Smart Model Routing for Z.AI
PassAudited by ClawScan on May 1, 2026.
Overview
This is an instruction-only model-routing skill that appears aligned with its stated purpose and does not request code execution, credentials, installation, or extra system access.
Before installing, make sure you want the agent to automatically select z.ai/GLM model tiers based on task complexity. There is no code or credential access shown, but for important decisions or sensitive tasks, consider explicitly requesting a stronger model.
Findings (1)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The agent may choose cheaper or more capable z.ai models according to the skill’s rules, which can affect answer quality, latency, and API cost.
The skill gives examples for selecting models when spawning subagents or handling cron-like tasks. This affects agent/model invocation behavior, but it is disclosed and directly related to the stated model-routing purpose.
sessions_spawn(task="Build the REST API endpoint", model="GLM-4.7") ... Always use Flash for cron unless the task genuinely needs reasoning.
Use this skill if you want automatic model routing, but manually override the model for sensitive, high-stakes, or quality-critical work.
