{"skill":{"slug":"startclaw-optimizer","displayName":"StartClaw-Optimizer","summary":"Master optimization system - APPLIES TO EVERY RESPONSE. Before responding, classify task complexity (simple question vs analysis vs coding). Use Haiku for simple/navigation/extraction/status. Use Sonnet ONLY for writing/analysis/planning/debugging. Monitor context size - if >50k tokens, recommend /compact. For automations, use scheduler wrapper. Never load full conversation history for simple tasks. Heartbeats always Haiku, single-line only. Never use Opus. This skill MUST run before every response to prevent 100k+ token bloat.","tags":{"latest":"1.0.2"},"stats":{"comments":2,"downloads":2545,"installsAllTime":7,"installsCurrent":6,"stars":1,"versions":3},"createdAt":1770102708063,"updatedAt":1777524972956},"latestVersion":{"version":"1.0.2","createdAt":1770153020652,"changelog":"- Migrated all major components from Python scripts to modular JavaScript files for better integration and performance.\n- Introduced automatic context compaction with token tracking and summarization at 50,000 tokens.\n- Enhanced task routing logic with intelligent model selection and real-time cost prediction.\n- Improved scheduler with robust preflight/postflight hooks and fault-tolerant execution.\n- Added real-time dashboard for budget, task, and model usage monitoring.\n- Removed legacy scripts and static state files, streamlining the architecture.","license":null},"metadata":null,"owner":{"handle":"idanmann10","userId":"publishers:idanmann10","displayName":"idanmann10","image":"https://avatars.githubusercontent.com/u/166182976?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.llm_suspicious"],"summary":"Detected: suspicious.llm_suspicious","engineVersion":"v2.4.5","updatedAt":1777524972956}}