#369369th of 455 in Skills, plugins and prompts
claude-code-apple-skills
Library of 165 Claude Code skills for iOS, macOS and Apple platform apps
- Stars
- 881
- License
- MIT
- Last commit
- Nov 2026
- Language
- Swift
Missed the latest GitHub check; these facts may be older.
Overview
Markdown skill library for Claude Code covering Swift and SwiftUI code generation, code and UI review, testing, App Store optimization, design and legal pages. It installs as a Claude Code plugin that exposes 23 category skills routing to sub-skills, or can be copied into .claude/skills. The skills are plain markdown, so they also load in other agents through the npx skills installer.
Who it is for: Indie developers building iOS, macOS, watchOS or visionOS apps with Claude Code
Strengths
- Covers 165 skills across 23 categories, from Swift concurrency to App Store rejections
- Plugin install loads only 23 short category descriptions into context
- Plain markdown works in Cursor, Windsurf, Codex and Copilot via npx skills
- Era tags mark WWDC content boundaries for pinning and rollback
Weaknesses
- README states content was generated with Claude Code and may contain inaccuracies
- Plugin installs track main with no version pinning; no releases published
- Skills reference each other by path; those links break if only some are installed
- iap-finalizer and privacy-publish need a repo-local asc.py helper the installer skips
What it needs
- no GPU
- Needs Claude Code, App Store Connect API (for iap-finalizer and privacy-publish)
Also in Skills, plugins and prompts
See all 455| Rank | Project | Score |
|---|---|---|
| 1 | claude-memPersistent cross-session memory plugin for Claude Code and other coding agents | 97 out of 100 |
| 2 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 97 out of 100 |
| 3 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 96 out of 100 |
| #4 | rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex | 96 out of 100 |
| #5 | cavemanShortens coding-agent replies and compresses tool output before the model reads it | 95 out of 100 |