smart-model-switching-glm
Auto-route tasks to the cheapest z.ai (GLM) model that works correctly. Three-tier progression: Flash → Standard → Plus/32B. Classify before responding.\nFLASH (default): factual Qu0026A, greetings, reminders, status checks, lookups, simple file ops, heartbeats, casual chat, 1–2
Installation
Pick a client and clone the repository into its skills directory.
Installation
About this skill
Auto-route tasks to the cheapest z.ai (GLM) model that works correctly. Three-tier progression: Flash → Standard → Plus/32B. Classify before responding.\nFLASH (default): factual Qu0026A, greetings, reminders, status checks, lookups, simple file ops, heartbeats, casual chat, 1–2 sentence tasks, cron jobs.\nESCALATE TO STANDARD: code u003e10 lines, analysis, comparisons, planning, reports, multi-step reasoning, tables, long writing u003e3 paragraphs, summarization, research synthesis, most user conversations.\nESCALATE TO PLUS/32B: architecture decisions, complex debugging, multi-file refactoring, strategic planning, nuanced judgment, deep research, critical production decisions.\nRule: If a human needs u003e30 seconds of focused thinking, escalate. If Standard struggles with complexity, go to Plus/32B. Save major API costs by starting cheap and escalating only when needed.
Related skills
skill-creator
by anthropics
last30days
by sickn33
deepwiki-rs
by sopaco
claude-automation-recommender
by anthropics
nano-banana-pro
by garg-aayush
web-artifacts-builder
by anthropics