skillkitPackage 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.
Why switchOverlapping job, different model: skillkit is an imperative installer + format translator chasing breadth (46 agents, 400K skills); apm is declarative — manifest, lockfile, transitive deps, org policy — chasing reproducibility. apm's README even ships a 'coming from npx skills add' migration.
Full comparison → teamai-cliTencent's team-level agent config manager: skills, rules, agents, hooks, MCP and env live in a shared git repo and sync into Claude Code, Codex, Cursor, CodeBuddy, OpenCode and more on every session.
Why switchBoth declare and install skills, prompts, MCP servers and hooks into multiple coding agents from a versioned manifest; apm is a per-project dependency manager, teamai is a team-wide sync with push/pull against a shared repo.
Full comparison → asmScriptable 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.
Why switchBoth manage agent skills across tools, at different layers: asm is an imperative, machine-driven CLI for installing and auditing skills on one workstation; apm is a declarative project manifest — apm.yml + lockfile ships with the repo so the whole team reproduces the same agent context.
Full comparison → ECCCross-harness 'operating system' for coding agents — 268 skills, 66 agents, hooks, rules, memory persistence, instinct-based continuous learning and AgentShield security scanning. MIT.
Why switchBoth ship reproducible agent-context setups across many clients. apm is a lean dependency manager (declare skills/prompts/MCP in apm.yml, lockfile-pinned installs); ECC ships the content itself — a batteries-included catalog of skills, agents, hooks and rules.
Full comparison →