StartClaw-Optimizer

Intelligently compresses and optimizes context to reduce token usage by 40-60%, using deduplication, pruning, summarization, and adaptive learning.

Auto-route tasks to the cheapest Claude model that works correctly. Three-tier progression: Haiku → Sonnet → Opus. Classify before responding. HAIKU (default): factual Q&A, greetings, reminders, status checks, lookups, simple file ops, heartbeats, casual chat, 1-2 sentence tasks. ESCALATE TO SONNET: code >10 lines, analysis, comparisons, planning, reports, multi-step reasoning, tables, long writing >3 paragraphs, summarization, research synthesis, most user conversations. ESCALATE TO OPUS: archi

Analyzes AI conversation logs to evaluate skill performance and generate optimization suggestions. Use when user mentions "优化技能", "迭代技能", "skill optimization...

Design and build OpenClaw skills. Use when asked to "make/build/craft a skill", extract ad-hoc functionality into a skill, or package scripts/instructions for reuse. Covers OpenClaw-specific integration (tool calling, memory, message routing, cron, canvas, nodes) and ClawHub publishing.

Reduce OpenClaw AI costs by 97%. Haiku model routing, free Ollama heartbeats, prompt caching, and budget controls. Go from $1,500/month to $50/month in 5 min...

Automatically analyze and reduce OpenClaw token waste through context compression, tool-call deduplication insights, model selection guidance, and session hygiene checks. Use when sessions are nearing context limits, costs are climbing, or you want proactive token optimization before expensive tasks.