tooling & infrastructure
skill creators, installers, marketplaces, and orchestrators — the meta-layer. see creating-skills for how to build your own.
related: creating skills · frameworks · official · resources · productivity
creating skills
- skill-creator — Anthropic's official meta-skill. includes eval framework and description optimizer. see creating-skills.
- Skill Seekers — auto-converts any documentation website into a Claude skill. by @yusufkaraaslan
- claude-code-skill-factory (685 stars) — toolkit for building production-ready skills.
installers & package managers
- antigravity (32.3k stars) — 1,370+ installable skills with CLI installer. works across Claude Code, Codex, Gemini CLI, Cursor.
- CCPI (1.9k stars) — 340 plugins + 1,367 skills with package manager.
- skillshare (1.4k stars) — sync skills across all AI CLI tools with one command.
- open-skills (398 stars) — run Claude Skills locally using any LLM.
marketplaces & directories
start with antigravity (biggest installer, most skills) and OfficialSkills.sh (300k+ monthly views, most traffic). the rest overlap heavily — skip unless you're hunting for something specific.
| marketplace | notes |
|---|---|
| SkillsMP | aggregates from GitHub |
| Claude Marketplaces | 2,400+ skills, 2,500+ marketplaces |
| skills.pawgrammer.com | 280+ free community skills |
| buildwithclaude.com | plugin marketplace |
| claudepluginhub.com | plugin directory |
| AITMPL | 497+ extensions |
| OfficialSkills.sh | 300k+ monthly views |
orchestrators & multi-agent
also see frameworks for development methodologies that use multi-agent patterns.
- claude-squad — manage multiple Claude agents in separate workspaces.
- claude-swarm — agent swarms.
- claude-code-flow — code-first orchestration.
- claude-octopus (2.5k stars) — puts up to 8 AI models on every coding task.
- claude_code_agent_farm (780 stars) — orchestration for 20+ agents in parallel.
memory & context
- claude-mem (48.2k stars) — captures everything Claude does, injects context into future sessions.
- beads (20.6k stars) — memory upgrade for coding agents.
- claude-supermemory (2.5k stars) — persistent memory, tops benchmarks (LongMemEval, LoCoMo, ConvoMem).
- Acontext (3.3k stars) — Agent Skills as a Memory Layer.
- second-brain-skills (664 stars) — turns Claude Code into a Second Brain.
observability
- claude-hud (18.4k stars) — shows context usage, active tools, running agents, todo progress.
- multi-agent-observability (1.4k stars) — real-time monitoring via hook event tracking.