Marked External Downloads · Command Execution · Indirect Prompt Injection
Install
npx -y skills add magentosh/superpowers --skill p-image --agent claude-codeRun in a terminal. Claude loads the skill when a task calls for it. Check the repo's README before you run it.
Files
Install the belt CLI skill:
npx skills add belt-sh/cli
Pruna P-Image Generation
Generate images with Pruna's optimized P-Image models via inference.sh CLI.

Quick Start
Requires inference.sh CLI (
belt). Install instructions
belt login
belt app run pruna/p-image --input '{"prompt": "a futuristic cityscape at sunset"}'
P-Image Models
Pruna optimizes AI models for speed without sacrificing quality.
| Model | App ID | Best For |
|---|---|---|
| P-Image | pruna/p-image |
Fast text-to-image, multiple aspect ratios |
| P-Image-LoRA | pruna/p-image-lora |
Custom styles with preset LoRAs |
| P-Image-Edit | pruna/p-image-edit |
Image editing with multi-image support |
| P-Image-Edit-LoRA | pruna/p-image-edit-lora |
Stylized image editing |
Examples
Text-to-Image
belt app run pruna/p-image --input '{
"prompt": "professional product photo of sneakers, studio lighting",
"aspect_ratio": "1:1"
}'
With LoRA Presets
P-Image-LoRA includes built-in style presets:
belt app run pruna/p-image-lora --input '{
"prompt": "portrait of a woman in golden hour light",
"lora_preset": "photos-realism"
}'
Available presets: photos-realism, pixel-art, japanese-modern-look, cinematic-movie-style, graffiti-splash, neon-punk, anime-2-5d, ethereal-portrait, retro-90s-style, ink-sketchbook, paper-cut
Image Editing
belt app run pruna/p-image-edit --input '{
"prompt": "change the background to a beach",
"images": ["https://your-image.jpg"]
}'
Multi-Image Compositing
belt app run pruna/p-image-edit --input '{
"prompt": "combine these images into a collage",
"images": ["https://img1.jpg", "https://img2.jpg", "https://img3.jpg"]
}'
Custom Aspect Ratios
belt app run pruna/p-image --input '{
"prompt": "landscape mountain scene",
"aspect_ratio": "16:9"
}'
Supported ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, or custom with width/height
Other Pruna Models
Pruna offers optimized versions of popular models:
# FLUX Dev (optimized)
belt app run pruna/flux-dev --input '{"prompt": "..."}'
# FLUX Klein 4B (extremely fast, $0.0001/image)
belt app run pruna/flux-klein-4b --input '{"prompt": "..."}'
# Qwen Image
belt app run pruna/qwen-image --input '{"prompt": "..."}'
# Z-Image Turbo (ultra-fast)
belt app run pruna/z-image-turbo --input '{"prompt": "..."}'
# WAN Image Small (batch generation)
belt app run pruna/wan-image-small --input '{"prompt": "..."}'
Browse All Pruna Apps
belt app list --namespace pruna
Related Skills
# Full platform skill (all apps)
npx skills add inference-sh/skills@infsh-cli
# All image generation models
npx skills add inference-sh/skills@ai-image-generation
# Pruna video generation
npx skills add inference-sh/skills@p-video
# FLUX models
npx skills add inference-sh/skills@flux-image
Browse all apps: belt app list
Documentation
- Running Apps - How to run apps via CLI
- Image Generation Example - Complete image generation guide
- Streaming Results - Real-time progress updates
Facts
- Kind
- Skill
- Repo
- magentosh/superpowers
- Group
- Uncategorized
- Installs
- 6.1k
- Stars
- 2
- 1find-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.3.8M
- 2grill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.3M
- 3grill-with-docsmattpocock/skillsA relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.1.1M
- 4agent-browservercel-labs/agent-browserBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.1.1M
- 5improve-codebase-architecturemattpocock/skillsScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.1.1M
- 6tddmattpocock/skillsTest-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.1.1M