Media Processing
nicepkg/ai-workflow
Video/audio/image processing with FFmpeg and ImageMagick. An agent skill from nicepkg/ai-workflow.
Process multimedia files with FFmpeg (video/audio encoding, conversion, streaming, filtering, hardware acceleration), ImageMagick (image manipulation, format conversion, batch processing, effects…
$ npx skills add ynulihao/AgentSkillOS --skill media-processing -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ynulihao/AgentSkillOS media-processing --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ynulihao/AgentSkillOS.git skills-src && mkdir -p .claude/skills && cp -r skills-src/data/skill_seeds/media-processing .claude/skills/media-processing && rm -rf skills-srcUse ~/.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/
Install the "media-processing" agent skill from https://github.com/ynulihao/AgentSkillOS/tree/main/data/skill_seeds/media-processing into .claude/skills/media-processing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "media-processing", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ynulihao/AgentSkillOS/tree/main/data/skill_seeds/media-processingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ynulihao/AgentSkillOS --skill media-processing -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ynulihao/AgentSkillOS media-processing --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ynulihao/AgentSkillOS.git skills-src && mkdir -p .agents/skills && cp -r skills-src/data/skill_seeds/media-processing .agents/skills/media-processing && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "media-processing" agent skill from https://github.com/ynulihao/AgentSkillOS/tree/main/data/skill_seeds/media-processing into .agents/skills/media-processing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "media-processing", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ynulihao/AgentSkillOS --skill media-processing -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ynulihao/AgentSkillOS media-processing --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ynulihao/AgentSkillOS.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/data/skill_seeds/media-processing .cursor/skills/media-processing && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "media-processing" agent skill from https://github.com/ynulihao/AgentSkillOS/tree/main/data/skill_seeds/media-processing into .cursor/skills/media-processing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "media-processing", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ynulihao/AgentSkillOS.git --path data/skill_seeds/media-processing--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ynulihao/AgentSkillOS --skill media-processing -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ynulihao/AgentSkillOS media-processing --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ynulihao/AgentSkillOS.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/data/skill_seeds/media-processing .gemini/skills/media-processing && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "media-processing" agent skill from https://github.com/ynulihao/AgentSkillOS/tree/main/data/skill_seeds/media-processing into .gemini/skills/media-processing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "media-processing", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ynulihao/AgentSkillOS media-processingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ynulihao/AgentSkillOS --skill media-processing -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ynulihao/AgentSkillOS.git skills-src && mkdir -p .github/skills && cp -r skills-src/data/skill_seeds/media-processing .github/skills/media-processing && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "media-processing" agent skill from https://github.com/ynulihao/AgentSkillOS/tree/main/data/skill_seeds/media-processing into .github/skills/media-processing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "media-processing", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ynulihao/AgentSkillOS --skill media-processing -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ynulihao/AgentSkillOS media-processing --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ynulihao/AgentSkillOS.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/data/skill_seeds/media-processing .opencode/skills/media-processing && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "media-processing" agent skill from https://github.com/ynulihao/AgentSkillOS/tree/main/data/skill_seeds/media-processing into .opencode/skills/media-processing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "media-processing", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
media-processingProcess multimedia files with FFmpeg (video/audio encoding, conversion, streaming, filtering, hardware acceleration), ImageMagick (image manipulation, format conversion, batch processing, effects…
Media Processing is an agent skill from ynulihao/AgentSkillOS. Process multimedia files with FFmpeg (video/audio encoding, conversion, streaming, filtering, hardware acceleration), ImageMagick (image manipulation, format conversion, batch processing, effects, composition), and RMBG (AI-powered background removal). Use when converting media formats, encoding videos with specific codecs (H.264, H.265, VP9), resizing/cropping images, removing backgrounds from images, extracting audio from video, applying filters and effects, optimizing file sizes, creating streaming manifests…
Its SKILL.md is about 820 tokens, which your agent loads only when the skill is triggered. The skill folder holds 24 other files, including scripts and reference files (for example `references/common-workflows.md`, `references/ffmpeg-encoding.md` and `references/ffmpeg-filters.md`).
It sits in Media & Creative, covering Video production, Data pipelines and ETL and Image editing. It works with FFmpeg. The repository describes itself as: Build your agent from 200,000+ skills via skill RETRIEVAL & ORCHESTRATION. The licence is MIT.
Read from SKILL.md and the folder at commit c3cfae1. It shows what the files ask for, not the result of running them.
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.
Ships 8 files in scripts/ (Shell, Python and JavaScript, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
ffmpegmagicknpmbrewapt-getFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Media Processing loads about 817 tokens when it runs, and up to ~19k if it reads all its reference files. Until then it costs about 187 tokens; SKILL.md has 170 words of instructions outside code blocks.
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.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
sudo apt-get install ffmpeg imagemagickAutomated 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); the scripts in this folder are not scanned.
The full file from ynulihao/AgentSkillOS at commit c3cfae1, republished under its MIT licence (© ynulihao). 170 words, ~817 tokens.
.claude/skills/media-processing/SKILL.md (or your agent's skills folder). This skill also uses 21 other files; get the full folder from GitHub.Process video, audio, and images using FFmpeg, ImageMagick, and RMBG CLI tools.
| Task | Tool | Reason |
|---|---|---|
| Video encoding/conversion | FFmpeg | Native codec support, streaming |
| Audio extraction/conversion | FFmpeg | Direct stream manipulation |
| Image resize/effects | ImageMagick | Optimized for still images |
| Background removal | RMBG | AI-powered, local processing |
| Batch images | ImageMagick | mogrify for in-place edits |
| Video thumbnails | FFmpeg | Frame extraction built-in |
| GIF creation | FFmpeg/ImageMagick | FFmpeg for video, ImageMagick for images |
# macOS
brew install ffmpeg imagemagick
npm install -g rmbg-cli
# Ubuntu/Debian
sudo apt-get install ffmpeg imagemagick
npm install -g rmbg-cli
# Verify
ffmpeg -version && magick -version && rmbg --version# Video: Convert/re-encode
ffmpeg -i input.mkv -c copy output.mp4
ffmpeg -i input.avi -c:v libx264 -crf 22 -c:a aac output.mp4
# Video: Extract audio
ffmpeg -i video.mp4 -vn -c:a copy audio.m4a
# Image: Convert/resize
magick input.png output.jpg
magick input.jpg -resize 800x600 output.jpg
# Image: Batch resize
mogrify -resize 800x -quality 85 *.jpg
# Background removal
rmbg input.jpg # Basic (modnet)
rmbg input.jpg -m briaai -o output.png # High quality
rmbg input.jpg -m u2netp -o output.png # FastFFmpeg:
-c:v libx264 - H.264 codec-crf 22 - Quality (0-51, lower=better)-preset slow - Speed/compression balance-c:a aac - Audio codecImageMagick:
800x600 - Fit within (maintains aspect)800x600^ - Fill (may crop)-quality 85 - JPEG quality-strip - Remove metadataRMBG:
-m briaai - High quality model-m u2netp - Fast model-r 4096 - Max resolutionDetailed guides in references/:
ffmpeg-encoding.md - Codecs, quality, hardware accelerationffmpeg-streaming.md - HLS/DASH, live streamingffmpeg-filters.md - Filters, complex filtergraphsimagemagick-editing.md - Effects, transformationsimagemagick-batch.md - Batch processing, parallel opsrmbg-background-removal.md - AI models, CLI usagecommon-workflows.md - Video optimization, responsive images, GIF creationtroubleshooting.md - Error fixes, performance tipsformat-compatibility.md - Format support, codec recommendations© ynulihao, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 21 other files (scripts, references) in data/skill_seeds/media-processing of ynulihao/AgentSkillOS.
Open the folder on GitHubat commit c3cfae1
Media Processing 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Media Processing this skillynulihao/AgentSkillOS | 617 | — | ~817 | Automated safety check: Notes | MIT | |
| Media Processingnicepkg/ai-workflow | 285 | — | ~2.4k | Automated safety check: Notes | MIT | |
| Image To Pnggodot-fun/gai | 181 | — | ~1.1k | Automated safety check: Pass | MIT | |
| API Medianodetool-ai/nodetool | 554 | — | ~1.9k | Automated safety check: Pass | AGPL-3.0 | |
| Ffmpeg Experttheneoai/awesome-skills | 183 | — | ~2.5k | Automated safety check: Pass | MIT | |
| Video To 4kgodot-fun/gai | 181 | — | ~1.2k | Automated safety check: Pass | MIT |
nicepkg/ai-workflow
Video/audio/image processing with FFmpeg and ImageMagick. An agent skill from nicepkg/ai-workflow.
godot-fun/gai
Converts image files to PNG using FFmpeg while preserving dimensions and alpha.
nodetool-ai/nodetool
Call nodetool.media or nodetool.generations from a code action: generate or edit images, video, speech and music with a picked model, transcribe and embed, judge images with a vision model, read a…
theneoai/awesome-skills
Expert FFmpeg command-line user for video/audio processing. An agent skill from theneoai/awesome-skills.
godot-fun/gai
Upscales a single low-resolution video to 4K with Video2X (Real-ESRGAN), then encodes to unified 3840×2160 H.265 Main10 40Mbps + AAC 320kbps MP4.
calesthio/OpenMontage
Understand video content locally using ffmpeg frame extraction and Whisper transcription.
ynulihao/AgentSkillOS
Generate or edit images using AI models (FLUX, Gemini). An agent skill from ynulihao/AgentSkillOS.
ynulihao/AgentSkillOS
Transform data into compelling narratives using visualization, context, and persuasive structure.
ynulihao/AgentSkillOS
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production.
ynulihao/AgentSkillOS
Create employment contracts, offer letters, and HR policy documents following legal best practices.
ynulihao/AgentSkillOS
Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries.
ynulihao/AgentSkillOS
Xiaohongshu (Little Red Book) infographic series generator with multiple style options.
Works with
Categories
Process multimedia files with FFmpeg (video/audio encoding, conversion, streaming, filtering, hardware acceleration), ImageMagick (image manipulation, format conversion, batch processing, effects…. Media Processing is an agent skill from ynulihao/AgentSkillOS. Process multimedia files with FFmpeg (video/audio encoding, conversion, streaming, filtering, hardware acceleration), ImageMagick (image manipulation, format conversion, batch processing, effects, composition), and RMBG (AI-powered background removal).
Media Processing fits situations like: converting media formats; encoding videos with specific codecs (H.264; resizing/cropping images; removing backgrounds from images.
Run `npx skills add ynulihao/AgentSkillOS --skill media-processing -a claude-code`. Or copy the skill folder (data/skill_seeds/media-processing in ynulihao/AgentSkillOS) into .claude/skills/media-processing in your project. Claude Code loads it when a task matches its description.
Run `npx skills add ynulihao/AgentSkillOS --skill media-processing -a codex`. Or copy the skill folder (data/skill_seeds/media-processing in ynulihao/AgentSkillOS) into .agents/skills/media-processing in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ynulihao/AgentSkillOS --skill media-processing -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-processing, .gemini/skills/media-processing, .github/skills/media-processing and .opencode/skills/media-processing in your project.
Going by SKILL.md and its folder, Media Processing needs a shell, Python and JavaScript for the scripts in its folder and the command-line tools its instructions call (ffmpeg, magick, npm, brew and apt-get). Our summary lists: Python 3; Node.js; A Bash shell.
SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (runs commands with sudo), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Media Processing is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 817 tokens (SKILL.md is roughly 3.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 18k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Media Processing: Media Processing (nicepkg/ai-workflow, 285 stars), Image To Png (godot-fun/gai, 181 stars), API Media (nodetool-ai/nodetool, 554 stars) and Ffmpeg Expert (theneoai/awesome-skills, 183 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
ynulihao (a GitHub user) maintains it in ynulihao/AgentSkillOS, which has 617 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on March 7, 2026.
Source: ynulihao/AgentSkillOS on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.