StackMap
Subscribe

asm vs skillkit

Scriptable skill manager for AI coding agents — install, search, dedupe-audit and security-scan skills across 19 providers, with --json/--yes on every command so agents and CI can drive it. — versus — Package manager for AI agent skills — install from 400K+ skills across 31 sources, auto-translate between 46 agents' incompatible formats, security-scan on install, sync to every agent at once.

The curated verdict

Same job — install and manage skills across many coding agents — opposite bets: skillkit maximizes breadth (400K skills, 46 agents, format auto-translation); asm maximizes scriptability (agent-first --json/--yes CLI, dedupe audit, curated catalog, no accounts/telemetry).

asmskillkit
Stars7301.4k
Forks61127
LanguageTypeScriptTypeScript
LicenseMITApache-2.0
Last activity6 days ago1 months ago
Topicscoding, skillscoding, skills
Curated connections511

asm — the curator's take

Pick it when the CLI consumer is a machine: every command is non-interactive and JSON-emitting, so your agent or CI pipeline can inventory, install, and dedupe skills without a human — that plus `asm audit` (finds duplicate/stale skills scattered across 19 providers' hidden dirs) is the differentiator. NOT the breadth play: ~4.3K curated skills vs skillkit's 400K firehose, and no format translation between agent dialects. Solo-maintainer project — fine for personal/team tooling, but if you need org-level reproducibility and governance, apm's manifest+policy model is the grown-up answer.

skillkit — the curator's take

Use it the moment skills must live on more than one agent — you write Claude SKILL.md, a teammate runs Cursor: author once, `skillkit sync` translates and deploys everywhere; the install-time security scan is a real feature now that skill marketplaces are a prompt-injection vector. NOT needed if you're all-in on a single agent — Claude Code's first-party plugin/marketplace flow is simpler and better supported. Format translation is lossy at the edges (agent-specific frontmatter, hooks, tool references), so verify ported skills actually trigger; and treat the optional mesh/messaging/REST extras as experiments, not infrastructure.