OpenParable
Skip to content
← Back to skills

Runway Core Workflow A

Apps & Automation
runway-core-workflow-a

Runway Core Workflow A is an Agent Skill for apps & automation published in the jeremylongshore/claude-code-plugins-plus-skills repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Runway core workflow a — AI video generation and creative AI platform. Use when working with Runway for video generation, image editing, or creative AI. Trigger with phrases like "runway core workflow a", "runway-core-workflow-a", "AI video generation".

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/jeremylongshore/claude-code-plugins-plus-skills/blob/HEAD/plugins/saas-packs/runway-pack/skills/runway-core-workflow-a/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/runway-core-workflow-a, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Runway Core Workflow A

Overview

Advanced text-to-video generation: prompt engineering, model selection, parameter tuning, and batch generation.

Prerequisites

  • Completed runway-hello-world

Instructions

Step 1: Model Selection

from runwayml import RunwayML
client = RunwayML()

# Available models:
# gen3a_turbo   — Fast, lower cost, good quality
# gen4_turbo    — Latest model, highest quality

task = client.image_to_video.create(
    model='gen4_turbo',
    prompt_text='A futuristic cityscape at night with flying cars and neon signs, cyberpunk aesthetic',
    duration=10,
    ratio='16:9',
)
result = task.wait_for_task_output()

Step 2: Prompt Engineering Tips

# Structure: Subject + Action + Setting + Style + Camera
prompts = [
    # Good: specific, visual, stylistic
    "A red fox walking through a snowy forest, soft winter light, documentary style, tracking shot",

    # Good: detailed motion and camera
    "Waves of golden wheat swaying in the wind, drone flyover, warm sunset, cinematic grain",

    # Bad: too abstract
    # "Something beautiful happening" — too vague
]

Step 3: Batch Generation

import asyncio

prompts = [
    "A butterfly emerging from a cocoon, macro lens, time-lapse, studio lighting",
    "Rain falling on a Tokyo street at night, reflections, neon, dolly zoom",
    "A chef preparing sushi in a traditional kitchen, close-up, warm lighting",
]

tasks = []
for prompt in prompts:
    task = client.image_to_video.create(
        model='gen3a_turbo',
        prompt_text=prompt,
        duration=5,
    )
    tasks.append(task)
    print(f"Queued: {task.id}")

# Wait for all
for task in tasks:
    result = task.wait_for_task_output()
    status = "OK" if result.status == "SUCCEEDED" else "FAILED"
    print(f"  {task.id}: {status}")

Step 4: Output Format Options

task = client.image_to_video.create(
    model='gen3a_turbo',
    prompt_text='Abstract paint mixing in slow motion, vibrant colors, black background',
    duration=5,
    ratio='9:16',      # Vertical for mobile/TikTok
    # ratio='16:9',    # Landscape for YouTube
    # ratio='1:1',     # Square for Instagram
)

Output

  • Videos generated with optimal model selection
  • Prompt engineering best practices applied
  • Batch generation for multiple videos
  • Output in various aspect ratios

Error Handling

IssueCauseSolution
Low qualityGen3a_turbo for complex sceneUse gen4_turbo for higher quality
Content rejectionPolicy violationRemove violent/explicit content from prompt
Slow generationHigh queueUse turbo model or try later
Wrong aspect ratioNot specifiedAlways set ratio explicitly

Resources

Next Steps

Image-to-video: runway-core-workflow-b