calesthioCommunity·149 Agent Skills Included

generative-media-skills

Research-backed image, video, audio, and voice production workflows

Guides media production across 150+ skills covering image, video, music, speech, transcription, motion capture, and avatar providers. Eliminates guesswork on model selection, API contracts, pricing, rights, consent, and licensing for commercial content. Includes executable scripts, hidden evaluation rubrics, and QA checklists so deliverables ship with provenance and legal safety.

123|21

↗

npx skills add calesthio/generative-media-skills --all -g -y

Available:

Directs the agent to follow AGENTS.md and METHODOLOGY.md rules for how each skill package is structured, researched, evidenced, and evaluated before use.

All Skills in This Repository (149)

Pure Emerald Level Indicators

📦 In Repo

calesthio

suno-music

Create and validate Suno music workflows with rights and compliance requirements.

ace-step

Generate and prepare original music with ACE-Step for production workflows.

minimax-music

Generate songs, instrumentals, covers, and soundtrack assets via MiniMax Music APIs.

elevenlabs-music

Plan and generate ElevenLabs Eleven Music assets with prompt safety and QA.

google-lyria

Generate rights-aware music with Google Lyria models and production safeguards.

amazon-transcribe

Convert audio into transcripts and captions using Amazon Transcribe workflows.

elevenlabs-scribe

Transcribe audio and video into time-aligned transcripts with speaker metadata.

assemblyai-transcription

Convert recorded or live speech into timecoded transcripts and captions via AssemblyAI.

nvidia-maxine-audio-effects

Select and validate NVIDIA Maxine audio effects for cleaning speech recordings.

deepmotion-animate-3d

Convert recorded human performance video into 3D character animation.

move-ai-motion-capture

Plan and validate markerless human motion capture workflows with Move AI products.

xai-grok-imagine-image

Generate and edit production images via the Grok Imagine API.

Community

Advanced

Frequently Asked Questions

FAQPage Schema

How to install generative-media-skills?▼

Run `npx skills add calesthio/generative-media-skills --all -g -y` in your terminal to install all skills globally.

What does generative-media-skills cover?▼

It covers 150+ production skills across image, video, music, speech, transcription, motion capture, and avatar providers, plus creative direction, post-production, and delivery governance.

Does it help with AI music licensing and rights?▼

Yes. Provider skills like Suno, ElevenLabs Music, and Google Lyria include dated guidance on commercial rights, copyright limits, disclosure rules, and litigation status.

Which runtimes work with these skills?▼

The skills follow the standard SKILL.md format and work with Claude Code, Codex, Cursor, GitHub Copilot, OpenClaw, and other compatible runtimes.

Can non-developers use these media skills?▼

Yes. Once installed, you describe the deliverable in plain language and the agent applies the right provider knowledge, safety checks, and QA steps.