Install
$ agentstack add skill-jianshuo-claude-skills-wjs-teaching-english ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
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/.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/ffprobeon PATH (Homebrew).- Python
volcengineSDK (declared in mirarequirements.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
- Get the word. A single English word (or short phrase). If the user gave
a sentence, pick the target word.
- 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_textis read aloud over the intro card — keep it to the word + a
short 中文 gloss (Volcano reads mixed English/中文 fine).
usageis one short line shown on the card (≤ ~20 chars renders best at
low resolutions).
- 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 , --out .
- Report the printed output path (
search-app/out/.m3u8) and the
clip count. The .m3u8 plus its sibling .intro.ts / .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/.m3u8, or serve theout/
folder over HTTP and open in any HLS player (Safari plays .m3u8 natively).
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: jianshuo
- Source: jianshuo/claude-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.