Skip to content
Get packs

Media Production

Lets the agent generate, edit, and verify images, vector art, audio, and video, then deliver the finished files.

Source Download skill
Repository
leon-ai/leon
Stars
17,627
Licence
MIT
Files
1 file

What it does

This skill gives an AI agent a structured workflow for making visual and audio media. It tells the agent which tools to use for hosted image generation, layered photo edits, vector artwork, motion graphics, video timelines, and narration, and how to check the results before handing them over. Once installed, the agent is expected to preview its work, verify video playback and timing, and attach finished files for the owner rather than just describing them.

Great for

  • Creators who want an agent to produce social clips, title cards, or simple motion graphics from a brief
  • Marketers building image sets or short videos that must be checked against a brief before sharing
  • Developers who already run the Leon toolchain (HyperFrames, PhotoCraft, FFmpeg) and want a consistent production procedure

Skip it if

  • Users who need a fully self-contained tool with no setup: the skill references several external tools (FFmpeg, FFprobe, hosted image providers) that must already be available, and the SKILL.md does not install them
  • Anyone who wants to generate images or media from a provider account they do not control, since the skill can use the conversation's active provider and requires the owner to choose between providers when asked
  • High-stakes final video delivery without human review: the skill itself says passing automated checks does not prove a video is ready to share

Try asking

  • “Create a 15-second vertical motion graphic promoting our spring sale, with text overlays and a title card, and deliver the final MP4”
  • “Generate three square product images in a clean studio style and attach them to this chat”
  • “Remove the background from this photo in layers using PhotoCraft and export a PNG”
  • “Narrate this script with a clear voice and combine it with the clip I uploaded”
Step-by-step guide: how to use Media ProductionInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    media-production.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip media-production.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip media-production.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Give the agent the exact duration, aspect ratio, and any reference files up front so it does not need to guess
  • Ask it to validate one representative frame or asset before applying an effect to a whole batch
  • Review the final video yourself before sharing it publicly, because the skill notes that automated checks alone are not enough

What's inside

  • SKILL.md

Redistributed unmodified from leon-ai/leon under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.