视觉从代码生长的技术讲解视频工厂:给一个主题,产出一条"图解动画 + AI 配音"的 MP4: , 结构图/矩阵/连线拓扑/图表/数字滚动全部用 Remotion + React/SVG 代码精确绘制(不用 AI 视频模型,杜绝公式乱码与连线漂移,可参数化、改数据自动重排),旁白由 TTS 逐段生成 + ffprobe 实测时长(默认 edge-tts 神经音色;`--engine clone` 支持自定义克隆音色服务,上传参考音频即可用真人音色配音,人声更真实),build-timeline.mjs 按实测时长自动重建时间线(场景 = max(视觉最短, 配音+40帧尾巴),画面永远跟着配音走、绝不被切断),三层音频混音(配音 + 可开关 BGM + 音效钉帧表),确定性渲染(禁随机数/当前时间),双版本交付(带 BGM + 无 BGM 供后期自配乐 + 逐句 SRT)。Use whenever the user wants 技术讲解视频、图解动画视频、科普/架构动画 + AI 配音、克隆声音/克隆音色做视频配音、矩阵/连线/图表动画视频、"给我一个主题做个会动的技术动画"、Remotion 视频、或强调"画面要精确/可改/文字不能乱码"的程序化视频, 视觉主体是代码绘制的矢量图解(非实拍、非数字人、非产品界面复刻)时选本 skill。
- Stars
- 289
- Version
- v1
- Copies
- 0
Overview
Waxell's checks found 7 findings to review, highest severity high.
- Highest severity
- high
- Findings
- 7
- What ran
- Static analysis
A clean result means nothing alarming in what is published, not a guarantee. How the checks work
We don't republish the skill's instructions. Read them on GitHub at the reviewed commit.
Security
Security scan
Checked 2 days ago
Result
Review findings Waxell's checks found 7 findings to review, highest severity high.
Checked with static analysis: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. Nothing was run. How the checks work
Findings (7)
high · 3
- high
Tells Claude to install unpinned packages (requests)
references/workflow.md:69 · skill_risk:S2
- high
Tells Claude to install unpinned packages (edge-tts)
scripts/check-env.mjs:62 · skill_risk:S2
- high
Tells Claude to install unpinned packages (requests)
scripts/tts.py:245 · skill_risk:S2
medium · 4
- medium
assets/template-project/public/bgm/bgm.mp3: not scanned (a file type Waxell can't inspect)
assets/template-project/public/bgm/bgm.mp3 · binary_risk:B5
- medium
assets/template-project/public/vo/scene1.mp3: not scanned (a file type Waxell can't inspect)
assets/template-project/public/vo/scene1.mp3 · binary_risk:B5
- medium
assets/template-project/public/vo/scene2.mp3: not scanned (a file type Waxell can't inspect)
assets/template-project/public/vo/scene2.mp3 · binary_risk:B5
- medium
assets/template-project/public/vo/scene3.mp3: not scanned (a file type Waxell can't inspect)
assets/template-project/public/vo/scene3.mp3 · binary_risk:B5
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
One version so far: v1, seen 2026-11-03.
See and control which skills your people use
Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.
30 minutes. No commitment.
SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF
More images, video & audio skills and plugins
env-setupwwwzhouhuiChecking and provisioning the machine's environment for the video-agent-kit plugin, probing for ffmpeg/ffprobe that actually carry the… Review findingsImages, video & audioAI & agents289
voice-to-videowwwzhouhui口播文字稿一键成片:TTS 配音(edge-tts,带逐句/逐词时间戳)→ HTML 动画合成(场景由时间戳驱动,画面跟着声音走)→ Playwright 逐帧确定性渲染合成 MP4。Use whenever the user wants to… Review findingsImages, video & audio289
felo-youtube-subtitlingfelo-incFetch YouTube video subtitles/captions using Felo YouTube Subtitling API. Use when users ask to get YouTube subtitles, extract captions… Review findingsImages, video & audioEngineering251
skywork-music-makerskyworkaiCreate professional music with Mureka AI API: songs, instrumentals, and lyrics from natural language descriptions in any language. Use… Review findingsImages, video & audioEngineering207