Theme
AI Resources
ASM
ASM, short for agent-skill-manager, is a command-line tool for managing reusable skills across AI coding agents.
It can inventory skills from several agent environments, search a shared catalog, install or remove skill packages, inspect their metadata, check for duplicates, and return structured output for scripts or agents. Use this as a first read, not a recommendation. Open the original project before trusting details like terms, limits, privacy, cost, setup, or safety.
What it is
One inventory across agent tools
ASM discovers skill folders used by Codex, Claude Code, Cursor, Copilot, Gemini CLI, and other supported environments, then exposes them through one CLI and an optional terminal interface.
Why it stands out
Built for scripts as well as people
Commands support JSON output and non-interactive flags, so an agent or automation can search, inspect, install, audit, activate, or remove skills without relying on a visual workflow.
Availability
Local CLI with an open repository
The project is available through npm or its repository, requires Node.js 18 or newer within the supported range, and publishes its code under the MIT license.
Why it matters
What makes it useful
Reusable skills can become scattered when each coding agent keeps its own folder and copy. ASM gives builders one place to see what is installed, find duplicates, search for additions, and carry a more consistent skill setup between supported tools.
What to know
Where it fits
Use it when the problem is organizing and moving skill packages across several coding-agent environments. It manages skill artifacts and catalogs; it is not itself a general AI agent, a guarantee that an imported skill is safe, or a replacement for reviewing what a skill can instruct an agent to do.
Notable points
What stands out
The repository describes support for 19 agent providers and a catalog containing more than 4,300 skills. Those counts can change as providers and indexed repositories are added or removed, so the current project materials remain the better place to confirm coverage.
Before using
What to review
Review a skill and its source before installing it, especially when its instructions can run shell commands, reach the network, read credentials, or modify project files.
Check which global and project skill folders ASM will discover or change for each enabled provider before using install, uninstall, audit, link, or activation commands.
Treat the built-in security scan as one review layer rather than a safety guarantee; inspect warnings, dependencies, source commits, and the final installed files yourself.
Confirm the supported Node.js and npm versions, Git access, private-repository authentication, and any symlink restrictions in the environment where it will run.
Reader fit
Who may find it relevant
Builders who use more than one skills-aware coding agent and want one inventory of their installed skill packages.
People automating skill discovery or installation through JSON and non-interactive commands.
Skill authors who want scaffolding, local linking, evaluation, bundles, and a registry publishing path in one tool.
Less relevant for someone using one small static skill folder with no need for catalog, audit, or cross-agent management.
Editorial note
Why LifeHubber lists it
LifeHubber lists ASM because it addresses a practical portability problem: the same reusable skill can otherwise be copied into several hidden agent folders and drift into different versions. Its shared inventory, structured commands, duplicate checks, and install paths help readers decide whether one local manager would make a multi-agent setup easier to understand and maintain.
Source links
Source materials
Reader note
Before relying on this entry
LifeHubber lists entries to help readers inspect AI projects, not to endorse them or prove they are safe, suitable, accurate, maintained, or right for a specific use. We do not verify every entry in depth. Before relying on anything listed, review the original materials, terms, privacy practices, limits, and risks that matter for your situation.
What to explore next
Compare management with deeper skill review.
ASM organizes skill packages across agent tools. These next steps cover task-history evidence and a separate inspection layer before a skill is trusted with real work.
More in AI Agents
Keep browsing this category
Explore more AI agent projects.
Agent-Reach
Panniantong/Agent-Reach
A CLI routing layer that helps command-capable agents reach web, social, repository, video, RSS, and search sources through ordered backends. For multi-backend channels, its doctor command reports the active backend, while default setup only checks the machine unless system changes are explicitly authorized.
AIPOCH Medical Research Skills
aipoch/medical-research-skills
A curated library of medical research agent skills designed to support evidence review, protocol design, data analysis, and academic writing workflows.
Claude Code Game Studios
Donchitos/Claude-Code-Game-Studios
A multi-agent game-development studio system for Claude Code, organized around specialized agents, workflow skills, hooks, rules, and templates.
