by xnydl · Codex Skill · ★ 54
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
macOS & Windows Codex Desktop 梦幻换肤 Skill｜由世事宜AI免费提供
| Stars | 54 |
| Forks | 2 |
| Language | JavaScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 57.1638194426598/100 |
| Open Issues | 1 |
| Last Updated | 2026-07-17 |
| Created | 2026-07-15 |
| Platforms | codex, node |
| Est. Tokens | ~13k |
Looking for a codex-dream-skin alternative? If you're comparing codex-dream-skin 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.
Named CODEX_HOME profiles and ChatGPT Desktop windows with separate local state, without copying tokens
AI controls your OS. OS AI Computer Use, OS and API agnostic. For now on OpenAI and Anthropic API. Desktop app
发一张图给你的 Codex，它自己给自己换肤 | Send one image to your Codex and it reskins itself. Agent-native skin engine for the
The AI agent that works while you don't watch. Lives in your menu bar, finds you when needed.
Harness-enforced AI business research skill for Claude Code and Codex Desktop
Wraps any OpenAI API interface as Responses with MCPs support so it supports Codex. Adding any missing statefu
Explore other popular codex skill tools:
codex-dream-skin is macOS & Windows Codex Desktop 梦幻换肤 Skill｜由世事宜AI免费提供. It is categorized as a Codex Skill with 54 GitHub stars.
codex-dream-skin is primarily written in JavaScript. It covers topics such as codex, codex-desktop, macos.
You can find installation instructions and usage details in the codex-dream-skin GitHub repository at github.com/xnydl/codex-dream-skin. The project has 54 stars and 2 forks, indicating an active community.
codex-dream-skin is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to codex-dream-skin on Agent Skills Hub include codex-profiles, os-ai-computer-use, codex-autoskin. 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: