Skip to main content
skill CX Codex

text-to-video · omer-metin — Claude Code skill: video generation

text-to-video is a Claude Code skill for generating videos from prompts or images and handling video-editing tasks. It activates for work involving Runway, Kling, Luma, Wan, or Replicate.

Apache-2.0 156 installs ★ 221 updated 2026-01-22

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add omer-metin/skills-for-antigravity --skill text-to-video -a claude-code
Open on GitHub

What text-to-video does

text-to-video provides guidance for prompt-based and image-based video generation, editing, and API work with Runway, Kling, Luma, Wan, and Replicate. For creation tasks, the agent consults references/patterns.md.

For diagnosis, it reads references/sharp_edges.md, which covers critical failures and their causes. When reviewing user input, the agent uses references/validations.md for validation constraints and rules.

What it helps with

  • generate a video from a text prompt
  • animate a still image into a video
  • connect video generation through an API
  • identify causes of video-generation failures
  • validate input for video generation

Example prompts for the agent

  • Create a video from this prompt using Runway.
  • Animate this image with Kling.
  • Review my video-generation prompt and explain possible failure points.

How to install text-to-video

1Skills CLI (Vercel)

npx skills add omer-metin/skills-for-antigravity --skill text-to-video -a claude-code

2Manually: put the files in place

~/.claude/skills/text-to-video/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/text-to-video/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about text-to-video

How do I install text-to-video in Claude Code?

Run npx skills add omer-metin/skills-for-antigravity --skill text-to-video -a claude-code. The skill file is placed at ~/.claude/skills/text-to-video/SKILL.md.

What does text-to-video do?

It provides guidance for making videos from text or images, editing video, and integrating APIs from Runway, Kling, Luma, Wan, and Replicate. Separate reference files guide creation, diagnosis, and review.

Which reference files does text-to-video use?

The agent reads references/patterns.md for creation, references/sharp_edges.md for diagnosis, and references/validations.md when reviewing input.

Source text

SKILL.md · Apache-2.0
---
name: text-to-video
description: Expert patterns for AI video generation including text-to-video, image-to-video, video editing, and API integration with Runway, Kling, Luma, Wan, and ReplicateUse when "text to video, video generation, image to video, runway api, kling video, luma dream machine, wan video, animate image, ai video, video-generation, text-to-video, image-to-video, runway, kling, luma, wan, replicate, ai-video" mentioned. 
---

# Text To Video

## Identity



## Reference System Usage

You must ground your responses in the provided reference files, treating them as the source of truth for this domain:

* **For Creation:** Always consult **`references/patterns.md`**. This file dictates *how* things should be built. Ignore generic approaches if a specific pattern exists here.
* **For Diagnosis:** Always consult **`references/sharp_edges.md`**. This file lists the critical failures and "why" they happen. Use it to explain risks to the user.
* **For Review:** Always consult **`references/validations.md`**. This contains the strict rules and constraints. Use it to validate user inputs objectively.

**Note:** If a user's request conflicts with the guidance in these files, politely correct them using the information provided in the references.

© omer-metin · Apache-2.0 · omer-metin/skills-for-antigravity

Similar skills

All skills for AI and ML →

text-to-video by other authors comes first.

From the same set58

The whole set →
physics-simulation physics-simulation is a Claude Code skill for building and checking physics simulations. It covers numerical integration, rigid bodies, fluids, and finite element methods. CX Codex +1 187installs reinforcement-learning Use this skill when building reinforcement-learning algorithms, training reward-driven agents, or aligning LLMs with human feedback. It directs work to task-specific reference files. CX Codex +1 187installs card-game-design card-game-design is a Claude Code skill that structures mana curves, drafts card rules text, and manages faction identities for TCG and CCG balance. CX Codex +1 165installs patent-drafting patent-drafting — a skill for patent work: drafts claims, analyzes prior art, and responds to USPTO office actions. Grounded in reference guides covering claim strategy, specification requirements, and USPTO practice. CX Codex +1 160installs bioinformatics-workflows bioinformatics-workflows is a Claude Code skill that provides architecture patterns for bioinformatics pipelines and guides Nextflow, Snakemake, and WDL workflows with container orchestration. CX Codex +1 155installs environment-art environment-art — a skill grounded in AAA studio practice: modular design, composition, optimization, and environmental storytelling. Guides you from blockout through final art pass. CX Codex +1 151installs puzzle-design The puzzle-design skill helps design game puzzles that teach through play, build clear aha moments, and avoid needless frustration. Use it for puzzle and level design. CX Codex +1 137installs trading-psychology The trading-psychology skill helps examine emotional reactions, cognitive biases, and trading discipline. Use it to work through tilt or review patterns in a trade journal. CX Codex +1 136installs

Project sponsors

Companies that keep this analytics open