shortcuts-playground

shortcuts-playground is a skill for Claude Code from viticci/shortcuts-playground-plugin. It costs 81 tokens per session (10,826 once invoked), scanned A, original, MIT.

A tool for creating and modifying Apple Shortcuts files, which automate actions on macOS and iOS. It works with both new shortcuts and existing shortcut files.

In plain words
What is it for?
Building shortcuts from descriptions, making targeted changes, validating files, and preparing them for import into Apple's Shortcuts app.
Why use it?
It avoids manually editing complex shortcut data and helps preserve parts of an existing shortcut that should not change.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claude plugin — 1 skill, 2 commands, 2 agents, 1 hook shipped together

Good fit Building shortcuts from descriptions, making targeted changes, validating files, and preparing them for import into Apple's Shortcuts app.

Compare 6 skills from other repositories ↓
About the project

viticci/shortcuts-playground-plugin is a Claude Code and Codex plugin that turns natural-language descriptions into signed Apple Shortcuts files for macOS and iOS. It helps users build, validate, and remix shortcuts by generating their XML and signing it with Apple’s shortcuts command-line tool. The catalogue entries are the plugin’s own agents, commands, skill, and hook.

viticci/shortcuts-playground-plugin · 1,092 stars · on GitHub · macstories.net

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add viticci/shortcuts-playground-plugin
Claude Code
/plugin install claude

Made for: Claude Code.

Or install claude, the plugin that ships this one along with the rest of its 1 skill, 2 commands, 2 agents, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for shortcuts-playground

README.md
[![agentmods](https://agentmods.dev/badge/skills/viticci/shortcuts-playground-plugin/shortcuts-playground/github.svg)](https://agentmods.dev/skills/viticci/shortcuts-playground-plugin/shortcuts-playground)
Your own site
<a href="https://agentmods.dev/skills/viticci/shortcuts-playground-plugin/shortcuts-playground"><img src="https://agentmods.dev/badge/skills/viticci/shortcuts-playground-plugin/shortcuts-playground/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for shortcuts-playground

Your own site · 80×15
<a href="https://agentmods.dev/skills/viticci/shortcuts-playground-plugin/shortcuts-playground"><img src="https://agentmods.dev/badge/skills/viticci/shortcuts-playground-plugin/shortcuts-playground.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 10,826 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00081 $0.10826
Opus 5 $0.00041 $0.05413
Sonnet 5 $0.00016 $0.02165
Haiku 4.5 $0.00008 $0.01083

Measured 12d ago against content hash 7093f7ca8b5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

shortcuts-playground scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (scripts/generate_healthkit_reference.py, scripts/lookup_action_grounding.py, scripts/select_shortcut_icon_color.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

claude/skills/shortcuts-playground/SKILL.md · 467 lines

How it starts

The opening of the file, as written. The whole thing — 467 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shortcuts Playground

Generate valid .shortcut files that can be signed and imported into Apple's Shortcuts app. The plugin supports two workflows — building new shortcuts from scratch AND remixing existing XML shortcuts with a natural-language diff.

Two slash commands / two specialized agents:

Command Agent Purpose
/shortcuts-playground:build <brief> shortcut-builder Create a new shortcut from scratch based on a natural-language brief.
/shortcuts-playground:remix <path-to-xml> <idea> shortcut-remixer Apply a surgical diff to an existing unsigned .xml shortcut. Preserves UUIDs, icon, metadata, and every action the user didn't ask to touch.

Both commands share the same skill docs, the same validator, the same PostToolUse auto-validation hook, and the same sign-shortcut archive-and-sign pipeline. The only difference is the starting point (empty plist vs. an existing source XML).

Plugin-provided commands. When this skill is active, three wrapper commands are on the Bash PATH:

Command Purpose
resolve-icon Pick a Shortcuts glyph + color from a natural-language prompt (required step 5 in the build workflow; skipped for remixes, which preserve the source icon).
validate-shortcut Run the Craig Loop preflight validator against a .xml/.shortcut file.
sign-shortcut Archive the unsigned XML, sign with shortcuts sign, and write the final .shortcut to the configured output directory.

Prefer these wrappers over calling the underlying python3 scripts/*.py files directly — they work from any working directory and respect plugin configuration.

Auto-validation hook. A PostToolUse hook fires on every Write/Edit that produces a Shortcuts plist file and runs validate-shortcut automatically. Do not skip the Craig Loop when the hook reports errors — it already ran the validator for you, so read the errors and fix them before retrying. The hook applies to BOTH the builder and the remixer; neither agent needs to invoke validate-shortcut manually for edits it just made.

Mandatory: Follow the guidelines in BEST_PRACTICES.md for every shortcut. If guidance here conflicts with BEST_PRACTICES.md, follow BEST_PRACTICES.md.

Definition of done: a new build is not complete when XML validation passes. It is complete only after sign-shortcut archives the unsigned XML, writes the signed .shortcut, and you verify the signed file exists with non-zero size.

Pipeline-first rule: write the smallest complete shortcut that implements the request, validate it, sign it, and verify the signed file before spending turns on cosmetic polish. Comments only need to be concise and repair-oriented. A valid XML draft without a signed .shortcut is not a useful stopping point.

Read the full file on GitHub · 467 lines

Files

What ships with it

59 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 467 lines · 81 tokens per session scan A 7093f7ca8b5e

Subscribe to this mod's changes

shortcuts-playground is a skill published in the GitHub repository viticci/shortcuts-playground-plugin (1,092 stars, last pushed 2mo ago), licensed MIT. It adds 81 tokens to every session and 10,826 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

Apple Shortcuts Integration

Create and trigger Apple Shortcuts for iOS/macOS automation and cross-platform workflows.

claude-office-skills/skills · 21 tokens

swiftui-coding-guideline

SwiftUI coding guidelines covering style, structure, patterns, formatting, and pure-functions methodology. Use when editing or generating SwiftUI code or Swift files containing SwiftUI views, view models, services, or related architecture.

JordanCoin/ios-skills-collection · 50 tokens

asc-revenuecat-catalog-sync

Reconcile App Store Connect subscriptions and in-app purchases with RevenueCat products, entitlements, offerings, and packages using asc and RevenueCat MCP. Use when setting up or syncing subscription catalogs across ASC and RevenueCat.

rorkai/app-store-connect-cli-skills · 51 tokens

asc-localize-metadata

Automatically translate and sync App Store metadata (description, keywords, what's new, subtitle) to multiple languages using LLM translation and asc CLI. Use when asked to localize an app's App Store listing, translate app descriptions, or add new languages to App Store Connect.

rorkai/app-store-connect-cli-skills · 60 tokens

asc-shots-pipeline

Orchestrate iOS screenshot automation with xcodebuild/simctl for build-run, AXe for UI actions, JSON settings and plan files, Koubou-based framing (asc screenshots frame), and screenshot upload (asc screenshots upload). Use when users ask for automated screenshot capture, AXe-driven simulator flows, frame composition…

rorkai/app-store-connect-cli-skills · 79 tokens

asc-metadata-sync

Sync, validate, and apply App Store metadata with the current asc canonical metadata workflow. Use when updating metadata, localizations, keywords, or migrating legacy fastlane metadata.

rorkai/app-store-connect-cli-skills · 39 tokens