by asgard-ai-platform · MCP Server · ★ 245
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Featured in: Claude Code Skills · Knowledge Base & RAG
None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 245 |
| Forks | 30 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 58/100 |
| Last Updated | 2026-06-06 |
| Created | 2026-04-07 |
| Platforms | claude-code, mcp, python |
| Est. Tokens | ~282k |
Asgard Skills 開源的 301 個 coding agent skills 知識庫,分成 22 個主題類別。每個 skill 都是獨立的 Markdown 檔案(),遵循 Claude Agent Skills 規範,部分附帶純 Python 腳本做確定性計算。 English 概觀 本 repo 是 Asgard AI Platform 的原料庫。Skills 會與 Asgard MCPs 組合,打包成針對特定使用者情境的 coding agent plugins(例如台股分析師、電商營運、政策研究者)。 每個 skill 封裝的是某個明確任務的方法論 + 判斷 + 陷阱——那些 LLM agent 若沒有提示就會重新摸索、或直接做錯的東西。 Repo 結構 類別(22 個前綴,301 個 skills) 設計 / UX 方法論
These tools work well together with skills for enhanced workflows:
Looking for a skills alternative? If you're comparing skills 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.
The Ultimate Claude Code Toolkit: 183 skills, 10 agents, 29 commands, 7 hooks, and 86 marketplace repos (11,30
Persistent memory for AI coding agents
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
Just another desktop client for OpenCode 2. Manage projects, sessions, parallel agents, requests, and changes
Polymcp provides a simple and efficient way to interact with MCP servers using custom agents
Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 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: