A conversational backend for a Hugo static blog, a site generated from content files rather than managed through a traditional publishing dashboard. It edits posts, categories, images, and related files, then commits and pushes the changes so the repository's deployment process can publish them.
A release workflow for iOS apps that uses fastlane and GitHub Actions to build and upload a new version to TestFlight when code is pushed to the main branch. TestFlight is Apple's service for distributing beta builds to testers before App Store release.
A workflow for writing or lightly editing articles for a WeChat public account, with optional title images and explanatory illustrations. It follows a separate style file and can convert the article and upload it as a draft.
Use when the user wants to convert a video between horizontal and vertical orientations while preserving the inverted aspect ratio (16:9 ↔ 9:16, 4:3 ↔ 3:4, 21:9 ↔ 9:21). The skill crops a narrow band from the source and tracks the active speaker — the person whose mouth is moving — via MediaPipe face landmarks and…
Use when the user has a long-form video (interview / lecture / podcast / conversation) and a transcript SRT, and wants to extract 3–6 stand-alone topical short clips from it. This skill ONLY cuts and crops — it produces raw clips + per-clip SRTs as a hand-off package for downstream post-production…
Use when the user has 2+ video / audio recordings of the same event captured by different devices (cameras, phones, separate audio recorders) and wants them aligned to a single common timeline. Outputs only a lightweight .sync.json sidecar per input — original files are never re-encoded. Triggers — "多机位同步", "对齐这几个机位"…
Use when the user wants to auto-syndicate their latest 微信公众号 article across social platforms — picks the newest un-syndicated article, extracts one core copy, auto-posts to API platforms (X / Bluesky / Threads / LinkedIn) and prepares a copy-paste outbox for manual platforms (Facebook / 小红书 / 即刻 / 知乎). Triggers …
Use when the user wants to teach / learn an English word as a video — turn a single English word into a self-contained HLS "supercut" lesson built from the mira video base. Stitches every season2 clip where the word is spoken (via the search-app API) into one .m3u8, prepended with a Claude-written bilingual word-intro…
Use when the user has audio or video and wants a timestamped transcript (SRT) in the source language. Routes by source language — Chinese defaults to Volcano (豆包) ASR; other languages (Spanish, English, Portuguese, French, Italian, Japanese, Korean, etc.) use OpenAI Whisper API with word-level timestamps and…
Use when the user has an SRT (or transcript text) in one language and wants it translated to another, with punctuation-bounded re-segmentation so cues end at real sentence breaks. Simplified Chinese (zh-CN) and English (en) are first-class targets; other targets follow the same rules. Outputs a target-language SRT or…
Use when the user wants to post a daily X/Twitter tweet inspired by one of their recently-published 微信公众号 articles. Picks the newest article that hasn't been tweeted yet, drafts 3 tweet candidates from it (different angles — quote / metaphor / one-liner), posts the chosen one via xurl, records to history. Triggers …
Upload one or many videos to YouTube. Use when the user wants to "上传到 YouTube", "发 YouTube", "批量上传", "upload to YouTube", "post videos to YouTube", or to publish a finished final/ directory of MP4s. Reads per-video metadata (title / description / tags) from a sibling UPLOADMETA.md file when present (the user's…
Use when 王建硕 wants to decide whether a VoiceDrop article should get an AI 题图 (公众号封面), and which style of image prompt to use — before generating any cover. Triggers — "这篇要不要配题图", "选个题图风格", "给这篇出个题图 prompt", "choosing cover", "/wjs-voicedrop-choosing-cover".
Use when a newly mined VoiceDrop article needs automated post-processing — invoked headless by the 5-minute poller (launchd com.jianshuo.voicedrop-postprocess) with the article stem as argument. Triggers — "/wjs-voicedrop-post-processing ".
Use when the user wants text turned into an audiobook / read aloud — they give a passage, a file, a URL, or a VoiceDrop article and want an mp3 narration with expressive voices. Triggers — "做成有声书", "朗读出来", "读给我听", "念出来", "read aloud", "/wjs-voicedrop-reading-aloud".
Use when 王建硕 wants to systematically improve his X (Twitter) content by iterating on the content-generation prompt (prompts/x/prompt.md, used by the every-6h tweet Action) and finding which prompt version produces the highest-reach tweets. Each prompt edit is a git-SHA-versioned, numbered experiment with a hypothesis…
Use when 王建硕 wants to systematically grow his X (Twitter) followers by running numbered, A/B-testable growth experiments and tracking which ones actually work. Every action gets a number, a hypothesis, a target metric, a before-state (for rollback), and a verdict. The North-Star metric is the new-follower ÷…