wangmiaozero/laya-router-skill
laya-router
VerifiedCross-platform local decision routing for AI coding agents using Laya and Laya-MLX. Use for fast task classification, complexity estimation, model escalation hints, tool-use routing, and lightweight risk assessment. Advisory only.
Laya Router
Use this skill when a short structured decision would help route a coding task. Summarize only the task details needed for classification. Never include secrets.
Call python scripts/decide.py "task summary" --json from this skill directory through a local shell tool. The helper uses the private runtime Python when installed. If laya-router is on PATH, laya-router decide "task summary" --json is equivalent. If the optional laya_decide MCP tool is available, it returns the same protocol.
The result is advisory. It can suggest task type, complexity, reasoning depth, tool use, security sensitivity, and risk. It cannot approve commands, deny work, perform a security audit, or replace coding and debugging. Follow the host agent's permission and sandbox policy. If the router returns status=unavailable, continue normal work.
Run laya-router info or python scripts/healthcheck.py to inspect availability without downloading a checkpoint. Model weights load on the first actual decision. Local inference follows the initial checkpoint download. Task text is not persisted by default.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |