Media asset tools

Skill percymcn/agent-cookbook/skills/media/media-asset-tools

Production-ready AI agent skills, playbooks, and workflows from the pharma6 automation lab

Install

npx -y skills add percymcn/agent-cookbook --skill media-asset-tools

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Media asset tools umbrella: GIF search/download, AI song/music generation prompts, HeartMuLa generation, audio feature/spectrogram analysis, and lightweight media utilities. Use for small media assets and audio/music workflows that do not require the full video-production or YouTube pipelines.

SKILL.md

2.1 KB, 388 tokens by cl100k_base, as published. Nobody here has run it

Media Asset Tools

Use this umbrella for small media and audio/music tasks. Keep full video production and YouTube monitoring pipelines separate when their dedicated project-specific package is needed.

GIF search

Use Tenor-style search/download flows when the user wants a reaction GIF or animated media asset. Search first, pick a relevant result, download if needed, and deliver as native media when the target platform supports it.

Typical pattern:

curl -s "https://tenor.googleapis.com/v2/search?q=<query>&key=$TENOR_API_KEY&limit=10" | jq

Songwriting and AI music prompts

For songs, separate craft from generation:

Clarify genre, mood, tempo, language, singer perspective, and structure.
Draft lyrics with sections ([Verse], [Pre-Chorus], [Chorus], [Bridge]).
Provide compact model tags/style prompts for Suno-like generators.
Avoid overstuffed tags; prioritize the musical identity and vocal direction.

HeartMuLa generation

Use HeartMuLa when the task is direct song/audio generation from lyrics and tags. Verify provider credentials/tool availability before promising generated output. Save returned media and deliver with MEDIA:/path when local.

Audio feature analysis via SongSee

Use SongSee-style spectrogram/feature tools for mel, chroma, MFCC, or audio visualization tasks. Prefer concrete outputs: image files, feature summaries, or CSV/JSON artifacts.

AudioCraft

Use AudioCraft/MusicGen/AudioGen patterns when generating music or sound effects locally from text prompts. Check model availability and hardware constraints before running heavy inference.

Reporting

For media work, report:

Source or generation tool used.
Output file path/URL.
Any licensing or attribution concerns.
Whether output was verified by opening/analyzing/listing the file.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.