Screenshots

Create professional App Store and Google Play screenshots with automatic sizing, device frames, marketing copy, and iterative visual learning.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "Screenshots" with this command: npx skills add ivangdavila/screenshots

Quick Reference

ContextFile
Store dimensions and specsspecs.md
Marketing text overlaystext-style.md
Visual templates by categorytemplates.md
Full creation workflowworkflow.md
Learning from feedbackfeedback.md

Memory Storage

User preferences stored at ~/screenshots/memory.md. Read on activation.

Format:

# Screenshots Memory

## Style Preferences
- style: dominant-color | gradient | minimal | dark | light
- fonts: preferred headline fonts
- frames: with-frame | frameless | floating
- tone: punchy | descriptive | minimal

## Learned Patterns
- templates that converted well
- font/size combinations that worked

Create folder on first use: mkdir -p ~/screenshots

Workspace Structure

~/screenshots/
├── memory.md              # Style preferences (persistent)
├── {app-slug}/
│   ├── config.md          # Brand: colors, fonts, style
│   ├── raw/               # Raw simulator/device captures
│   ├── v1/, v2/           # Version exports
│   └── latest -> v2/      # Symlink to current
└── templates/             # Reusable visual templates

Core Workflow

  1. Intake — Get raw screenshots + app icon + brand colors
  2. Size — Generate all required dimensions per specs.md
  3. Style — Apply backgrounds, device frames, text overlays
  4. Review — Use vision to verify quality before sending
  5. Iterate — Adjust based on user feedback
  6. Export — Organize by store/device/language

Quality Checklist

Use vision model to verify EVERY screenshot set:

  • Text readable at thumbnail size?
  • No text in unsafe zones (corners, notch area)?
  • Consistent style across all screenshots?
  • Device frames match the target size?
  • Colors harmonious with app branding?

If ANY check fails → fix before presenting to user.

Versioning Rules

  • Never overwrite — each batch goes in v{n}/
  • Symlink latest to current approved version
  • config.md stores brand decisions for regeneration
  • Compare versions when user says "go back to the old style"

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Coding

Gpu Cluster Manager

Turn your spare GPUs into one inference endpoint. Auto-discovers machines on your network, routes requests to the best available device, learns when your mac...

Registry SourceRecently Updated
Coding

Local Llm Router

Local LLM model router for Llama, Qwen, DeepSeek, Phi, Mistral, and Gemma across multiple devices. Self-hosted local LLM inference routing on macOS, Linux, a...

Registry SourceRecently Updated
Coding

yuhang

一个"制造技能的技能"。这个工具自动化了将任意 GitHub 仓库转换为标准化 Trae 技能的全过程,是扩展 AI Agent 能力的核心工具。

Registry SourceRecently Updated
Coding

Venn Nino

Safely connects Gmail, Calendar, Drive, Atlassian (Jira/Confluence), Notion, GitHub, Salesforce, and dozens of other enterprise tools via a single MCP endpoi...

Registry SourceRecently Updated