- name
SKILL.md
Tệp skill vẫn nằm trong kho mã của nhà phát hành.
Dán lệnh đã sao chép vào terminal. Lệnh sẽ cài đặt tệp SKILL.md này vào agent đó.
npx skills add ZJU-REAL/Easel --skill clipify -a cursor -yDán lệnh đã sao chép vào terminal. Lệnh sẽ cài đặt tệp SKILL.md này vào agent đó.
npx skills add ZJU-REAL/Easel --skill clipify -a claude-code -yDán lệnh đã sao chép vào terminal. Lệnh sẽ cài đặt tệp SKILL.md này vào agent đó.
npx skills add ZJU-REAL/Easel --skill clipify -a codex -yDán lệnh đã sao chép vào terminal. Lệnh sẽ cài đặt tệp SKILL.md này vào agent đó.
npx skills add ZJU-REAL/Easel --skill clipify -a grok -yGửi tin nhắn đã sao chép trong cuộc trò chuyện Grok Bot. Bot sẽ lấy tệp SKILL.md này từ GitHub và thêm vào bộ skill mà mọi Bot của bạn dùng chung.
Install this skill: https://github.com/ZJU-REAL/Easel/tree/HEAD/skills/builtin/clipifyTừ nhà phát hành
Find the funniest moments in a video, cut them as standalone clips, optionally reformat 16:9 → 9:16 (face-pan or split-screen), and burn opus-style word-by-word captions.
whisper --model tiny.en --word_timestamps True --output_format json (≈10× faster than small.en; quality fine for English). For non-English: --model base (drop --language).-hwaccel auto, or omit it (macOS: videotoolbox; Linux: vaapi/cuda/none). Add -preset ultrafast for renders. Use -c:v libx264 -crf 20 for the final master.<skill-dir>/scripts/ (where <skill-dir> is the directory containing this SKILL.md — typically ~/.claude/skills/clipify/)
analyze.py — speaker timeline from two ROI motion filesbuild_pan.py — ffmpeg crop x-expression with hard cutsbuild_ass.py — opus-style ASS captions from whisper JSONaudio_align.py — find offset of a sub-clip in a longer sourceWorking dir: /tmp/clipify/ (mkdir at start, leave artifacts for debugging).
mkdir -p /tmp/clipify
ffmpeg -y -i "$VIDEO" -vn -ac 1 -ar 16000 /tmp/clipify/audio.wav
whisper /tmp/clipify/audio.wav --model tiny.en --word_timestamps True --output_format json --output_dir /tmp/clipify --language en
Read the resulting JSON (or .txt) and pick 3–5 candidate clips. Funny signals to scan for:
ffmpeg -af volumedetect or look for rapid back-and-forth (alternating short Whisper segments)For each candidate, propose: [start, end, why-it's-funny, suggested title]. Aim for 10–25s clips. Show the list and let the user confirm/pick.
ffmpeg -y -ss "$START" -t "$DURATION" -i "$VIDEO" -c copy /tmp/clipify/clip_$N.mp4
(Use -c copy for instant trim. Re-encode only if cuts must be frame-accurate.)
Ask the user (skip if they already specified): "9:16 (TikTok / Reels), 16:9 (YouTube), or 1:1 (Insta feed)?"
Detect source aspect with ffprobe. If source is 16:9 and target is 9:16, ask:
"Two options: (a) hard-cut pan that follows whoever is speaking (single face on screen at a time), or (b) split-screen stack with both faces visible. Which do you want?"
Skip the question if there's only one face (single-talker clip). For single-talker, just center-crop.
Locate the two face ROIs. Sample one frame: ffmpeg -ss <middle> -i <clip> -frames:v 1 /tmp/clipify/probe.jpg. Read it. Eyeball each face's mouth+chin area as x,y,w,h in the source's pixel space. (No cv2 needed — camera is static within a clip; one frame is enough.) Verify by drawing boxes:
ffmpeg -i probe.jpg -vf "drawbox=x=$LX:y=$LY:w=$LW:h=$LH:[email protected]:t=4,drawbox=x=$RX:y=$RY:w=$RW:h=$RH:[email protected]:t=4" verify.jpg
Iterate at most twice. Boxes should cover mouth + chin and avoid hands/mics. Don't over-tune — frame differencing is forgiving.
Extract per-frame motion energy in each ROI:
ffmpeg -y -i clip.mp4 -filter_complex "
[0:v]split=2[a][b];
[a]crop=$LW:$LH:$LX:$LY,format=gray,tblend=all_mode=difference,signalstats,metadata=mode=print:key=lavfi.signalstats.YAVG:file=/tmp/clipify/L.txt[la];
[b]crop=$RW:$RH:$RX:$RY,format=gray,tblend=all_mode=difference,signalstats,metadata=mode=print:key=lavfi.signalstats.YAVG:file=/tmp/clipify/R.txt[ra]
" -map "[la]" -f null - -map "[ra]" -f null -
Build speaker timeline (min dwell 1.0s — short interjections merge into the prior speaker):
python3 <skill-dir>/scripts/analyze.py /tmp/clipify/L.txt /tmp/clipify/R.txt 1.0 > /tmp/clipify/segments.json
Pick pan x-coordinates for a 9:16 vertical strip from the source. With source W=1920 and target W=1080, crop strip width = 608.
face_left_center_x - 304 (clamp ≥ 0)face_right_center_x - 304 (clamp ≤ source_W - 608)Generate the hard-cut x expression and render:
EXPR=$(python3 <skill-dir>/scripts/build_pan.py /tmp/clipify/segments.json $LEFT_X $RIGHT_X)
ffmpeg -y -i clip.mp4 -filter_complex \
"[0:v]crop=608:1080:x='$EXPR':y=0,scale=1080:1920:flags=lanczos[v]" \
-map "[v]" -map 0:a -c:v libx264 -preset fast -crf 20 -pix_fmt yuv420p \
-c:a aac -b:a 192k /tmp/clipify/clip_panned.mp4
Source 1920×1080 assumed; for 4K source either downscale first or double all coordinates.
Two stacked tiles, 1080×960 each. The active speaker's tile is on top — overlay flips at speaker changes.
[0:v]split=2[a0][a1];
[a0]crop=Wcrop:Hcrop:LX_tile:LY_tile,scale=1080:960,split=2[lt0][lt1];
[a1]crop=Wcrop:Hcrop:RX_tile:RY_tile,scale=1080:960,split=2[rt0][rt1];
[lt0][rt0]vstack[layoutL];
[rt1][lt1]vstack[layoutR];
[layoutL][layoutR]overlay=0:0:enable='<RIGHT_SPEAKER_ENABLE>'[v]
Build <RIGHT_SPEAKER_ENABLE> from segments.json as between(t,a,b)+between(t,a,b)+... over the right-speaker segments. Tile crops should target ~720×640 around each face (1.125:1 to match 1080×960).
Ask once (only if user hasn't already specified a style):
"Three subtitle styles: opus (big bold white, yellow active-word highlight), karaoke (4-word chunks, green highlight), minimal (clean Helvetica, no highlight). Or paste an example you like."
If they paste a reference image/example: match the font, size, weight, color, position, and animation as closely as possible — write a custom ASS by hand or extend build_ass.py.
Else use the preset:
# Re-run whisper on the trimmed clip for accurate timestamps relative to clip start
whisper /tmp/clipify/clip_panned.mp4 --model tiny.en --word_timestamps True --output_format json --output_dir /tmp/clipify --language en
python3 <skill-dir>/scripts/build_ass.py /tmp/clipify/clip_panned.json /tmp/clipify/captions.ass opus
Burn captions:
ffmpeg -y -i /tmp/clipify/clip_panned.mp4 -vf "subtitles=/tmp/clipify/captions.ass" \
-c:v libx264 -preset fast -crf 20 -c:a copy "$OUTPUT.mp4"
<source_dir>/clipify_out/ (mkdir if missing)xdg-open <path>, macOS open <path>) so the user can check itffmpeg -filter:v "select='gt(scene,0.3)',showinfo" -f null - to count cuts. If a 16:9→9:16 clip has many cuts, the fixed face ROIs only work for the dominant scene; warn the user, and offer to either pick a single-take clip or accept off-center framing during cuts.audio_align.py) and trim from there.>-
---name: clipifydescription: >----# skills/builtin/clipify/SKILL.mdCâu hỏi thường gặp
Tải skills/builtin/clipify/SKILL.md từ nhà phát hành, hoặc sao chép đường dẫn và mở kho mã. PlugMCP chỉ liệt kê skill và không lưu trữ tệp này.
Nhà phát hành duy trì nó tại https://github.com/ZJU-REAL/Easel.
Claude, Cursor, Codex và Grok Build có thể đọc tệp SKILL.md mà bạn thêm từ kho mã của nhà phát hành. Grok Bot cài đặt skill khi bạn gửi liên kết thư mục GitHub của skill trong cuộc trò chuyện.