Skip to main content
skill CX Codex

image-upscaling · 101-skills — Claude Code skill for enlarging images

The image-upscaling skill for Claude Code enlarges and enhances images through inference.sh using belt, for print or high-resolution displays.

no license 246 installs ★ 31 updated 2026-08-31

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add 101-skills/superpowers --skill image-upscaling -a claude-code
Open on GitHub

What image-upscaling does

The skill runs inference.sh apps with belt app run. Its examples use Real-ESRGAN and Topaz Image Upscaler, whose app ID is falai/topaz-image-upscaler. You can process an existing image or generate one with FLUX Klein before enlarging the result.

You need the belt CLI and an authenticated session; run belt login first. The skill's commands will not run without that CLI. Image-processing examples pass an image URL, while the generation workflow writes its result to image.json.

What it helps with

  • enlarge a low-resolution image
  • prepare AI artwork for printing
  • increase the resolution of an old photo
  • make a high-resolution thumbnail

Example prompts for the agent

  • Enlarge this image with an available upscaler.
  • Prepare this picture for printing by increasing its resolution.
  • Generate an image with FLUX Klein, then upscale the result.

How to install image-upscaling

1Skills CLI (Vercel)

npx skills add 101-skills/superpowers --skill image-upscaling -a claude-code

2Manually: put the files in place

~/.claude/skills/image-upscaling/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/image-upscaling/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about image-upscaling

How do I install image-upscaling in Claude Code?

Run npx skills add 101-skills/superpowers --skill image-upscaling -a claude-code. The skill file will be at ~/.claude/skills/image-upscaling/SKILL.md.

What does image-upscaling do?

It runs inference.sh apps through the belt CLI to enlarge and enhance images. The examples include Real-ESRGAN and Topaz Image Upscaler.

What do I need to run image-upscaling?

Install the belt CLI and sign in with belt login before running an app. The image-processing commands take an image URL.

Similar skills

All skills for AI and ML →

image-upscaling by other authors comes first.

image-upscaling eachlabs image-upscaling — a skill for Claude Code, Cursor and other platforms that upscales images 2x to 16x via each::sense. Runs on a prompt with a scale factor and image URL. CX Codex +1 351installs upscale-image pilioai upscale-image upscales images and improves clarity through the Pilio API. Use it when an agent needs to process an image file and wait for the completed task. CX Codex +1 7,600installs image-outpainting prime-skills image-outpainting — a skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode: extends an image beyond its original canvas through the runcomfy CLI, changes aspect ratios, and fills in what the camera missed. CX Codex +1 387,500installs videoagent-image-studio wells The videoagent-image-studio skill provides one-command access to Midjourney, Flux, Ideogram, and five other image models without storing API keys. The agent picks the best model and handles Midjourney's async workflow automatically. CX Codex +1 5,600installs ai-image-prompts-skill YouMind-OpenLab ai-image-prompts-skill — a skill for Claude Code that recommends curated text-to-image prompts paired with preview images. Activates when generating marketing visuals, social banners, or illustrations. CX Codex +1 1,200installs image-prompt social-media-skills Shapes visual briefs for social posts, prevents pointless AI generation, crafts clean natural prompts, and routes requests to the right image engine. CX Codex +1 1,200installs eachlabs-image-generation eachlabs eachlabs-image-generation is a Claude Code skill that creates images from text prompts via the EachLabs Predictions API. It polls for completion and returns the output image URL. CX Codex +1 351installs

From the same set81

The whole set →
ai-social-media-content ai-social-media-content produces multi-platform social media posts, videos, voiceovers, and captions via the belt command-line utility. CX Codex +1 248installs ai-music-generation The ai-music-generation skill lets an agent create music and songs through belt and inference.sh. Use it for background tracks, podcast jingles, game scores, and other audio. CX Codex +1 248installs agent-ui agent-ui is a Claude Code skill that adds a ready-made AI agent interface to React and Next.js, with chat, user approvals, and browser tool calls. CX Codex +1 247installs ai-automation-workflows ai-automation-workflows — a skill that writes automated AI workflows out of belt calls: batches, chained models, cron runs, retries with a fallback model. CX Codex +1 246installs text-to-speech text-to-speech gives the agent ready belt commands for speech synthesis: Kokoro, ElevenLabs, Inworld TTS-2 with emotion steering, and a few more models. CX Codex +1 246installs google-veo Generates videos with Google Veo models via the inference.sh CLI. Useful when creating cinematic clips and timelapses directly from text prompts. CX Codex +1 246installs content-repurposing content-repurposing is a Claude Code skill that reshapes one source into content for different channels. Ask it to adapt a blog post, podcast, or video into another format. CX Codex +1 245installs og-image-design og-image-design builds the image behind a link preview: per-network sizes, text layout rules, and rendering through the inference.sh CLI. CX Codex +1 244installs

Project sponsors

Companies that keep this analytics open