封面、视频封面、标题图、合集封面、3:4、4:3、1:1、短视频首图、动态封面首帧、给这期视频做图、这封面为什么没人点、帮我改封面、封面点击率怎么提升、诊断封面时都应使用。小白学AI系列封面除外：遇到“小白学AI封面/小白学AI第N集封面”时优先使用…
Minimax Voice Director
bozhouDev/video-skills-toolkit
用 MiniMax 云端为视频制作可审批的声音导演稿，再生成、挑选和验收人声，最后以定稿音频产生字幕。用于用户明确选择 MiniMax 配音、继续已有 MiniMax 视频配音项目，或明确请求 MiniMax Voice ID/克隆/设计。泛指本地 TTS 或 IndexTTS 不使用本 skill；音乐、BGM、歌曲使用同级 music Skill。
Related
Categories
Questions about Talking Head Hyperframes
What does Talking Head Hyperframes do?
为 HyperFrames 口播或旁白项目创建、修复并验证固定舞台，锁定数字人 PIP 的区域、裁切、人物安全区和不透明背景，归档输入，生成 manifest 与 template handoff，并在就绪后按“字幕驱动的全镜头静态审核→动效”门禁路由到 hyperframes-scene-animator。适用于“新建 HyperFrames…. Talking Head Hyperframes is an agent skill from bozhouDev/video-skills-toolkit.
When should I use Talking Head Hyperframes?
Talking Head Hyperframes fits situations like: tasks that involve Motion graphics.
How do I install Talking Head Hyperframes in Claude Code?
Run `npx skills add bozhouDev/video-skills-toolkit --skill talking-head-hyperframes -a claude-code`. Or copy the skill folder (skills/talking-head-hyperframes in bozhouDev/video-skills-toolkit) into .claude/skills/talking-head-hyperframes in your project. Claude Code loads it when a task matches its description.
How do I install Talking Head Hyperframes in Codex?
Run `npx skills add bozhouDev/video-skills-toolkit --skill talking-head-hyperframes -a codex`. Or copy the skill folder (skills/talking-head-hyperframes in bozhouDev/video-skills-toolkit) into .agents/skills/talking-head-hyperframes in your project. Codex loads it when a task matches its description.
Can I use Talking Head Hyperframes in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add bozhouDev/video-skills-toolkit --skill talking-head-hyperframes -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/talking-head-hyperframes, .gemini/skills/talking-head-hyperframes, .github/skills/talking-head-hyperframes and .opencode/skills/talking-head-hyperframes in your project.
What does Talking Head Hyperframes need to run?
Going by SKILL.md and its folder, Talking Head Hyperframes needs the command-line tools its instructions call (npm and node).
Does Talking Head Hyperframes access the network?
SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Talking Head Hyperframes safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Talking Head Hyperframes use?
Talking Head Hyperframes is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Talking Head Hyperframes use?
About 927 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.9k tokens, read only when the agent opens those files.
What are the alternatives to Talking Head Hyperframes?
Skills that share tags, products or a category with Talking Head Hyperframes: Ui2v (illli-studio/ui2v, 105 stars), Create Video (Cuongyd196/auto-compare-video, 210 stars), Session Story Film (heygen-com/hyperframes-community-skills, 178 stars) and HyperFrames Animation (heygen-com/hyperframes, 59k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Talking Head Hyperframes?
bozhouDev (a GitHub user) maintains it in bozhouDev/video-skills-toolkit, which has 150 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on July 27, 2026.
Source: bozhouDev/video-skills-toolkit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.