Agent skill

Film Creator

by happycapy-ai in happycapy-ai/Happycapy-skills

AI-powered film creation assistant that transforms a single sentence or image into a complete 30-second film.

MITAuto-check: notesMedia & Creative

Install Film Creator

skills CLI
$ npx skills add happycapy-ai/Happycapy-skills --skill film-creator -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install happycapy-ai/Happycapy-skills film-creator --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/happycapy-ai/Happycapy-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/film-creator .claude/skills/film-creator && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
film-creator
GitHub stars
137
Token cost
~3k tokens
SKILL.md length
1,025 words
Files
2
Skills in repo
28
Repo updated
First seen
Licence
MIT

At a glance

AI-powered film creation assistant that transforms a single sentence or image into a complete 30-second film.

  • Works in 4 steps: Creative Analysis → Screenplay Writing → Scene-by-Scene Generation → …
  • User wants to create a movie
  • SKILL.md covers Overview, Prerequisites, Quick Start and Features, plus 5 more sections
  • Calls node; needs AI_GATEWAY_API_KEY

What it does

Film Creator is an agent skill from happycapy-ai/Happycapy-skills. AI-powered film creation assistant that transforms a single sentence or image into a complete 30-second film. Automatically generates screenplay with scenes, dialogue, and camera directions, then produces cinematic video. Use when user wants to create a movie, film, or video story from text or image input. Trigger phrases: '创作电影', '生成电影', 'film creator', 'make a movie', 'create a film'.

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `README.md`).

It sits in Media & Creative, covering Creative writing and fiction and AI video generation. The repository describes itself as: A curated collection of high-quality Claude Code skills to enhance your development workflow. The licence is MIT.

When your agent uses it

  • User wants to create a movie
  • Video story from text

Example prompts

  • “film creator”
  • “make a movie”
  • “create a film”
  • “/film-creator”

Requirements

  • Node.js
  • A credential in AI_GATEWAY_API_KEY
  • Pre-approved tools (allowed-tools): Bash, Read, Write, Edit

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Creative Analysis
  2. Screenplay Writing
  3. Scene-by-Scene Generation
  4. Video Assembly

What it can do on your machine

Read from SKILL.md and the folder at commit 9ff72fe. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Write
    • Edit

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • AI_GATEWAY_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Film Creator loads about 3k tokens when it runs. Until then it costs about 101 tokens; SKILL.md has 1,025 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~101
When it runs · the whole SKILL.md, loaded when a task matches
~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Write, Edit

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from happycapy-ai/Happycapy-skills at commit 9ff72fe, republished under its MIT licence (© happycapy-ai). 1,025 words, ~2,986 tokens.

Download SKILL.mdSave it as .claude/skills/film-creator/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
film-creator
description
AI-powered film creation assistant that transforms a single sentence or image into a complete 30-second film. Automatically generates screenplay with scenes, dialogue, and camera directions, then produces cinematic video. Use when user wants to create a movie, film, or video story from text or image input. Trigger phrases: '创作电影', '生成电影', 'film creator', 'make a movie', 'create a film'.
allowed-tools
Bash, Read, Write, Edit
version
1.0.0
license
MIT

Film Creator - AI Film Production Assistant

Transform a single idea or image into a complete 30-second cinematic film with professional screenplay and video generation.

Overview

This skill provides end-to-end film creation capabilities:

  1. Creative Analysis: Analyzes text prompt or image to extract core creative elements
  2. Screenplay Generation: Writes professional screenplay with scenes, dialogue, shot descriptions, and camera movements
  3. Scene Planning: Breaks screenplay into 5-6 scenes (5 seconds each) optimized for video generation
  4. Video Production: Generates high-quality video for each scene using AI Gateway
  5. Film Assembly: Combines scenes into a cohesive 30-second film with transitions

Prerequisites

Required Environment Variable:

  • AI_GATEWAY_API_KEY: Your AI Gateway API key (automatically configured in HappyCapy)

Required Tools:

  • Node.js 24+ (pre-installed in HappyCapy)
  • FFmpeg (pre-installed in HappyCapy)

Quick Start

Create a Film from Text
bash
node scripts/create_film.js "A lonely robot discovers the last flower on Earth"
Create a Film from Image
bash
node scripts/create_film.js --image "/path/to/image.jpg" "Transform this into a cinematic story"
Create a Film with Custom Settings
bash
node scripts/create_film.js \
  "A time traveler's final journey" \
  --model "openai/sora-2" \
  --aspect-ratio "16:9" \
  --output "my_film.mp4"

Features

Screenplay Generation
  • Story Structure: Three-act structure adapted for 30-second format
  • Scene Breakdown: 5-6 distinct scenes with clear transitions
  • Visual Descriptions: Detailed shot compositions and camera movements
  • Cinematic Language: Professional terminology (establishing shot, close-up, tracking shot, etc.)
  • Emotional Arc: Clear beginning, middle, and end with emotional progression
Video Generation
  • Multi-Scene Production: Generates 5-6 individual scenes
  • Cinematic Quality: Uses professional video generation models
  • Smart Prompting: Converts screenplay into optimized video generation prompts
  • Continuity: Maintains visual consistency across scenes
Film Assembly
  • Scene Stitching: Seamlessly combines individual scenes
  • Transitions: Smooth cuts or fade transitions between scenes
  • Duration Control: Precisely timed to 30 seconds total
  • Quality Preservation: No re-encoding loss

Supported Models

ModelBest ForDuration per Scene
google/veo-3.1-generate-previewBalanced quality and reliability (Recommended)5-6 seconds
openai/sora-2Cinematic quality with complex scenes4-6 seconds
openai/sora-2-proProfessional-grade cinematic output4-6 seconds
byteplus/seedance-1-0-proFlexible aspect ratios5-6 seconds

Usage Examples

Basic Film Creation
bash
# From a simple concept
node scripts/create_film.js "A cat astronaut explores a distant planet"

# With specific genre
node scripts/create_film.js "A noir detective story set in the rain"

# From an uploaded image
node scripts/create_film.js --image "concept_art.jpg" "Make this into an epic adventure"
Advanced Options
bash
# Use premium model for highest quality
node scripts/create_film.js \
  "An emotional reunion at a train station" \
  --model "openai/sora-2-pro" \
  --output "reunion.mp4"

# Create vertical video for mobile
node scripts/create_film.js \
  "A day in the life of a street performer" \
  --aspect-ratio "9:16" \
  --model "byteplus/seedance-1-0-pro"

# Generate only the screenplay
node scripts/generate_screenplay.js "A magical library where books come alive"

Workflow

Step 1: Creative Analysis

The system analyzes your input (text or image) to identify:

  • Core concept and theme
  • Emotional tone
  • Visual style
  • Key story elements
Step 2: Screenplay Writing

Generates a professional screenplay including:

  • Scene Headings: INT./EXT. location and time
  • Action Lines: Visual descriptions of what happens
  • Camera Directions: Shot types and movements
  • Timing: Duration for each scene

Example screenplay output:

FADE IN:

EXT. ABANDONED CITY - DAY

WIDE ESTABLISHING SHOT: A desolate cityscape covered in rust and vines.
The sun casts long shadows through broken buildings.

A small ROBOT (weathered, curious) rolls through debris, its single eye
scanning the ground.

CLOSE-UP: The robot's sensors light up as it detects something.

LOW ANGLE: The robot stops at a crack in the concrete where a single
FLOWER blooms in brilliant red.

EXTREME CLOSE-UP: The robot's optical lens focuses on the flower,
reflecting its petals.

The robot extends a gentle mechanical hand, not to touch, but to protect.

FADE OUT.
Step 3: Scene-by-Scene Generation

Each scene is converted to an optimized video prompt:

  • Camera angles and movements specified
  • Visual details enhanced
  • Lighting and mood emphasized
  • Continuity elements maintained
Step 4: Video Assembly

All scenes are combined with:

  • Frame-accurate stitching
  • Optional transitions (cut/fade)
  • Audio-ready format (MP4)
  • Optimized compression

Command Reference

create_film.js (Main Script)

Parameters:

  • prompt (required): Text description or story concept
  • --image PATH (optional): Image file to use as creative inspiration
  • --model MODEL (optional): Video generation model (default: google/veo-3.1-generate-preview)
  • --aspect-ratio RATIO (optional): Video aspect ratio (default: 16:9)
  • --output PATH (optional): Output file path (default: generated_film.mp4)
  • --no-assembly (optional): Generate scenes only, don't combine them
  • --transition TYPE (optional): Transition type: "cut" or "fade" (default: cut)
generate_screenplay.js

Generate screenplay without video production:

bash
node scripts/generate_screenplay.js "Your story concept" [--output screenplay.txt]
generate_scene.js

Generate a single scene from a prompt:

bash
node scripts/generate_scene.js "Scene description with camera angles" [--model MODEL] [--duration SECONDS]
assemble_film.js

Combine pre-generated scene videos:

bash
node scripts/assemble_film.js scene1.mp4 scene2.mp4 scene3.mp4 --output final.mp4

Best Practices

Writing Effective Prompts

Good prompts include:

  • Clear genre or style ("noir film", "whimsical animation style")
  • Emotional core ("a story about hope", "bittersweet reunion")
  • Visual anchors ("neon-lit city", "misty forest")
  • Character elements ("lonely protagonist", "mischievous creature")

Examples:

✓ "A cyberpunk story about a hacker who discovers they're an AI"
✓ "A heartwarming tale of a child's robot friend, Studio Ghibli style"
✓ "A suspenseful noir detective story in the rain at night"
✓ "An epic space opera battle with massive starships"

✗ "Make a video"  (too vague)
✗ "Something cool"  (no direction)
Model Selection
  • Use Google Veo 3.1 for most projects - excellent balance of quality and reliability
  • Use OpenAI Sora 2 Pro for highest cinematic quality and complex physics
  • Use BytePlus Seedance when you need non-standard aspect ratios (1:1, 9:16, 21:9)
Image Input Tips

When using an image as input:

  • Provide a complementary text prompt to guide the narrative
  • The system will analyze visual elements (colors, composition, mood)
  • Works best with conceptual or atmospheric images
  • Character-focused images can become protagonists
Show full SKILL.md (422 more words)Show less
Duration Optimization
  • Each scene is 5 seconds for optimal storytelling pace
  • 6 scenes = 30 seconds total
  • This pacing allows for:
    • Establishing shot
    • Rising action
    • Climax/key moment
    • Resolution
    • Emotional beat
    • Closing image

Troubleshooting

"Generation timeout" or "Scene generation failed"

Video generation can take time. The script automatically waits up to 5 minutes per scene. If it fails:

  • Try a simpler prompt for that scene
  • Use a faster model (google/veo-3.1-fast-generate-preview)
  • Check your internet connection
"FFmpeg error" during assembly

Ensure all scene files were generated successfully:

bash
ls -lh scene_*.mp4

If some scenes are missing or corrupted, regenerate them individually:

bash
node scripts/generate_scene.js "Scene description" --output scene_3.mp4
Poor visual continuity between scenes

The screenplay generator aims for continuity, but AI models may interpret scenes differently. To improve:

  • Add more specific visual details in your prompt
  • Specify a consistent color palette or lighting
  • Use model-specific style references
"API key not found"

Set the environment variable:

bash
export AI_GATEWAY_API_KEY="your-api-key-here"

Technical Details

Screenplay Format

The generated screenplay follows industry-standard formatting:

  • Scene headings in caps
  • Action lines in present tense
  • Camera directions in caps or parentheses
  • Timing notes for pacing
Video Specifications
  • Format: MP4 (H.264)
  • Resolution: Model-dependent (typically 1280x720 or 1920x1080)
  • Frame Rate: 24-30 fps
  • Duration: Exactly 30 seconds
  • Aspect Ratios: 16:9, 9:16, or custom (model-dependent)
Assembly Process

Uses FFmpeg with:

  • Lossless concatenation when possible
  • Minimal re-encoding
  • Frame-accurate cutting
  • Preserved metadata
Example 1: Sci-Fi Short

Prompt: "A lonely robot discovers the last flower on Earth"

Generated Screenplay (abbreviated):

Scene 1: Wide shot of desolate cityscape
Scene 2: Robot character introduction
Scene 3: Discovery of flower (key moment)
Scene 4: Emotional close-up of robot's reaction
Scene 5: Robot protecting the flower
Scene 6: Hopeful closing image
Example 2: Fantasy Adventure

Prompt: "A young wizard's first spell goes wonderfully wrong"

Key Scenes:

  • Establishing: Magic academy interior
  • Character: Nervous student with wand
  • Action: Spell casting with dramatic effects
  • Consequence: Humorous magical mishap
  • Reaction: Wizard's surprise and laughter
  • Resolution: Acceptance and learning moment
Example 3: Noir Detective

Prompt: "A 1940s detective receives a mysterious case in the rain"

Style Elements:

  • High contrast lighting (noir aesthetic)
  • Rain effects and reflections
  • Dramatic shadows
  • Close-ups on key objects
  • Moody, atmospheric tone

Integration with Other Skills

This skill works well with:

  • generate-image: Create concept art before film production
  • image-enhancer: Improve reference images
  • video-frames: Extract keyframes from generated films for editing

Limitations

  • Maximum duration: 30 seconds (by design)
  • Scene count: 5-6 scenes (optimal for pacing)
  • No dialogue audio (visual storytelling only)
  • No custom music (silent film format)
  • Limited character consistency across scenes (model limitation)

Future Enhancements

Potential additions:

  • Background music generation and integration
  • Text-to-speech for dialogue
  • Extended duration options (60s, 90s)
  • Multi-character tracking
  • Style transfer between reference and generated scenes
  • Storyboard visualization before generation

Credits

Built on top of:

  • AI Gateway API (video generation)
  • FFmpeg (video assembly)
  • Node.js (orchestration)

License

MIT License - Free to use and modify

© happycapy-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/film-creator of happycapy-ai/Happycapy-skills.

  • SKILL.md
  • README.md

Open the folder on GitHubat commit 9ff72fe

Compare with similar skills

Film Creator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Film Creator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Film Creator this skillhappycapy-ai/Happycapy-skills137—~3kAutomated safety check: NotesMIT
Emotion Performance Directorkangarooking/director-skills181—~2.4kAutomated safety check: PassMIT
Novel Artsuihe1/short-drama-production181—~1.3kAutomated safety check: NotesApache-2.0
Seedance Interview1370998960-del/https-github.com-Emily2040-seedance-2.0241—~2.6kAutomated safety check: PassMIT
Storyboard Managerailabs-393/ai-labs-claude-skills4551 repos~4.6kAutomated safety check: PassMIT
Seedance Brand Storybeshuaxian/higgsfield-seedance2-jineng952—~14kAutomated safety check: PassNone

Similar skills

  • Emotion Performance Director

    kangarooking/director-skills

    A skill your agent uses when the user wants to design, rewrite, refine, or vary emotional acting prompts for live-action AI video characters.

    181 GitHub stars~2.4k tokensUpdated 4 days ago
    Media & CreativeAuto-check passed
  • Novel Art

    suihe1/short-drama-production

    为 AI 短剧设计场景和叙事道具母本、光照与状态变体,产出 art.json、Markdown、评审报告和可选设定图。用于美术设定、场景与道具一致性;不代替导演调度或成片人流设计。

    181 GitHub stars~1.3k tokensUpdated 25 days ago
    Media & CreativeAuto-check: notes
  • Seedance Interview

    1370998960-del/https-github.com-Emily2040-seedance-2.0

    This skill should be used when the user has a vague Seedance 2.0 video idea and asks for creative guidance, story development, scene planning, a director interview, or help turning an undeveloped…

    241 GitHub stars~2.6k tokensUpdated 3 mo ago
    Media & CreativeAuto-check passed
  • Storyboard Manager

    ailabs-393/ai-labs-claude-skills

    Assist writers with story planning, character development, plot structuring, chapter writing, timeline tracking, and consistency checking.

    455 GitHub starsUsed in 1 repo~4.6k tokens
    Media & CreativeAuto-check passed
  • Seedance Brand Story

    beshuaxian/higgsfield-seedance2-jineng

    Generate brand storytelling and narrative video prompts for Seedance 2.0 on Higgsfield.

    952 GitHub stars~14k tokensUpdated 6 mo ago
    Media & CreativeAuto-check passed
  • Story To Video Workflow

    Utopai-Research/pai-code

    Orchestrates story, script, screenplay, concept, product promo, and multi-shot idea work into finished video.

    357 GitHub stars~2k tokensUpdated 11 days ago
    Media & CreativeAuto-check passed

More from happycapy-ai/Happycapy-skills

All 28 skills in this repo
  • Happycapy Skill Creator

    happycapy-ai/Happycapy-skills

    Automate HappyCapy skill creation by finding and adapting existing skills from anthropics/skills repository.

    137 GitHub stars~627 tokensUpdated 1 mo ago
    Auto-check passed
  • 360 Panorama Viewer

    happycapy-ai/Happycapy-skills

    Build a fully self-contained 360° equirectangular panorama viewer as a single HTML file.

    137 GitHub stars~2.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Generate Image

    happycapy-ai/Happycapy-skills

    Generate and transform images using AI Gateway API. An agent skill from happycapy-ai/Happycapy-skills.

    137 GitHub stars~2k tokensUpdated 1 mo ago
    Auto-check: notes
  • LLM Council

    happycapy-ai/Happycapy-skills

    Multi-model LLM Council with live dashboard. An agent skill from happycapy-ai/Happycapy-skills.

    137 GitHub stars~581 tokensUpdated 1 mo ago
    Auto-check passed
  • PPTX

    happycapy-ai/Happycapy-skills

    Create polished PowerPoint (.pptx) presentations directly from a topic or content description.

    137 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed
  • World Class Carousel

    happycapy-ai/Happycapy-skills

    Generate world-class Instagram carousel content on any topic.

    137 GitHub stars~16k tokensUpdated 1 mo ago
    Auto-check: notes

Questions about Film Creator

What does Film Creator do?

AI-powered film creation assistant that transforms a single sentence or image into a complete 30-second film. Film Creator is an agent skill from happycapy-ai/Happycapy-skills. AI-powered film creation assistant that transforms a single sentence or image into a complete 30-second film.

When should I use Film Creator?

Film Creator fits situations like: user wants to create a movie; video story from text.

How do I install Film Creator in Claude Code?

Run `npx skills add happycapy-ai/Happycapy-skills --skill film-creator -a claude-code`. Or copy the skill folder (skills/film-creator in happycapy-ai/Happycapy-skills) into .claude/skills/film-creator in your project. Claude Code loads it when a task matches its description.

How do I install Film Creator in Codex?

Run `npx skills add happycapy-ai/Happycapy-skills --skill film-creator -a codex`. Or copy the skill folder (skills/film-creator in happycapy-ai/Happycapy-skills) into .agents/skills/film-creator in your project. Codex loads it when a task matches its description.

Can I use Film Creator in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add happycapy-ai/Happycapy-skills --skill film-creator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/film-creator, .gemini/skills/film-creator, .github/skills/film-creator and .opencode/skills/film-creator in your project.

What does Film Creator need to run?

Going by SKILL.md and its folder, Film Creator needs the command-line tools its instructions call (node) and credentials named AI_GATEWAY_API_KEY. Our summary lists: Node.js; A credential in AI_GATEWAY_API_KEY. Its frontmatter pre-approves these tools: Bash, Read, Write, Edit.

Does Film Creator access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Film Creator safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Film Creator use?

Film Creator is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Film Creator use?

About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Film Creator?

Skills that share tags, products or a category with Film Creator: Emotion Performance Director (kangarooking/director-skills, 181 stars), Novel Art (suihe1/short-drama-production, 181 stars), Seedance Interview (1370998960-del/https-github.com-Emily2040-seedance-2.0, 241 stars) and Storyboard Manager (ailabs-393/ai-labs-claude-skills, 455 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Film Creator?

happycapy-ai (a GitHub user) maintains it in happycapy-ai/Happycapy-skills, which has 137 GitHub stars. The repository holds 28 skills in this directory. The repository was last updated on September 3, 2026.

Source: happycapy-ai/Happycapy-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.