by wanghuan9 · MCP Server · ★ 265
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
| Stars | 265 |
| Forks | 4 |
| Category | MCP Server |
| Quality Score | 65/100 |
| Open Issues | 5 |
| Last Updated | 2026-07-09 |
| Created | 2026-05-13 |
| Platforms | claude-code, cli, codex, gemini, mcp |
| Est. Tokens | ~17k |
SkillDock - AI Skills, MCP & Plugins Manager SkillDock is a skills, MCP, and plugin manager for AI coding tools. It helps users install, view, edit, organize, sync, and update skills, MCP servers, and plugin bundles, with Git-aware updates for tracking upstream changes and local modifications. 中文说明 · Download · Install issue? What It Does SkillDock is a desktop control center for AI coding tools.
These tools work well together with skill-manager for enhanced workflows:
Looking for a skill-manager alternative? If you're comparing skill-manager with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
One zero-dependency MCP gateway CLI for every server and agent skill. Token optimization, tool discovery and c
103 ready-to-use AI agent skills for Claude Code, OpenAI Codex, Gemini CLI, Cursor, GitHub Copilot, Windsurf,
One-stop shop for AI skills and agents. Search 110K+ community skills, install and track them declaratively, a
More than a skill manager — manage skills, MCP servers, plugins, hooks, CLIs, configs, memory & rules across e
A collection of AI agent skills for Clawdbot, Claude Code, Codex
The open-source skill registry for AI coding agents. Create, manage, and distribute SKILL.md files across Open
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: