Skip to main content
skill CX Codex

ai-content-pipeline — Claude Code skill: what it does, how to install

ai-content-pipeline — a skill that chains image, video, voice and music generation into one sequence on top of the inference.sh belt CLI.

no license 270 installs ★ 31 updated 2026-08-31

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add 101-skills/superpowers --skill ai-content-pipeline -a claude-code
Open on GitHub

What ai-content-pipeline does

Every stage is one belt app run call with a JSON payload. The skill has the agent keep each result in its own file, so a bad frame or a flat line gets regenerated alone instead of rerunning the whole chain.

Recipes inside cover a still that is animated and scored, plus a script that goes through Kokoro TTS into an OmniHuman avatar. Named models: falai/flux-dev, falai/wan-2-5, google/veo-3-1-fast, infsh/media-merger, Topaz upscalers.

The whole thing sits on inference.sh. Install the belt CLI first with npx skills add belt-sh/cli, then log in with belt login. Only Bash(belt *) is allowed, so nothing fires until that login goes through.

What it helps with

  • turn a written script into a narrated clip with moving visuals
  • build a talking-head video from a portrait and a voice track
  • cut a product demo with rotation, upscaling and background music
  • split an article into scenes, one image per scene
  • merge separate clips and a narration into a single file

Example prompts for the agent

  • Chain a 30-second script through Kokoro TTS, a FLUX background and Wan 2.5 animation, then merge the tracks with infsh/media-merger.
  • Make a talking head: portrait from falai/flux-dev, speech from infsh/kokoro-tts, avatar from bytedance/omnihuman-1-5.
  • Run the product demo pipeline: earbuds shot, slow rotation, Topaz upscale, music at volume 0.3.

How to install ai-content-pipeline

1Skills CLI (Vercel)

npx skills add 101-skills/superpowers --skill ai-content-pipeline -a claude-code

2Manually: put the files in place

~/.claude/skills/ai-content-pipeline/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/ai-content-pipeline/

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

Questions about ai-content-pipeline

How do I install ai-content-pipeline in Claude Code?

Run npx skills add 101-skills/superpowers --skill ai-content-pipeline -a claude-code. The skill lands at ~/.claude/skills/ai-content-pipeline/SKILL.md.

What does ai-content-pipeline do?

It lays out media production as a series of belt app run calls, saving each output before handing it to the next tool in the chain.

What do I need before it works?

The inference.sh CLI: install it with npx skills add belt-sh/cli, then run belt login. The skill is limited to Bash(belt *).

Similar skills

All skills for AI and ML →

From the same set81

The whole set →
seedance Drives ByteDance Seedance 2.0 through the inference.sh CLI to make videos with synchronized audio. Useful for clips, demos and animation. CX Codex +1 14,500installs p-video p-video generates videos from text prompts or still images using Pruna models via the belt CLI. Handy for creating 720p and 1080p clips directly in your agent terminal. CX Codex +1 14,500installs p-image A skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode that connects four Pruna P-Image models through the belt CLI. Covers text-to-image, image editing, LoRA style presets, and multi-image compositing. CX Codex +1 14,500installs p-video-avatar p-video-avatar — a skill for generating talking avatar videos from portrait images via CLI. Built-in text-to-speech, 30 voices, 10 languages, up to 1080p resolution — 18x faster and 6x cheaper than competitors. CX Codex +1 14,400installs video-prompting-guide video-prompting-guide breaks a video prompt into shot, movement, light and style, with phrase tables and per-model notes. For the point where plain descriptions stop working. CX Codex +1 268installs data-visualization data-visualization picks the right chart for your data, sets a palette and axis labels, then renders the figure through the belt CLI. CX Codex +1 255installs prompt-engineering prompt-engineering — a skill that lays out prompt structure for text models, image generators and video models, with examples you can run through the belt CLI. CX Codex +1 251installs explainer-video-guide The explainer-video-guide skill maps an explainer video from script to assembly, with guidance for pacing, scene design, voiceover, and generated visuals. CX Codex +1 249installs

Project sponsors

Companies that keep this analytics open