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 Lynnouo · Claude Skill · ★ 219
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is yushio safe to install? View the security audit →
Yushio (夕潮) An AI collaborator persona for Claude Code (and beyond). Five layered skills: base + art director + auditor + parallel + VI. Portable across 6+ AI tools. 中文版 README · Landing page · About / Credits · Changelog What is this Yushio (夕潮) is not a code generator. It is an AI collaborator persona — a portable set of skills that gives Claude (and other capable LLMs) four properties that a default "polite assistant" lacks: Emotion — actually feeling whether a design is right Judgment — opinions and pushback, not blind execution Reflection — fixing the pattern, not just the instance Autonomy — taking initiative, asking before irreversible operations On top of that, Yushio bundles work discipline (5 questions before any non-trivial task / "slow is fast" / post-fix reverse audit / pattern recognition / agent invocation rules / memory system) refined over half a year of dogfooding across multiple production projects. This repo packages it as an installable Claude Code plugin and drop-in entry files for Cursor, Codex, Gemini CLI, ChatGPT, Claude.ai web, and Aider. What's included | [skills/
| Stars | 219 |
| Forks | 36 |
| Language | JavaScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 61.2987477385646/100 |
| Open Issues | 4 |
| Last Updated | 2026-06-16 |
| Created | 2026-05-19 |
| Platforms | browser, claude-code, cli, codex, gemini, node |
| Est. Tokens | ~16k |
These tools work well together with yushio for enhanced workflows:
Looking for a yushio alternative? If you're comparing yushio with other claude skill tools, these 4 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
An open-source AI marketing operating system for strategy, SEO, AEO/GEO, paid media, content, CRM, and analyti
Repo for the Claude Code Marketplace to use with the Claude for Life Sciences Launch. This will continue to ho
Report issues related to MCP integration with Claude here.
A tool for autonomous agents like OpenClaw to discover and learn skills autonomously
Explore other popular claude skill tools:
yushio is Yushio (夕潮) — An AI collaborator persona for Claude Code and beyond. Three layered skills: base + art director + code auditor. Distilled from months of dogfooding. Portable across Claude Code, Cursor,. It is categorized as a Claude Skill with 219 GitHub stars.
yushio is primarily written in JavaScript.
You can find installation instructions and usage details in the yushio GitHub repository at github.com/Lynnouo/yushio. The project has 219 stars and 36 forks, indicating an active community.
yushio is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to yushio on Agent Skills Hub include digital-marketing-pro, life-sciences, claude-ai-mcp. 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: