No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by viticci · Codex Skill · ★ 1.0k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is shortcuts-playground-plugin safe to install? View the security audit →
Shortcuts Playground Create Apple Shortcuts with natural language using Claude Code or Codex. Shortcuts Playground is a plugin for Claude Code and Codex that lets you turn any idea into a shortcut for Apple's Shortcuts app. Describe what you want in plain English; a few minutes later, you get a real, signed file ready to import into the Shortcuts app. Under the hood, shortcuts have always been XML files that get signed and encrypted into a special, Apple-only format. Shortcuts Playground ships a comprehensive knowledge base that teaches Claude and Codex how Shortcuts actions work, what syntax they use, and how they connect to one another. Agents generate the XML, validate it through a loop, and sign it using Apple's native CLI. For macOS 27 Golden Gate, the plugin also ships target-gated ToolKit v78 action coverage plus a reviewed static Apple-derived grounding catalog. That catalog is generated from Apple's local ToolKit/ToolRenderer/WorkflowKit metadata on a maintainer Mac, then packaged as JSON so existing users do not need macOS 27 or private Apple frameworks. The result is a valid shortcut, built from a sentence. A project by Federico Viticci.
| Stars | 1,022 |
| Forks | 47 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 77.2381800480509/100 |
| Open Issues | 4 |
| Last Updated | 2026-06-15 |
| Created | 2026-04-14 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~16k |
These tools work well together with shortcuts-playground-plugin for enhanced workflows:
Looking for a shortcuts-playground-plugin alternative? If you're comparing shortcuts-playground-plugin with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Claude Code skills for Apple platform development (iOS, macOS, iPadOS) — product validation, code generation,
Skills to automate app store deployed and everything related to it using the asc cli
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
AI-powered E2E testing for 10 platforms. 253 MCP tools. Zero config. Works with Claude, Cursor, Windsurf, Copi
A Model Context Protocol (MCP) server that enables LLMs to interact with iOS simulators through natural langua
Excel MCP server: let AI (Claude, Cursor, VS Code) create and edit Excel files with charts, PivotTables, slice
Explore other popular codex skill tools:
shortcuts-playground-plugin is Shortcuts Playground: A Claude Code and Codex plugin for building, validating, signing, and remixing macOS/iOS Shortcuts with natural language.. It is categorized as a Codex Skill with 1.0k GitHub stars.
shortcuts-playground-plugin is primarily written in Python. It covers topics such as apple, automation, claude.
You can find installation instructions and usage details in the shortcuts-playground-plugin GitHub repository at github.com/viticci/shortcuts-playground-plugin. The project has 1.0k stars and 47 forks, indicating an active community.
shortcuts-playground-plugin is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to shortcuts-playground-plugin on Agent Skills Hub include claude-code-apple-skills, app-store-connect-cli-skills, Overture. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: