by luongnv89 · Agent Tool · ★ 949
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
CLI to install and manage agent skills agent-skill-manager () is a scriptable CLI built for AI agents and automation — install, search, audit, and organize skills across Claude Code, Codex, Cursor, and 18 more tools. Every command supports and for non-interactive use. An optional TUI () is available fo
| Stars | 949 |
| Forks | 82 |
| Language | TypeScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 69.6464553784013/100 |
| Open Issues | 18 |
| Last Updated | 2026-10-01 |
| Created | 2026-03-11 |
| Platforms | node |
| Est. Tokens | ~25k |
Looking for a asm alternative? If you're comparing asm with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Costrict - strict AI coder for enterprises, quality first, including AI Agent, AI CodeReview, AI Completion.
🧑🎨 A collection of Golang agentic skills that works
🤖 A comprehensive list of 1,500+ resources and tools related to AI agents.
AI agent tooling for data engineering workflows.
An AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified e
Token conscious database MCP server for Postgres, MySQL, SQL Server, Oracle, MariaDB, SQLite.
Explore other popular agent tool tools:
asm is The universal skill manager for AI coding agents.. It is categorized as a Agent Tool with 949 GitHub stars.
asm is primarily written in TypeScript. It covers topics such as agents, ai, aiagents.
You can find installation instructions and usage details in the asm GitHub repository at github.com/luongnv89/asm. The project has 949 stars and 82 forks, indicating an active community.
asm is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to asm on Agent Skills Hub include costrict, cc-skills-golang, awesome_ai_agents. 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: