anime-action-scene
Skill2 starsChanged 53 days agoApache-2.0View on GitHub
Generate high-intensity anime action sequences with key frame impact and dynamic camera work
In this repository74 other files it gives its agents.
- card-gameSkill
- pixel-art-spriteSkill
- rhythm-gameSkill
- side-scrollerSkill
- visual-novelSkill
- boss-modelSkill
- character-modelSkill
- environment-sceneSkill
- vfx-effectSkill
- weapon-propSkill
- worldview-3d-asset-production-routeSkill
- film-action-combatSkill
- film-character-sheetSkill
- film-dialogue-voiceoverSkill
- film-directionSkill
- film-end-creditsSkill
- film-generate-reviewSkill
- film-locationSkill
- film-pipelineSkill
- film-prop-sheetSkill
- film-screen-captureSkill
- film-scriptSkill
- film-shot-promptSkill
- film-storySkill
- film-style-librarySkill
- cinematic-filmSkill
- game-cutscene-generatorSkill
- product-demoSkill
- social-media-videoSkill
- worldview-gameplay-experience-studySkill
- worldview-gameplay-video-analysisSkill
- boss-battleSkill
- hero-skill-systemSkill
- horror-chaseSkill
- narrative-choiceSkill
- platformer-levelSkill
- puzzle-mechanicSkill
- roguelike-generatorSkill
- worldview-game-asymmetric-information-cooperationSkill
- worldview-game-barricade-delay-and-route-choiceSkill
- worldview-game-character-handoff-and-shared-evidenceSkill
- worldview-game-chase-route-architectureSkill
- worldview-game-death-loop-persistent-cluesSkill
- worldview-game-driving-horror-divided-attentionSkill
- worldview-game-evidence-based-entity-identificationSkill
- worldview-game-horror-experience-rhythmSkill
- worldview-game-horror-mundane-routine-corruptionSkill
- worldview-game-horror-procedural-duty-and-incidentSkill
- worldview-game-horror-returning-place-escalationSkill
- worldview-game-horror-role-and-identity-pressureSkill
- worldview-game-key-item-backtrackingSkill
- worldview-game-limited-save-riskSkill
- worldview-game-lure-hide-escapeSkill
- worldview-game-observation-gated-stalkerSkill
- worldview-game-perception-distortion-and-trustSkill
- worldview-game-relief-resource-with-hidden-costSkill
- worldview-game-restore-power-under-pressureSkill
- worldview-game-roaming-stalker-pressureSkill
- worldview-game-safe-room-pressure-resetSkill
- worldview-game-scarce-inventory-triageSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 56
That's it: No complex questions. The skill automatically:
- Very specific: line 120
Always strict: Effects only after actions
- Distinctive: line 124
If you know what you want:
- Distinctive: line 184
Default: Dynamic (handles most cases)
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Anime Action Scene Generator
Generate high-intensity animated action with readable physical causes, deliberate impact frames, and dynamic camera work.
If the scene includes spoken dialogue or narration, run film-dialogue-voiceover before video generation. Recommend ElevenLabs MCP or the user's compatible speech service, retain one voice ID per speaker, prepare and measure recordings, and attach them through the video provider's supported audio interface with the visual references. Combat sound effects alone do not satisfy a requested line. Silent action needs no TTS setup.
What you get
- ✅ 10-30 second action sequence
- ✅ Dynamic camera work (Whip Pan, Spin, tracking shots)
- ✅ Key frame impacts (speed lines, impact frames, camera shake)
- ✅ Physical consistency (grounded combat, momentum preservation)
- ✅ Causality-locked VFX (effects follow actions)
How it works
Simple Conversation
User: Generate a 10-second sword fight
Skill: [Analyzes your request]
✅ Detected: Melee combat, fast-paced
✅ Auto-selected parameters:
- Action density: High (6-8 actions/second)
- Camera: Dynamic Whip Pan
- Key frames: Strong impact style
Tell me about the fighters:
Who's fighting? (e.g., "ninja vs samurai", "hero vs boss")
User: Female warrior with dual swords vs armored knight
Skill: ✅ Got it. Generating...
[10 seconds later]
✅ Done! [Download video]That's it. No complex questions. The skill automatically:
- Detects combat type from your description
- Chooses appropriate intensity level
- Applies matching camera style
- Generates with optimal parameters
When You Want More Control
User: Generate a chase scene, but make it REALLY intense
Skill: [Detects "REALLY intense"]
✅ Upgraded to: Insane action density (8-12 actions/s)
✅ Extreme camera (1200-1800°/s Whip Pan)
What's being chased?
User: Hero escaping from monster horde
Skill: ✅ Generating an extreme-density aerial pursuit...The skill understands intensity from your words:
- "intense", "crazy", "epic" → High density
- "REALLY", "extremely", "insane" → Insane density
- "smooth", "elegant" → Standard density
Advanced: Describe the motion language
User: Generate a vertical pursuit with cable swings and an orbiting camera
Skill: ✅ Matched: anchored aerial maneuvering
✅ Parameters: Insane density + camera
Your scene?
User: Sci-fi soldier with grappling hook vs aliens
Skill: ✅ Applying that motion language to your sci-fi setting...Technical Details
Auto-Detection Logic
The skill analyzes your description and automatically sets:
Action Density (hidden parameter):
standard(4-5/s): Dialogue, dramatic moments, "elegant", "smooth"high(6-8/s): Combat, chase, "fast", "intense", "epic"insane(8-12/s): "crazy", "insane", "relentless", "extreme"
Camera Intensity (hidden parameter):
stable: Emotional scenes, dialoguedynamic: Most action scenes (default)insane: "crazy camera", "full orbit", "extreme"
Key Frame Style (hidden parameter):
smooth: Continuous motionstrong: short impact hold, flash, speed lines, and camera reactionextreme: localized distortion, longer hold, and one-frame color inversion
Causality Mode (hidden parameter):
- Always
strict: Effects only after actions
Manual Override
If you know what you want:
User: Generate combat with:
- Action density: insane
- Camera: stable
- Key frames: extreme
Skill: ✅ Custom config appliedExamples
Example 1: Dual Sword vs Knight
User input: "Female warrior with dual swords vs armored knight"
Auto-detected:
- Action density: High (melee combat detected)
- Camera: Dynamic
- Duration: 10s (default)
Expected deliverable: a reviewable dual-sword-versus-knight sequence.
Example 2: Monster Chase
User input: "Hero escaping from monster horde, REALLY intense"
Auto-detected:
- Action density: Insane ("REALLY" detected)
- Camera: Insane
- Duration: 15s (chase needs more time)
Expected deliverable: a reviewable high-intensity monster-chase sequence.
Example 3: Elegant Duel
User input: "Two masters, elegant sword duel, focus on technique"
Auto-detected:
- Action density: Standard ("elegant" detected)
- Camera: Stable ("focus" suggests observational)
- Key frames: Smooth (no impact effects)
Expected deliverable: a reviewable restrained duel sequence.
Related Skills
- Boss Battle - Design complete boss encounters
- Hero Skill System - Create Q/W/E/R abilities
- Game Cutscene - Cinematic cutscenes
Tips
Get the intensity you want
Use these words:
- Standard: "smooth", "elegant", "graceful", "technical"
- High: "fast", "intense", "epic", "exciting"
- Insane: "crazy", "extreme", "relentless", "insane", "REALLY"
Camera control
- Default: Dynamic (handles most cases)
- Say "stable camera" or "fixed angle" for less movement
- Say "crazy camera" or "extreme camera" for more
Duration
- Short (10s): Single combat exchange
- Medium (20s): Chase or multi-phase fight
- Long (30s): Complete battle sequence
Skill auto-suggests duration based on your scene.
Installation
npx skills add LogicOber/Worldview-Skills --skill anime-action-sceneDoes it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

