plugins/viral-video-master/skills/viral-video-short-form/SKILL.md
Complete short-form video optimization for TikTok, Instagram Reels, YouTube Shorts, and Facebook Reels. PROACTIVELY activate for: (1) TikTok content strategy, (2) Instagram Reels optimization, (3) YouTube Shorts creation, (4) Facebook Reels strategy, (5) Short-form hook creation, (6) Vertical video best practices, (7) Trending audio selection, (8) Loop optimization, (9) Quick engagement tactics. Provides: Platform-specific length recommendations, algorithm insights, hook formulas, trending strategies, caption techniques, hashtag optimization, and posting schedules.
npx skillsauth add JosiahSiegel/claude-plugin-marketplace viral-video-short-formInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
MANDATORY: Always Use Backslashes on Windows for File Paths
When using Edit or Write tools on Windows, you MUST use backslashes (\) in file paths, NOT forward slashes (/).
Complete guide to creating viral short-form content across TikTok, Instagram Reels, YouTube Shorts, and Facebook Reels.
| Platform | Optimal Length | Peak Performance | Max Length | |----------|---------------|------------------|------------| | TikTok | 15-60 seconds | 15-30 seconds | 10 minutes | | YouTube Shorts | 50-60 seconds | 55 seconds (3x views) | 3 minutes | | Instagram Reels | 7-30 seconds | 30-90 seconds | 90 seconds | | Facebook Reels | 15-30 seconds | 15-30 seconds | 90 seconds |
| Platform | Aspect Ratio | Resolution | File Format | |----------|-------------|------------|-------------| | TikTok | 9:16 | 1080x1920 | MP4, MOV | | YouTube Shorts | 9:16 | 1080x1920 | MP4 | | Instagram Reels | 9:16 | 1080x1920 | MP4, MOV | | Facebook Reels | 9:16 | 1080x1920 | MP4 |
In 2025, attention spans have shortened to the point where you have just 1.3 seconds to stop the scroll and capture attention.
First 1.3 seconds: Scroll stop moment
|
v
First 3 seconds: 65% will watch 10+ seconds
|
v
First 3 seconds: 45% will watch 30+ seconds
|
v
Complete video: Algorithmic boost
|
v
Replay: Maximum algorithmic favor
Second 1: Visual/Audio Grab
Second 2: Value Proposition
Second 3: Curiosity Gap
| Hook Type | Example | Best For | |-----------|---------|----------| | Curiosity | "Here's what no one tells you about..." | Educational | | Controversy | "[Popular belief] is completely wrong" | Thought leadership | | Story | "I was about to give up when..." | Personal brand | | Result | [Show end result first] | Tutorials | | FOMO | "Before this gets removed..." | Time-sensitive | | Self-ID | "POV: You're someone who..." | Niche targeting |
Primary Signals:
Cold Start Testing:
Content Strategy:
Technical Optimization:
Engagement Tactics:
| Type | Examples | Purpose | |------|----------|---------| | Broad | #fyp, #foryou, #viral | Reach (debated effectiveness) | | Category | #fitness, #cooking, #tech | Topical discovery | | Niche | #beginneryoga, #airfryer | Targeted audience | | Trending | [Check Creative Center] | Ride trend waves |
Optimal: 3-5 relevant hashtags mixing niche and category
Key Signals:
Unique Advantage:
Content Strategy:
Technical Optimization:
Monetization:
| CTA Type | Placement | Impact | |----------|-----------|--------| | Verbal | Last 3 seconds | Highest conversion | | Text overlay | Throughout | Reinforcement | | End screen | Final frame | Action driver | | Pinned comment | After posting | Extended engagement |
Key Signals:
Algorithm Preference:
The 3/8/12 Rule:
Content Strategy:
Technical Optimization:
Structure:
Keyword Strategy:
Key Signals:
Content Strategy:
Technical Optimization:
Timing Critical:
| Platform | Method | |----------|--------| | TikTok | Creative Center, upward arrow indicator on sounds | | Instagram | Built-in leaderboard, trending section in audio library | | YouTube | YouTube Music trending, observation in Shorts feed |
Timing:
Selection:
Execution:
TikTok engagement weights: | Action | Weight | |--------|--------| | Likes | 1 | | Comments | 2 | | Shares | 3 | | Complete plays | 4 | | Replays | 5 |
Technical Requirements:
Content Strategies:
| Metric | Improvement | |--------|-------------| | Watch likelihood | 80% higher | | Engagement | 40% increase | | Watch time | 10% improvement | | Retention | 27% higher |
Visual Styles:
Technical Best Practices:
| Platform | Note | |----------|------| | TikTok | Algorithm reads caption text for categorization | | Instagram | 50% watch without sound (per Mosseri) | | YouTube | Closed captions improve SEO | | Facebook | Auto-captions available but manual is better |
TikTok:
Instagram:
Facebook Reels:
YouTube Shorts:
Consistency Beats Perfection:
Batch Content:
development
This skill should be used when the user asks to train, debug, scale, or improve ML models. PROACTIVELY activate for: (1) PyTorch, TensorFlow/Keras, JAX, Flax, Hugging Face Trainer/Accelerate training loops, (2) distributed training, DDP/FSDP/DeepSpeed, TPU/GPU setup, (3) mixed precision AMP/bf16, gradient accumulation, checkpointing, seeding, (4) overfitting, imbalance, loss functions, regularization, LR schedules, warmup, (5) memory optimization, gradient checkpointing, offloading, quantization-aware training. Provides: reproducible training best practices across deep learning and classical ML.
development
This skill should be used when the user asks to productionize, track, version, govern, monitor, or automate ML systems. PROACTIVELY activate for: (1) MLflow, Weights & Biases, Neptune, Comet, ClearML experiment tracking, (2) model registry, model versioning, artifact lineage, reproducibility, (3) Kubeflow, SageMaker Pipelines, Vertex AI Pipelines, Azure ML pipelines, Databricks workflows, (4) CI/CD, continuous training/evaluation, A/B tests, canary/shadow deployments, (5) drift detection, model monitoring, data validation, responsible AI governance. Provides: end-to-end MLOps architecture and operational safeguards.
development
This skill should be used when the user asks to optimize, export, serve, compress, or accelerate ML inference. PROACTIVELY activate for: (1) latency, throughput, p95/p99, batching, concurrency, KV cache, memory, or cost issues, (2) quantization INT8/INT4, GPTQ, AWQ, bitsandbytes, pruning, sparsity, distillation, (3) ONNX export, ONNX Runtime, TensorRT, TorchScript, torch.compile, XLA, OpenVINO, Core ML, TFLite, (4) Triton, TorchServe, TF Serving, BentoML, Seldon, KServe configuration, (5) edge deployment, CPU/GPU/TPU/Inferentia serving. Provides: hardware-aware inference optimization and safe benchmarking.
testing
This skill should be used when the user asks to tune hyperparameters, run sweeps, optimize search spaces, or use AutoML. PROACTIVELY activate for: (1) Optuna, Ray Tune, FLAML, AutoGluon, Hyperopt, Nevergrad, KerasTuner, W&B sweeps, (2) grid search, random search, Bayesian optimization, TPE, Gaussian processes, evolutionary search, (3) ASHA, Hyperband, successive halving, multi-fidelity optimization, population-based training, (4) learning-rate finder, batch-size search, early stopping, pruning, (5) reproducible sweep design and experiment analysis. Provides: budget-aware hyperparameter search strategy.