Short video production is the art and science of creating engaging 15-60 second vertical videos optimized specifically for Xiaohongshu's mobile-first, algorithm-driven platform. This skill encompasses the complete workflow from concept through filming, editing, and optimization—combining compelling storytelling, visual appeal, rapid pacing, and concise delivery to capture viewer attention within milliseconds and retain it through completion. The core principle: on mobile platforms with endless c
Fetches short-video-production from vivy-yi/xiaohongshu-skills and configures it for Cursor.
3
Select Cursor when prompted
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
◆ Which agents do you want to install to?
│
│ ── Universal (.agents/skills) ────────────────
│ · Cline · Codex · Goose · Windsurf
│ ●Cursor(selected)
│ · Cursor · Aider · Continue
4
Verify installation
Confirm successful installation by checking the skill directory location:
.cursor/skills/short-video-production
Restart Cursor to activate short-video-production. Access via /short-video-production in your agent's command palette.
⚠
Security Notice
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Short video production is the art and science of creating engaging 15-60 second vertical videos optimized specifically for Xiaohongshu's mobile-first, algorithm-driven platform. This skill encompasses the complete workflow from concept through filming, editing, and optimization—combining compelling storytelling, visual appeal, rapid pacing, and concise delivery to capture viewer attention within milliseconds and retain it through completion. The core principle: on mobile platforms with endless content competing for attention, you don't have luxury of slow builds—every second must earn the viewer's continued watching.
Key insight: Xiaohongshu's algorithm heavily weights video completion rate and watch time as signals of content quality. Well-produced short videos (15-60 seconds, vertical format, strong hooks) achieve 5-10x higher completion rates than unedited horizontal footage. The first 3 seconds determine 80% of a video's success—invest disproportionately in hooks, and make every frame earn its place through rapid pacing and clear value delivery.
When to Use
Use when:
Creating vertical video content for Xiaohongshu (primary format)
Filming vlogs, tutorials, reviews, or lifestyle content
Editing short-form vertical video (under 60 seconds)
Optimizing video for mobile-first consumption
Repurposing longer content into short clips
Creating product showcases or demonstrations
Building personal brand through video storytelling
Producing behind-the-scenes or day-in-the-life content
Making educational or how-to video content
Do NOT use when:
Creating static image posts (use photo-editing or graphic-layout instead)
Editing feature-length video or documentary content (use professional video editing software)
Production requires cinematic quality beyond smartphone capability
Content is fundamentally audio-first and doesn't benefit from visuals (podcast-style content)
Creating live streaming content (different production considerations)
Platform requires horizontal format (certain cinematic content for other platforms)
Core Pattern
Before (unoptimized, boring video):
❌ "3+ minutes long, viewers scroll away"
❌ "Horizontal format, black bars on mobile"
❌ "Poor audio, can't hear clearly"
❌ "No clear structure, rambles"
❌ "Boring 15-second intro, lost viewers"
❌ "Weak or missing call-to-action"
❌ "Raw footage, no editing"
After (engaging, optimized short video):
✅ "15-60 seconds, respects viewer time"
✅ "Vertical 9:16 format, mobile-native"
✅ "Clear audio, professional quality"
✅ "Hook-value-CTA structure, purposeful"
✅ "Captivating first 3 seconds, immediate hook"
✅ "Clear CTA, tells viewer what to do"
✅ "Polished editing, dynamic pacing"
6 Essential Short Video Elements:
Element
Purpose
Impact
Priority
Hook (0-3s)
Grab attention immediately
Critical
#1 - determines 80% of success
Value Delivery (3-45s)
Deliver on hook's promise
Critical
#2 - must earn continued watching
Pacing
Maintain engagement through speed
High
#3 - dynamic, fast cuts
Visual Quality
Professional, credible appearance
High
#4 - lighting, framing, stability
Audio Quality
Clear, pleasant sound experience
High
#5 - poor audio = video failure
Call-to-Action
Guide viewer to next step
Medium-High
#6 - engagement and conversion
Quick Reference
Video Type Comparison for Xiaohongshu:
Video Type
Optimal Length
Structure
Production
Engagement
Best For
Tutorial (教程)
45-60s
Hook → Problem → Steps → Result
Medium
Very High
Educational value
Review (测评)
30-45s
Hook → First impressions → Features → Verdict
Medium
High
Product content
Vlog (日常)
30-60s
Scene → Action → Reaction → Reflection
Low-Medium
Medium
Authenticity, lifestyle
Tips List (干货)
15-30s
Hook → Tip 1, 2, 3 → CTA
Low
Very High
Quick value delivery
Before-After (对比)
15-30s
Before → Process → After reveal
Low-Medium
Very High
Transformations
Storytelling (故事)
45-60s
Hook → Conflict → Journey → Resolution
High
High
Emotional connection
Challenge (挑战)
30-45s
Intro → Attempt → Result → Reaction
Medium
High
Entertainment, relatability
Quick Tip (秒懂)
7-15s
Hook → One tip → CTA
Very Low
High
Ultra-brief value
Video Format Specifications:
Specification
Recommended
Acceptable
Avoid
Aspect Ratio
9:16 (vertical)
1:1 (square)
16:9 (horizontal)
Resolution
1080×1920 (Full HD)
720×1280 (HD)
Below 720p
Frame Rate
30fps
24fps, 60fps
Below 24fps
File Size
Under 500MB
Under 1GB
Over 1GB
Length
15-60s
Up to 3 min (rare)
Over 3 min
Format
MP4, MOV
-
AVI, MKV (unsupported)
Equipment by Production Quality:
Quality Level
Camera
Audio
Lighting
Stabilization
Budget
Basic
Smartphone (built-in)
Phone mic
Natural light
Handheld careful
¥0
Improved
Smartphone + app
Lavalier mic (¥50)
Ring light (¥100)
Mini tripod (¥50)
¥200
Advanced
Smartphone + lens kit
Wireless mic (¥300)
Softbox + ring light
Gimbal stabilizer (¥500)
¥1,000
Professional
Mirrorless camera
Shotgun mic + recorder
3-point lighting
Professional rig
¥10,000+
Implementation
Step 1: Plan Video Structure and Concept
Great videos start with intentional planning, not random filming.
Define Your Video Type (from Quick Reference table above):
Tutorial: Teaching a skill or process
Review: Evaluating a product or service
Vlog: Documenting daily life or experience
Tips List: Delivering multiple quick tips
Before-After: Showing transformation
Storytelling: Narrative arc with emotion
Challenge: Attempting something difficult
Quick Tip: Ultra-brief single-value delivery
Structure Formula by Length:
15-Second Videos (ultra-fast):
0-2s: Hook (grab attention immediately)
2-13s: Single value point (one tip, one reveal, one moment)
13-15s: CTA (follow, like, save)
30-Second Videos (standard):
0-3s: Hook (setup, promise, curiosity)
3-25s: Main content (2-3 key points, examples)
25-30s: CTA + preview (what's next, why follow)
60-Second Videos (maximum):
0-3s: Hook (strongest opener)
3-50s: Main content (3-5 points, demonstration, examples)
50-55s: Summary or key takeaway
55-60s: CTA (specific action)
Pre-Filming Checklist:
Video type and structure defined
Hook concept finalized (first 3 seconds scripted)
Key points outlined (3-5 max)
Location and lighting scouted
Props and materials ready
Battery charged, storage available
Practice run-through (optional but recommended)
Step 2: Film High-Quality Vertical Footage
Good footage makes editing easy; bad footage can't be fully fixed.
Camera Settings for Smartphone:
Setting
Recommended
Why
Resolution
4K (downscale to 1080p in edit)
Future-proofing, editing flexibility
Frame Rate
30fps
Standard for social media, smooth motion
Grid
On (rule of thirds)
Composition guide
HDR
Off (can cause editing issues)
Consistent exposure
Stabilization
On (but use gimbal when possible)
Reduce shake
Framing and Composition:
Vertical Framing Rules:
Subject placement: Center or rule-of-thirds intersection
Headroom: Leave 10-15% space above head (not too much, not too little)
Eye level: Camera at subject's eye level (most flattering)
Close-ups: Chest up for talking head, closer for detail shots
Variety: Mix close-ups, medium shots, and wide shots for dynamic editing
Lighting Fundamentals:
Lighting Type
Quality
Best For
Setup
Natural (window)
Soft, flattering
Talking head, beauty
Face near window, not direct sun
Ring light
Even, circular catchlights
Product, tutorials
Ring light centered on face/product
Softbox
Professional, diffused
Any content
Softbox 45° angle to subject
Natural (outdoor)
Varied by weather
Vlog, lifestyle
Golden hour (sunrise/sunset) best
Lighting Setup Tips:
Avoid: Backlighting (subject becomes silhouette)
Avoid: Harsh overhead light (unflattering shadows under eyes)
Preferred: Light source in front of subject (illuminates face)
Test: Record 5-second test, check lighting before full shoot
Audio Recording Best Practices:
Microphone Selection:
Built-in phone mic: Acceptable for quiet indoor settings, worst choice
Lavalier (clip-on): Best for voice clarity, consistent distance (¥50-300)
Wireless mic: Freedom of movement, professional quality (¥300-800)
Continuous improvement through data-driven optimization.
Key Metrics to Track:
Metric
How to Measure
What It Indicates
Views
Total impressions
Reach + algorithm boost
Completion Rate
Finished / Started × 100%
Content engagement quality
3-
Implementation Guide
Prerequisites
›Claude Desktop or compatible AI client with skill support
›Clear understanding of task or problem to solve
›Willingness to iterate and refine outputs
Time Estimate
15-45 minutes depending on use case complexity
Steps
1Install skill using provided installation command
2Test with simple use case relevant to your work
3Evaluate output quality and relevance
4Iterate on prompts to improve results
5Integrate into regular workflow if valuable
Common Pitfalls
⚠Expecting perfect results without iteration
⚠Not providing enough context in prompts
⚠Using skill for tasks outside its intended scope
⚠Accepting outputs without review and validation
Best Practices
✓ Do
+Start with clear, specific prompts
+Provide relevant context and constraints
+Review and refine all outputs before using
+Iterate to improve output quality
+Document successful prompt patterns
✗ Don't
−Don't use without understanding skill limitations
−Don't skip validation of outputs
−Don't share sensitive information in prompts
−Don't expect skill to replace human judgment
💡 Pro Tips
★Be specific about desired format and style
★Ask for multiple options to choose from
★Request explanations to understand reasoning
★Combine AI efficiency with human expertise
When to Use This
✓ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
Learning Path
1Familiarize yourself with skill capabilities and limitations
2Start with low-risk, non-critical tasks
3Progress to more complex and valuable use cases
4Build expertise through regular use and experimentation
