{"skill":{"slug":"swarma","displayName":"swarma - growth loops","summary":"Agent teams that run growth experiments and build their own playbook. GROWS loop: generate hypothesis, run experiment, observe signal, weigh verdict, stack p...","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":93,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1774800753854,"updatedAt":1774801014426},"latestVersion":{"version":"1.0.0","createdAt":1774800753854,"changelog":"- Initial release of the \"swarma\" skill for growth experiment automation with agent teams.\n- Implements the GROWS loop (Generate hypothesis, Run experiment, Observe signal, Weigh verdict, Stack playbook) for continuous learning and optimization.\n- Provides 18 pre-built squad templates covering all AARRR funnel stages.\n- Includes a comprehensive CLI with commands for setup, team management, experiment cycles, metrics logging, and status checks.\n- Supports integration with Claude Code, Hermes, OpenClaw, and standalone CLI environments.\n- Requires OPENROUTER_API_KEY for LLM-powered agent cycles.","license":"MIT-0"},"metadata":null,"owner":{"handle":"glitch-rabin","userId":"s176ab43rq3v1cjj57w6zgcyt583vdsy","displayName":"glitch-rabin","image":"https://avatars.githubusercontent.com/u/112572952?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.llm_suspicious"],"summary":"Detected: suspicious.llm_suspicious","engineVersion":"v2.2.0","updatedAt":1774801014426}}