JosiahSiegel/viral-video-platform-algorithms
plugins/viral-video-master/skills/viral-video-platform-algorithms/SKILL.md
Deep understanding of TikTok, YouTube, Instagram, and Facebook algorithms for 2025-2026. PROACTIVELY activate for: (1) Algorithm optimization, (2) Platform-specific strategy, (3) Content distribution understanding, (4) Engagement signal optimization, (5) Cold start strategies, (6) Trending and discovery, (7) Hashtag and SEO strategy, (8) Posting time optimization, (9) Cross-platform differences. Provides: Algorithm signal breakdowns, platform comparisons, optimization strategies, posting schedules, hashtag strategies, and discovery mechanisms.
$ install --global
skillsauthnpx skillsauth add JosiahSiegel/claude-plugin-marketplace viral-video-platform-algorithmsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 26, 2026, 7:43 AM93.4s4 files scanned
SKILL.md
- name:
- viral-video-platform-algorithms
- description:
- |
- PROACTIVELY activate for:
- (1) Algorithm optimization, (2) Platform-specific strategy, (3) Content distribution understanding, (4) Engagement signal optimization, (5) Cold start strategies, (6) Trending and discovery, (7) Hashtag and SEO strategy, (8) Posting time optimization, (9) Cross-platform differences.
- Provides:
- Algorithm signal breakdowns, platform comparisons, optimization strategies, posting schedules, hashtag strategies, and discovery mechanisms.
CRITICAL GUIDELINES
Windows File Path Requirements
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 (/).
Platform Algorithms Deep Dive (2025-2026)
Complete guide to understanding and optimizing for TikTok, YouTube, Instagram, and Facebook algorithms.
Algorithm Fundamentals
How Social Algorithms Work
All major platforms use similar principles:
- Content Analysis: What is the video about?
- User Signals: How do viewers interact?
- Creator Signals: Creator history and behavior
- Distribution: Who should see this content?
- Feedback Loop: Performance adjusts distribution
Universal Algorithm Truths
Platforms Want:
- Users to stay on platform longer
- High engagement (interactions)
- Quality content that satisfies users
- Diverse content discovery
What Drives Distribution:
- Watch time (how long people watch)
- Engagement depth (comments > likes)
- Completion rates (especially for short-form)
- Sharing behavior
- Return visits
TikTok Algorithm (2025)
Algorithm Signals
| Signal | Weight | Description | |--------|--------|-------------| | Watch Time | Highest | Total seconds watched | | Completion Rate | Very High | % of video watched | | Replays | High | Video watched multiple times | | Shares | High | Direct shares to others | | Comments | Medium-High | Written engagement | | Follows | Medium | New followers from video | | Likes | Lower (2025) | Heart button taps |
2025 Update: Shallow interactions (likes) have reduced weight compared to deeper signals like watch time and replays.
TikTok's Cold Start System
How New Videos Are Tested:
- Video published
- Shown to 200-500 initial viewers
- Performance measured against benchmarks
- Strong performance = expanded distribution
- Weak performance = limited to followers
Cold Start Success Factors:
- First 3 seconds retention
- Completion rate vs video length
- Early engagement velocity
- Replay rate
TikTok Content Preferences
Algorithm Favors:
- Family-friendly content
- Positive emotional tone
- Educational value
- Authentic creator content
- Micro-niche targeting
- Trending sound usage
Algorithm Deprioritizes:
- Controversial/negative content
- Duplicated content
- Low-quality production
- Misleading thumbnails
- Watermarked content from other platforms
Micro-Niche Prioritization
2025 Algorithm Change: TikTok now heavily favors micro-niche over broad appeal.
Benefits:
- Specialized content sees 2.5x better distribution
- Algorithm micro-categorizes: "beginner leg workouts for women" vs just "fitness"
- Niche authority = more algorithm push for new content
Strategy:
- Define specific niche clearly
- Use niche-specific language and hashtags
- Build authority in one area before expanding
- Let algorithm understand your content category
TikTok For You Page (FYP)
How Videos Reach FYP:
- Initial Test: Small audience batch
- Performance Check: Engagement metrics evaluated
- Expanded Test: Larger audience if metrics strong
- FYP Placement: Continued performance = broader FYP reach
- Ongoing: Performance at each level determines next reach
FYP Success Factors:
- Hook in first 1.3 seconds
- High completion rate
- Strong replay rate
- Trending sound usage
- Relevant hashtags
TikTok Hashtag Strategy
| Hashtag Type | Purpose | Examples | |--------------|---------|----------| | Broad/Trending | Reach attempt | #fyp, #viral | | Category | Topic discovery | #fitness, #cooking | | Niche | Targeted audience | #beginneryoga, #airfryer | | Branded | Campaign tracking | #YourBrandChallenge |
Optimal Strategy:
- 3-5 hashtags per video
- Mix of niche and category
- Quality over quantity
- Trending hashtags increase engagement 23%
TikTok Posting Schedule
| Metric | Value | |--------|-------| | Recommended frequency | 1-4 times daily | | Views in first 24 hours | 68% | | Peak window improvement | 30% better results | | Growth with 2-4x daily | 2.5x higher follower growth |
YouTube Algorithm (2025)
Long-Form Algorithm Signals
| Signal | Weight | Description | |--------|--------|-------------| | Watch Time | Highest | Total minutes watched | | Audience Retention | Very High | % of video watched | | Click-Through Rate | Very High | Clicks / Impressions | | Session Time | High | Time viewer stays on YouTube | | Engagement | Medium | Likes, comments, shares | | Subscriber Actions | Medium | New subs, bell clicks |
YouTube Shorts Algorithm
| Signal | Weight | Description | |--------|--------|-------------| | Watch Time | Highest | Per-video and cumulative | | Completion Rate | Very High | Essential for short-form | | Engagement | High | All interaction types | | Swipe-Away Rate | High | Inverse signal (lower = better) |
Shorts + Long-Form Connection:
- Shorts help identify resonant audiences
- Algorithm recommends long-form to Shorts viewers
- Combined strategy = 41% faster channel growth
YouTube Discovery Mechanism
Where Videos Are Discovered:
| Source | Description | |--------|-------------| | Home Feed | Personalized recommendations | | Search | Keyword-based discovery | | Suggested | After/alongside other videos | | Browse Features | Trending, playlists | | Notifications | Subscriber alerts | | External | Google search, social shares |
YouTube SEO Signals
Ranking Factors:
| Factor | Importance | |--------|------------| | Watch time | Most important | | Click-through rate | Very important | | Engagement | Important | | Keywords (title, description) | Important | | Closed captions | 94% of top videos have them | | Video length | 8-9 minutes best for search |
SEO Statistics:
- 25%+ of Google searches include video snippets
- Videos can get 2-5x more views from Google ranking
- Top-ranking videos average 29 months in age
YouTube Posting Schedule
| Day | Best Time | Notes | |-----|-----------|-------| | Tuesday | 6-9 PM | Peak performance | | Wednesday | 6-9 PM | Peak performance | | All weekdays | 12-3 PM | Good secondary window | | Friday-Saturday | Afternoon | Broader engagement window |
YouTube Algorithm Optimization
Key Strategies:
-
Maximize Watch Time
- Front-load value
- Eliminate dead time
- Use pattern interrupts
-
Optimize CTR
- Test thumbnails (up to 3 variants)
- Compelling titles
- Curiosity without clickbait
-
Increase Session Time
- End screens with relevant videos
- Playlist optimization
- Content series
Instagram Algorithm (2025-2026)
Instagram Reels Algorithm
| Signal | Weight | Description | |--------|--------|-------------| | Topic Clarity | Very High | Clear content categorization | | Engagement | High | Saves, shares, comments, likes | | Watch Time | High | Duration viewed | | Follows from Reel | High | Audience growth signal | | Audio Usage | Medium | Trending audio preference |
December 2025 Algorithm Update
Key Change: Topic Clarity Emphasis
Instagram now prioritizes content that can be clearly categorized by topic.
Impact:
- Clear niche content gets better distribution
- Mixed-topic creators may see reduced reach
- Keyword optimization becoming more important
The 3/8/12 Rule
Instagram's content evaluation framework:
| Time | Checkpoint | Algorithm Action | |------|------------|------------------| | 3 seconds | Hook evaluation | Continue or abandon | | 8 seconds | Interest deepening | Engagement prediction | | 12+ seconds | Value delivery | Distribution decision |
Instagram Trial Reels
New Feature (2025): Test content without risking engagement metrics.
Benefits:
- Risk-free experimentation
- No negative impact on feed
- Learn what works before full publish
- Test hooks, formats, topics
Instagram Hashtag Evolution
2025 Shift: Instagram moving from hashtags to keyword-based SEO.
New Strategy:
- Focus on keywords in caption
- Reduce hashtag quantity (3-5 vs 30)
- Posts with at least one hashtag: 12.6% more engagement
- Think "what would someone search for?"
Instagram Posting Schedule
| Day | Best Time | Notes | |-----|-----------|-------| | Tuesday | 11 AM - 6 PM | Peak engagement | | Wednesday | 11 AM - 6 PM | Peak engagement | | Thursday | 11 AM - 6 PM | Peak engagement |
Best Practices:
- Consistency matters more than perfect timing
- 1-2 Reels daily recommended
- Test different times with your audience
Facebook Reels, Platform Comparison & Optimization Framework
Detailed Facebook Reels algorithm notes, cross-platform comparison matrix, algorithm optimization framework, and upcoming changes to watch live in references/facebook-comparison-optimization.md. Load that reference when comparing platform tradeoffs or adapting one asset across multiple algorithms.
Quick Reference
Algorithm Success Checklist
TikTok:
- [ ] Hook in 1.3 seconds
- [ ] Trending or appropriate sound
- [ ] 3-5 relevant hashtags
- [ ] Clear niche focus
- [ ] High completion potential
YouTube:
- [ ] Compelling thumbnail (test 3 variants)
- [ ] Keyword-optimized title/description
- [ ] Strong hook (5-10 seconds)
- [ ] Closed captions included
- [ ] End screens/cards configured
Instagram:
- [ ] Clear topic/niche
- [ ] 3/8/12 structure
- [ ] Keyword-rich caption
- [ ] 3-5 relevant hashtags
- [ ] Sound-off friendly (captions)
Facebook:
- [ ] Share-worthy content
- [ ] Conversation starters
- [ ] Vertical format (9:16)
- [ ] Weekend timing considered
- [ ] Native upload (not cross-posted link)
Related Skills
JosiahSiegel/ml-training
development
VerifiedTrustedCommunity
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.
38SKILL.mdUpdated May 28, 2026
JosiahSiegel/ml-mlops
development
VerifiedTrustedCommunity
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.
38SKILL.mdUpdated May 28, 2026
JosiahSiegel/ml-inference-optimization
development
VerifiedTrustedCommunity
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.
38SKILL.mdUpdated May 28, 2026
JosiahSiegel/ml-hyperparameter-tuning
testing
VerifiedTrustedCommunity
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.
38SKILL.mdUpdated May 28, 2026