New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Media Production

by leon-ai in leon-ai/leon

Generates images, audio and video through Leon's media tools, joins them with FFmpeg, checks the output and attaches playable files for the owner.

MITAuto-check passedMedia & Creative

Install Media Production

skills CLI
$ npx skills add leon-ai/leon --skill media-production -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install leon-ai/leon media-production --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/leon-ai/leon.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agent/media-production .claude/skills/media-production && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
media-production
GitHub stars
18k
Token cost
~999 tokens
SKILL.md length
521 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

Generates images, audio and video through Leon's media tools, joins them with FFmpeg, checks the output and attaches playable files for the owner.

  • Works in 8 steps: Establish the desired output, duration,… → For hosted image generation, use… → Generate image assets with… → …
  • Producing a short video that combines generated images, narration and music
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Creating a single image or spoken clip and delivering it as a playable file

What it does

The skill starts by pinning down the desired output, length, aspect ratio and any reference material; a single image or speech request needs only its generation tool. Generation goes through a `generate` call, which uses the conversation's active provider unless the owner is asked to choose one, and a specific model is used only when the owner names it.

Assets come from the image, audio and video generation tools, with existing local speech tools reused where they fit. Video requests return a job ID, so the agent polls its status instead of submitting again. FFmpeg and FFprobe handle composition, conversion and validation, and the agent inspects representative frames, audio and duration before calling the result verified. Finished files are attached so you get a player or download, never raw provider links or credentials.

If setup needs diagnosing, the agent inspects the default settings, and a saved provider preference is written only when you ask for one. MiniMax music generation requires an eligible account.

When your agent uses it

  • Producing a short video that combines generated images, narration and music
  • Creating a single image or spoken clip and delivering it as a playable file
  • Checking that a generated video has the right duration, frames and audio

Example prompts

  • “Make a short vertical video of a sunrise over a city with a calm voiceover.”
  • “Generate a square product image and a spoken intro, then combine them into one MP4.”
  • “Check the video you just made and confirm the audio matches its length.”

Requirements

  • A configured image, audio or video generation provider
  • FFmpeg and FFprobe for combining and checking files

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Establish the desired output, duration, aspect ratio and supplied reference material. A single image or speech request usually needs only…
  2. For hosted image generation, use media_production.image.generate with the desired prompt and output options; Core resolves tool settings…
  3. Generate image assets with media_production.image. Use existing music_audio speech tools for narration and owner-supplied audio or video…
  4. For local production, use media_production.photocraft for layered raster edits, vectorcraft for vector artwork, hyperframes for social…
  5. For an authored social video or motion graphic, establish a short storyboard and consistent visual direction: one main idea per scene…
  6. Batch independent grounding reads and author related files together. Use hyperframes.inspect to ground scene timing, then…
  7. Preview edited artwork and representative timeline/composition positions. Use existing FFmpeg and FFprobe tools for simple composition…
  8. Generated and edited artifacts are attached automatically. Attach other composed/local files through file_system.file.attach so the owner…

What it can do on your machine

Read from SKILL.md and the folder at commit 111ccc8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Media Production loads about 999 tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 521 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~999

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from leon-ai/leon at commit 111ccc8, republished under its MIT licence (© leon-ai). 521 words, ~999 tokens.

Download SKILL.mdSave it as .claude/skills/media-production/SKILL.md (or your agent's skills folder).
name
media-production
description
Generate and edit images, vector artwork, photos, audio and video; inspect results and deliver finished artifacts.
metadata.author
Louis Grenard <louis@getleon.ai>
metadata.version
1.0.0

Media Production

  1. Establish the desired output, duration, aspect ratio and supplied reference material. A single image or speech request usually needs only its generation tool.
  2. For hosted image generation, use media_production.image.generate with the desired prompt and output options; Core resolves tool settings, inheriting the active conversation provider by default. If selection_required is returned, ask the owner which available provider to use; never silently switch accounts. Use configure only when they request a saved preference. Inspect capabilities.defaults when setup needs diagnosis. Reserve generateWithModel for an explicitly owner-requested provider/model; never pick an older model from memory or bypass a default after an error.
  3. Generate image assets with media_production.image. Use existing music_audio speech tools for narration and owner-supplied audio or video clips for other media assets.
  4. For local production, use media_production.photocraft for layered raster edits, vectorcraft for vector artwork, hyperframes for social videos and motion graphics, filmcraft for timelines, and lightcraft for photo development. These tools run headlessly; PhotoCraft desktop control is optional. For Craft tools, discover commands and parameter schemas before edits, inspect the source, and use returned object/media IDs instead of guessing. Ordinary edits produce new artifacts while preserving originals. Keep referenced media available and use absolute asset paths. Select persistent LightCraft libraries only when the owner requests library work.
  5. For an authored social video or motion graphic, establish a short storyboard and consistent visual direction: one main idea per scene, readable typography at phone size, deliberate spacing, a focused palette, and useful visual assets. Match pacing to the brief; avoid walls of small text, repeated generic panels and gratuitous effects. Use hyperframes.create for a new project and the file tool to author its HTML, CSS and scene timelines. Look for suitable catalog components before inventing complex effects. Preserve supplied source by working in a copy. Tool guidance owns the composition and animation contract.
  6. Batch independent grounding reads and author related files together. Use hyperframes.inspect to ground scene timing, then hyperframes.check with options.mode=lint to catch source errors cheaply. During repairs use mode=targeted with affected times and preview neighboring frames; verify text fit, safe margins and continuity. On the final source run the default full check and require scope=full, complete=true and checks.ok=true. Targeted/lint success is partial evidence. Independent checks and previews may run together once source is stable; never edit files while they are being inspected. Reuse current-run evidence and successful checks while relevant source/assets are unchanged. Render delivery quality once and review that exact video for motion, pacing and audio; use a separate draft only when useful for unresolved motion. Rerender only after changes or an observed defect. Passing checks or looking at a still frame alone cannot establish that a video is ready to share.
  7. Preview edited artwork and representative timeline/composition positions. Use existing FFmpeg and FFprobe tools for simple composition, conversion and validation. Inspect frames and audio/duration before claiming the result is verified. Wait for background renders to complete before delivery.
  8. Generated and edited artifacts are attached automatically. Attach other composed/local files through file_system.file.attach so the owner receives a player or download. Do not expose provider URLs, credentials or base64 in chat.

© leon-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/agent/media-production of leon-ai/leon.

Open the folder on GitHubat commit 111ccc8

Compare with similar skills

Media Production next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Media Production compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Media Production this skillleon-ai/leon18k—~999Automated safety check: PassMIT
Qiaomu Cutjoeseesun/qiaomu-cut-skill372—~6.8kAutomated safety check: NotesMIT
MiniMax Multimodal Toolkitmadebyaris/advance-minimax-m3-cursor-rules126—~1.6kAutomated safety check: PassMIT
VRGDG H3 Short Film Pipelinevrgamegirl19/comfyui-vrgamedevgirl765—~4.2kAutomated safety check: PassCustom licence
ShowtimeFavioVazquez/showtime220—~3kAutomated safety check: PassMIT
Video Productionspeechlab0210/video-production-skill105—~4.1kAutomated safety check: NotesMIT

Similar skills

  • Qiaomu Cut

    joeseesun/qiaomu-cut-skill

    把一句话需求转成可复现、可验收视频工程的乔木智能剪辑导演。Use when the user asks to create, plan, edit, remix, explain, narrate, subtitle, animate, composite, or render a video—including one-line requests such as “制作一个科普视频：介绍…

    372 GitHub stars~6.8k tokensUpdated 13 days ago
    Media & CreativeAuto-check: notes

  • MiniMax Multimodal Toolkit

    madebyaris/advance-minimax-m3-cursor-rules

    Routes image, video, voice, music and media-processing requests to the smallest suitable MiniMax or local path, with FFmpeg-style processing around generated media.

    126 GitHub stars~1.6k tokensUpdated 3 mo ago
    Media & CreativeAuto-check passed

  • VRGDG H3 Short Film Pipeline

    vrgamegirl19/comfyui-vrgamedevgirl

    Builds an AI short film in a local ComfyUI with the VRGDG Video Builder, MiniMax H3 scenes, reference images, a music score, QA and a final edit.

    765 GitHub stars~4.2k tokensUpdated yesterday
    Media & CreativeAuto-check passed

  • Showtime

    FavioVazquez/showtime

    A skill your agent uses when the user wants a video made, edited or finished: a launch or promo, product demo, explainer, trailer or teaser, tutorial or walkthrough, a screen recording turned into a…

    220 GitHub stars~3k tokensUpdated 2 days ago
    Media & CreativeAuto-check passed

  • Video Production

    speechlab0210/video-production-skill

    AI educational video production pipeline. An agent skill from speechlab0210/video-production-skill.

    105 GitHub stars~4.1k tokensUpdated 3 mo ago
    Media & CreativeAuto-check: notes

  • Whiteboard Video

    gnipbao/codex-whiteboard-video-skill

    Generate smooth hand-drawn whiteboard and story videos directly inside Codex from text scripts, GPT Image 2 color storyboards, scene plans, SVGs, line art, or local images.

    327 GitHub stars~7.2k tokensUpdated 1 mo ago
    Media & CreativeAuto-check: notes

More from leon-ai/leon

  • Live Tutorial Video Maker

    leon-ai/leon

    Records a real workflow in the owner's own application and renders an annotated MP4 tutorial from verified screenshots, with captions in the language of the request.

    18k GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Leon Coding Agent

    leon-ai/leon

    Has Leon's agent investigate, change and verify code in a repository with its file, search and shell tools, staying inside the scope the owner authorized.

    18k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Document Authoring

    leon-ai/leon

    Create, inspect and deliver charts, PDFs, Word documents and spreadsheets, and open animated browser presentations.

    18k GitHub stars~1.7k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Media Production

What does Media Production do?

Generates images, audio and video through Leon's media tools, joins them with FFmpeg, checks the output and attaches playable files for the owner. The skill starts by pinning down the desired output, length, aspect ratio and any reference material; a single image or speech request needs only its generation tool. Generation goes through a `generate` call, which uses the conversation's active provider unless the owner is asked to choose one, and a specific model is used only when the owner names it.

When should I use Media Production?

Media Production fits situations like: producing a short video that combines generated images, narration and music; creating a single image or spoken clip and delivering it as a playable file; checking that a generated video has the right duration, frames and audio.

How do I install Media Production in Claude Code?

Run `npx skills add leon-ai/leon --skill media-production -a claude-code`. Or copy the skill folder (skills/agent/media-production in leon-ai/leon) into .claude/skills/media-production in your project. Claude Code loads it when a task matches its description.

How do I install Media Production in Codex?

Run `npx skills add leon-ai/leon --skill media-production -a codex`. Or copy the skill folder (skills/agent/media-production in leon-ai/leon) into .agents/skills/media-production in your project. Codex loads it when a task matches its description.

Can I use Media Production in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add leon-ai/leon --skill media-production -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/media-production, .gemini/skills/media-production, .github/skills/media-production and .opencode/skills/media-production in your project.

What does Media Production need to run?

SKILL.md names no scripts, command-line tools or credentials: Media Production is instructions for the agent only. Our summary lists: A configured image, audio or video generation provider; FFmpeg and FFprobe for combining and checking files.

Does Media Production access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Media Production safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Media Production use?

Media Production is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Media Production use?

About 999 tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Media Production?

Skills that share tags, products or a category with Media Production: Qiaomu Cut (joeseesun/qiaomu-cut-skill, 372 stars), MiniMax Multimodal Toolkit (madebyaris/advance-minimax-m3-cursor-rules, 126 stars), VRGDG H3 Short Film Pipeline (vrgamegirl19/comfyui-vrgamedevgirl, 765 stars) and Showtime (FavioVazquez/showtime, 220 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Media Production?

leon-ai (a GitHub organization) maintains it in leon-ai/leon, which has 17,564 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 11, 2026.

Source: leon-ai/leon on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.