wjs-teaching-english
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 card (word + IPA + 中文 gloss + usage, Volcano TTS) and appended with a 关注王建硕 CTA card. No MP4 burn. Triggers — "teach <word>", "讲讲 <word>", "学英语 <word>", "把 <word> 做成视频", "/wjs-teaching-english <word>".
git clone --depth 1 https://github.com/jianshuo/claude-skills /tmp/wjs-teaching-english && cp -r /tmp/wjs-teaching-english/wjs-teaching-english ~/.claude/skills/wjs-teaching-englishSKILL.md
# Teach an English word as a video supercut
Turn one English word into a self-contained HLS lesson:
```
intro.ts (word /IPA/ · 中文 gloss · usage + Volcano TTS)
⋯ EXT-X-DISCONTINUITY
[supercut] every season2 clip where the word is spoken (search-app /api/playlist, COS URLs)
⋯ EXT-X-DISCONTINUITY
cta.ts (关注王建硕 + Volcano TTS)
= search-app/out/<word>.m3u8
```
No MP4 is burned — only the two cards are rendered as tiny `.ts`, re-encoded to
match the supercut's codec so they play in any HLS player.
## Prerequisites (check once)
- `ffmpeg` / `ffprobe` on PATH (Homebrew).
- Python `volcengine` SDK (declared in mira `requirements.txt`, used for TTS):
`python3 -c "import volcengine"`. If missing, ask the user to allow
`pip3 install volcengine==1.0.58` (it's a pinned repo dependency).
- The deployed search-app at `https://search-app-three-kappa.vercel.app`
(default). Override with `SEARCH_APP_BASE=http://localhost:3000` if running
locally (needs Node ≥ 23.6 + `npm start`).
## Steps
1. **Get the word.** A single English word (or short phrase). If the user gave
a sentence, pick the target word.
2. **Write the mini-lesson JSON.** YOU (Claude) author it — no dictionary API.
Keep it accurate and concise. Save to a temp file, e.g. `/tmp/lesson.json`:
```json
{
"word": "love",
"ipa": "/lʌv/",
"pos": "v. / n.",
"gloss": "爱，热爱",
"usage": "下面是它在真实电影里的说法",
"tts_text": "love. 爱。"
}
```
- `tts_text` is read aloud over the intro card — keep it to the word + a
short 中文 gloss (Volcano reads mixed English/中文 fine).
- `usage` is one short line shown on the card (≤ ~20 chars renders best at
low resolutions).
3. **Build it:**
```bash
cd /Users/jianshuo/code/mira/search-app
python3 scripts/build_lesson.py --word love --lesson /tmp/lesson.json
```
Useful flags: `--speaker zh_female_qingxin` (default), `--limit 300` (max
clips), `--no-tts` (silent cards), `--base <url>`, `--out <dir>`.
4. **Report** the printed output path (`search-app/out/<word>.m3u8`) and the
clip count. The `.m3u8` plus its sibling `<word>.intro.ts` / `<word>.cta.ts`
are the deliverable; `out/` is git-ignored.
## Notes
- If the word has no clips, the script exits with "no clips match" and writes
nothing — tell the user and suggest a more common word.
- Intro/CTA are encoded to the FIRST supercut segment's resolution/codec/fps so
the first discontinuity needs no decoder re-init (avoids `bufferAppendError`).
- To play locally: `ffplay search-app/out/<word>.m3u8`, or serve the `out/`
folder over HTTP and open in any HLS player (Safari plays `.m3u8` natively).Repo-wide drift detector for the wjs-* Claude Code skills in this marketplace. Sweeps every SKILL.md, scores it against the repo's own conventions (V-ing naming, trigger-phrase density, companion files, description shape), and returns a grouped punch list ordered by severity. Read-only — never edits files. Use before pushing a batch of skill changes, or whenever you wonder "are these skills still internally consistent?
|
Use when the user asks to audit what's wrong with a project, "make it right", "看看项目出了什么问题", "为什么用户的需求还没上线", "为什么没提交App Store", "为什么没新build", or wants a holistic state-of-the-project check covering unmerged branches, stalled PRs, failed GitHub Actions, stale builds, plan drift (TODOS.md / ROADMAP), unreleased commits, and log errors. Runs read-only investigation, presents a grouped checklist, fixes only after explicit user confirmation. Aware of the Cathier iOS app workflow (Xcode + fastlane + auto-merge @claude PRs from in-app feedback).
Use when the user has a video + an SRT and wants the subtitles either burned into the pixels (libass, always-visible) or soft-muxed as a togglable track. Also handles the final composite step for the localization pipeline — burn subs, mix a dub track, and keep the original audio as a low-volume bed, all in ONE ffmpeg encode (no cascade). Verifies libass availability and auto-downloads a static evermeet ffmpeg build when Homebrew's stripped binary lacks it. Triggers — "烧字幕", "硬字幕", "burn subtitles", "burn-in subs", "embed subtitle", "soft mux SRT", "把字幕烧进视频", "做最终合成".
Use when the user complains about spam on his X/Twitter posts — 同城面付 / 寻固炮 / 线下上门 / 免费破处 这类引流号在他推文下刷的 emoji 垃圾回复 — and wants them removed. Covers the last 7 days (X recent-search window). Triggers — "把这些spam删掉", "清理X垃圾回复", "推文下面好多引流号", "clean spam replies", "/wjs-cleaning-spam".
Use when the user wants a 王建硕-style WeChat article (article.md) turned into a narrated short MP4 video — TTS voiceover via 火山引擎 Volcano TTS, HyperFrames CSS/GSAP animation per scene, subtle SFX, abstract watercolor background, full pipeline rendering to 1080×1920 portrait MP4 (30-90s). Triggers — "把这篇文章做成视频", "做一个解说视频", "讲解视频", "/wjs-converting-text-to-video".
Use when migrating a WordPress site to a Hugo static site on GitHub Pages from a WXR export (.xml) plus the wp-content/uploads folder — preserving /archives/<id>/ URLs, localizing images, and deploying via GitHub Actions. Triggers — "把 WordPress 迁成 Hugo", "wordpress 转静态站", "migrate WordPress to Hugo", "WXR to Hugo", "publish WordPress to GitHub Pages", "/wjs-converting-wp-to-hugo".
Use when the user has a video + a target-language SRT and wants the video to actually speak that language — generates a time-aligned TTS voice dub. Routes by voice ID — Volcano (豆包) TTS for Chinese, edge-tts neural for any language. Defaults to one voice (single-speaker); opt-in multi-speaker via visual diarization. Outputs `*_<lang>_dub.mp4` with the dub audio in place of the original. Final mixing (audio bed + burn-in) is handed off to `/wjs-burning-subtitles`. Triggers — "配音", "中文配音", "Chinese dub", "voice over this", "dub the video", "TTS this SRT", "different voice for each speaker".