AugmentClaude

Text to Video Converter

Convert articles into narrated short videos with animations and effects.

Installation

  1. Make sure Claude is on your device and in your terminal.

    Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.

    One-time setup
    npm i -g @anthropic-ai/claude-code

    Already have it? Skip ahead.

  2. Paste into Claude Code or into your terminal.

    This copies the whole skill folder into ~/.claude/skills/wjs-converting-text-to-video-jianshuo/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.

    Faster alternative (instruction-only skills)

    Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

    Quick install (SKILL.md only)
    Sign up to copy
  3. Restart Claude Code.

    Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.

  4. Just ask Claude.

    Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

Use when the user wants a -style WeChat article (article.md) turned into a narrated short MP4 video — TTS voiceover via Volcano TTS, HyperFrames CSS/GSAP animation per scene, subtle SFX, abstract watercolor background, full pipeline rendering to 1080×1920 portrait MP4 (30-90s). Triggers —, "/wjs-converting-text-to-video".

What this skill does

This skill converts articles into narrated short videos for social media. You provide an article in Markdown format, and the skill transforms it into a polished 1080×1920 portrait video (30–90 seconds) with text-to-speech narration, animated typography, abstract watercolor backgrounds, and sound effects.

What it does

  • Designs 5–10 visual scenes from your article text, each with a distinct layout, typography, and animation style—no two scenes look alike
  • Generates natural-sounding narration via Volcano TTS (default: conversational male voice), with proper timing and pacing synchronized to each scene
  • Creates an abstract watercolor background in a warm palette matching your article's theme, then softly blurs it to serve as a subtle base layer for all scenes
  • Animates text with modern techniques: kinetic character entrance, number tickers, color-fills, outline-to-solid morphs, highlight sweeps, and camera punches—each used strategically to avoid monotony
  • Applies a strict design system: warm cream text (#f5efe5), orange and other accent colors for emphasis, high-contrast layouts, and geometric decorative elements (bars, quotation marks, numbered lists)
  • Renders to MP4 in 1080×1920 portrait format at 30 fps, ready for YouTube Shorts, TikTok, or Xiaohongshu, with optional automatic upload to YouTube

How to use it

Provide an article folder containing article.md. Either run the command /wjs-converting-text-to-video <article-folder> or describe your request in natural language (e.g., "turn this into a video" or "make a narrated explainer"). The skill orchestrates the full pipeline: writing scene descriptions and narration chunks, generating TTS audio, creating the background, designing the HyperFrames composition with animations and transitions, adding sound effects, linting and inspecting the layout for overflow, rendering to MP4, and optionally uploading to YouTube on a daily schedule.

Related skills