Vibha-Ramprakash/claude-video-effects
effects
VerifiedAdd any of 51 video effects to a talking-head video (orbit, spotlight, glass widgets, timeline, checklist, headline wall, comment box, phone fan, liquid glass graph, match-cut, iPhone toggles, LED sign, over-the-shoulder zoom, iMessage pop-ups, place-in-grid and more). Effects track the speaker's face and can sit behind their head. Use when the user types /effects, names one of the effects, or asks to add an effect, zoom, grade, sticker or animation to their video.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 11.2 KB |
| assets/preview.jpg | binary | 541.4 KB |
| scripts/fx.pyexecutable | script | 150.1 KB |
| scripts/setup.shexecutable | script | 1.1 KB |
| scripts/words.pyexecutable | script | 1.5 KB |
scripts/words.py
View on GitHub#!/usr/bin/env python3
"""Find when each word is said, so effects can land on the right word.
usage: python words.py input.mp4 -> prints "12.34 word" lines and saves input.words.json
Uses faster-whisper (installed into the skill's .venv on first run). On a Mac with mlx-whisper installed, that is used instead.
"""
import json, os, subprocess, sys
src = sys.argv[1]
out = os.path.splitext(src)[0] + '.words.json'
words = []
try:
import mlx_whisper
r = mlx_whisper.transcribe(src, path_or_hf_repo='mlx-community/whisper-large-v3-turbo', word_timestamps=True)
words = [{'w': w['word'].strip(), 's': round(w['start'], 2), 'e': round(w['end'], 2)} for seg in r['segments'] for w in seg.get('words', [])]
except ImportError:
try:
from faster_whisper import WhisperModel
except ImportError:
print('Installing the transcriber (one time, about 1 minute)...', flush=True)
subprocess.run([sys.executable, '-m', 'pip', 'install', '-q', 'faster-whisper'], check=True)
from faster_whisper import WhisperModel
model = WhisperModel(os.environ.get('WHISPER_MODEL', 'base'), device='cpu', compute_type='int8')
segs, _ = model.transcribe(src, word_timestamps=True, vad_filter=True)
words = [{'w': w.word.strip(), 's': round(w.start, 2), 'e': round(w.end, 2)} for s in segs for w in (s.words or [])]
json.dump(words, open(out, 'w'), indent=0)
for w in words: print(f"{w['s']:7.2f} {w['w']}")
print(f'\nSaved {len(words)} words to {out}')
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |