Media Generation Skills

Media generation skills cover image generation, pixel art, animation, sound, diagrams, presentations, and asset pipelines. Source: Skill Registry, 2026-07-15

When To Use This

Use this family for image generation, image-to-code, sound, diagrams, slides/doc artifacts, pixel/sprite work, Blender/Substance pipelines, and generated visual assets.

Core Model

Executable behavior lives in skills/**/SKILL.md. This page owns family-level routing, tradeoffs, and failure modes. Exhaustive inventory lives in Skill Registry. Full retired article bodies live in Retired Skill Article Ledger.

Concept Position

Axis Value
Family Generated skill-family synthesis
Concept owned Media generation skills cover image generation, pixel art, animation, sound, diagrams, presentations, and asset pipelines.
Operationalizes into Skill Registry, Skill Resolver, executable SKILL.md source
Use this page when choosing the right skill family before loading executable source

Decision Matrix

Need Route
Choose provider/tool by artifact type. Load the named SKILL.md from Skill Registry and use this page for context.
Keep source intent and brand/taste constraints explicit. Load the named SKILL.md from Skill Registry and use this page for context.
Inspect generated artifacts. Load the named SKILL.md from Skill Registry and use this page for context.

Do Not Confuse

  • Frontend implementation belongs in frontend-design-skills.
  • Google Workspace document operations belong in google-workspace-skills.

Tool And Skill Routing

Skill Category Origin Executable source Trigger signal
codex-pet misc personal skills/misc/codex-pet/SKILL.md RunComfy fallback for Codex Pet generation when $imagegen / Codex Pro is unavailable. Uses one RunComfy GPT Image 2 edit from a reference image, then assembles Codex-compatible spritesh...
diagram-to-html misc personal skills/misc/diagram-to-html/SKILL.md Generate publication-quality diagrams and infographics by ideating with AI image generation, then converting to pixel-perfect HTML with custom fonts. Use when the user says "create a diag...
elevenlabs-sfx misc personal skills/misc/elevenlabs-sfx/SKILL.md Use when the user wants to generate sound effects, audio clips, or ambient sounds, or when they say /elevenlabs-sfx or /sfx. Creates MP3 files using the ElevenLabs Text-to-Sound-Effects A...
hatch-pet misc personal skills/misc/hatch-pet/SKILL.md Create, repair, validate, visually QA, and package Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual refe...
illo engineering unknown skills/engineering/illo/SKILL.md Creates original editorial illustrations where a recurring mascot character performs the idea — one caught scene by default, a hand-built explainer diagram (a flow, fan-out, timeline, loo...
remocn engineering unknown skills/engineering/remocn/SKILL.md Build Remotion videos with remocn — a shadcn registry of copy-paste animation components and timeline-driven UI primitives. Use when composing video scenes, adding text animations, transi...
remotion-best-practices engineering unknown skills/engineering/remotion-best-practices/SKILL.md Best practices for Remotion video creation in React. Use when writing, reviewing, debugging, or rendering Remotion code, including compositions, timelines, sequences, transitions, caption...

Failure Modes

  • Using atmosphere instead of inspectable assets.
  • Skipping artifact inspection.
  • Letting generated media override product clarity.

Timeline