← Back to Skills Marketplace
ivangdavila

Screenshots

by Iván · GitHub ↗ · v1.0.1
linuxdarwinwin32 ⚠ suspicious
838
Downloads
3
Stars
4
Active Installs
2
Versions
Install in OpenClaw
/install screenshots
Description
Create professional App Store and Google Play screenshots with automatic sizing, device frames, marketing copy, and iterative visual learning.
Usage Guidance
This skill is internally consistent and does what it says: it will create a ~/screenshots folder, read/write memory.md and learnings.md, and keep versioned exports. It does not request API keys or install software. Before installing: (1) confirm you’re comfortable with a skill writing persistent files under ~/screenshots and avoid putting secrets or sensitive screenshots there; (2) review the created files after first run and set filesystem permissions if desired; (3) if you don't want the agent to act autonomously with this persistent data, keep autonomous invocation disabled at the agent/platform level. If you need more assurance, ask the skill author for a minimal manifest that restricts paths or for an option to store data in a temporary/project-only folder.
Capability Analysis
Type: OpenClaw Skill Name: screenshots Version: 1.0.1 The skill bundle is classified as suspicious due to direct instructions for shell command execution and file system operations within `workflow.md` and `SKILL.md`. Specifically, `workflow.md` instructs the agent to run `xcrun simctl io booted screenshot` and `mkdir -p ~/screenshots/{app-slug}/raw`, and `cd ~/screenshots/{app-slug}`. While these commands are relevant to the skill's stated purpose, the use of variables like `{app-slug}` in shell commands without explicit sanitization instructions creates a significant shell injection vulnerability risk (potential RCE) if the agent's execution environment does not properly sanitize user-controlled inputs.
Capability Assessment
Purpose & Capability
Name/description (app-store screenshots, templates, iterative learning) match the instructions and files. The SKILL.md and supporting docs only describe image sizing, templates, workflows and storing templates/preferences — nothing requests unrelated platform access or credentials.
Instruction Scope
Instructions tell the agent to read/write files under ~/screenshots (memory.md, learnings.md, project config, versioned exports) and to use a vision model to verify screenshots. These file operations are coherent with the skill's purpose but grant the skill persistent access to a folder in the user's home directory; the skill also references optional local commands (e.g., xcrun simctl) as recommendations even though binaries are not declared as required.
Install Mechanism
No install spec or code is provided — this is instruction-only, so nothing is written to disk by an installer and no external packages/URLs are pulled. That minimizes install-time risk.
Credentials
The skill requires no environment variables, binaries, or external credentials (proportional). However it persists per-user learnings and preferences in the home folder which may include user-identifying notes; users should avoid storing secrets in those files.
Persistence & Privilege
The skill explicitly creates and uses persistent storage at ~/screenshots (memory.md, learnings.md, versioned exports and symlinks). always:false and it does not modify other skills. Persistent storage is reasonable for this workflow but is a persistent presence in the user's home directory and may accumulate personal data over time.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install screenshots
  3. After installation, invoke the skill by name or use /screenshots
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Preferences now persist across skill updates
v1.0.0
Initial release
Metadata
Slug screenshots
Version 1.0.1
License
All-time Installs 4
Active Installs 4
Total Versions 2
Frequently Asked Questions

What is Screenshots?

Create professional App Store and Google Play screenshots with automatic sizing, device frames, marketing copy, and iterative visual learning. It is an AI Agent Skill for Claude Code / OpenClaw, with 838 downloads so far.

How do I install Screenshots?

Run "/install screenshots" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Screenshots free?

Yes, Screenshots is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Screenshots support?

Screenshots is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux, darwin, win32).

Who created Screenshots?

It is built and maintained by Iván (@ivangdavila); the current version is v1.0.1.

💬 Comments