Turn one English word into a self-contained HLS lesson:

把一句平淡的话,变成读者忍不住接话的一条推文。两件事叠在一起就行:**一个真事实**(可信、有料)+ **一个钩子**(留个缺口让人补)。

**VoiceDrop 的全部能力都在 MCP 里。这个 skill 唯一的作用，是把你接上去。**

Video + SRT → video with subtitles. Also the final-encode stage for the localization pipeline: takes a video, an optional dub track from `/wjs-dubbing-video`, and an optional SRT to burn, and produces the upload-ready MP4 in **one** ffmpeg pass. No cascade of decodes/re-encodes.

把一本书做成 **按章节的 YouTube 视频**：每一章用 VoiceDrop 读书的有声书 mp3 作为音轨，从章节内容提炼 **1-3 个中心思想**，为每个中心思想设计提示词、用 GPT Image 2 生成画面（Ken Burns 缓推 + 交叉淡化），中心思想以大字叠加在ç

Installs a self-driving feedback loop into any website repo. Runs entirely on the repo owner's own GitHub Actions, authenticated with their Pro/Max OAuth token or their own `ANTHROPIC_API_KEY` — no extra service or backend.

VoiceDrop 收件箱（`jianshuo.dev/files` 上的 `VoiceDrop-*.m4a`）→ 逐条转写 → 交给 `wjs-mining-articles` 出公众号草稿。这是 VoiceDrop iOS app（开口即录、停即上传）的 Mac 端闭环。

Post-production for a video clip: cover, captions, illustrations, CTA, custom motion graphics — all composed in ONE HyperFrames project and rendered in a SINGLE final encode. No cascade of decodes/re-encodes (each cascade pass degrades quality and burns time).

每天早上 4:00 自动跑一遍：挑一个 `wjs-*` skill → 生成今日推广角度 → 发到 X → 起草社区帖。**X 真发，社区只起草到 outbox/ 让人工 review。**

Take an iOS app that's already building to **TestFlight** and ship it to the **App Store**: prepare the **screenshots** + **description/metadata**, then use the existing **fastlane** to **submit for review**.

Hugo 博客的对话式后台。**我就是后台**——没有 CMS、没有 /admin 页面、没有 PAT、没有 Cloudflare。 你说要发什么，我按仓库约定改 `content/`、放图、commit、push，走仓库现有部署流自动上线。

Compute a single time offset for each multi-source recording of the same event using audio cross-correlation, and emit a `.sync.json` sidecar next to each original. **Originals are never modified, copied, or re-encoded.** Downstream tools use `-itsoffset` to apply the offset at consume time.

每天把最新一篇还没分发过的公众号文章，扇出（syndicate）到各社交平台。**一套文案走天下**，有 API 的真发，没 API 的备好待发件箱让你手动粘。

Spoken audio in → timestamped SRT in the same language out. **This skill stops at the source-language SRT.** Translation to another language is the next skill (`/wjs-translating-subtitles`).

Source-language SRT in → target-language (or bilingual) SRT out. **This skill is text-only.** Burn-in lives in `/wjs-burning-subtitles`; voice dub in `/wjs-dubbing-video`.

Push finished videos to YouTube. Defaults are tuned for this user's workflow (王建硕 channel, China network with local proxy, 1080p horizontal recordings from Riverside / multicam edits).

底座是 **huashu-art-motion**（Canvas 逐帧画的引擎、风格配方、qa/deliver 门禁）。本 skill 加三样：整本书的分章流水线、**画风套件**（kits/，选过的画风做成库，下一本直接复用）、**公用组件**（scripts/*.mjs 与 player/，每本书不再重å†

文字 → 有声书 mp3。不是照字面念，而是先**编排**：不同性质的内容换不同声音，关键转折处加语音指令，然后用火山引擎豆包 seed-tts-2.0 合成。