#377377th of 389 in Skills, plugins and prompts
skills
Codex skill folders for Apple development, review swarms, and refactors
- Stars
- 4k
- License
- MIT
- Last commit
- Mar 2026
- Language
- Shell
3,283 on 21 Apr 20264,027 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A collection of 16 self-contained skills, each a folder with a SKILL.md, installed under $CODEX_HOME/skills. They cover SwiftUI and Swift concurrency work, macOS app packaging, iOS simulator debugging via XcodeBuildMCP, GitHub tasks through the gh CLI, and React performance diagnosis. Two skills run four-agent read-only swarms for diff review and bug investigation.
Who it is for: Codex users building Apple-platform apps who want reusable skills
Strengths
- Each skill is a self-contained folder with its own SKILL.md
- Deep Apple coverage: SwiftUI, Liquid Glass, Swift 6.2 concurrency, SwiftPM packaging
- Review and bug-hunt swarms split read-only work across four focused agents
- MIT licensed plain files, so single skills can be copied on their own
Weaknesses
- README documents install only for Codex; other agents are not mentioned
- Weighted toward Apple platforms; only one React skill
- No tagged releases, so versions cannot be pinned
- iOS debugger skill needs XcodeBuildMCP set up separately
What it needs
- no GPU
- Needs Codex, gh CLI, XcodeBuildMCP, Tuist
Quick answers
Is skills open source?
Yes. Its code is on GitHub under the MIT license.
Also in Skills, plugins and prompts
See all 389| 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 |