Skip to content

wangmiaozero/laya-router-skill

laya-router

Verified

Cross-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.

FileKindSize
SKILL.mdskill md1.6 KB
agents/openai.yamlconfig219 B
assets/icon.svgother2.9 KB
references/AGENTS.mdmarkdown1.1 KB
references/AGENT_E2E.mdmarkdown8.2 KB
references/ARCHITECTURE.mdmarkdown1.2 KB
references/BACKENDS.mdmarkdown967 B
references/RC_VALIDATION.mdmarkdown5.0 KB
scripts/decide.pyscript561 B
scripts/decide.shexecutablescript64 B
scripts/healthcheck.pyscript3.3 KB
scripts/healthcheck.shexecutablescript69 B
scripts/install.ps1script226 B
scripts/install.pyscript12.3 KB
scripts/install.shexecutablescript65 B
scripts/uninstall.pyscript6.5 KB
scripts/uninstall.shexecutablescript73 B

references/BACKENDS.md

View on GitHub
# Backends

| System | Auto backend | Device |
| --- | --- | --- |
| macOS Apple Silicon | laya-mlx | MLX GPU |
| macOS Intel | laya | PyTorch CPU or MPS when available |
| Windows | laya | PyTorch CPU or CUDA when available |
| Linux | laya | PyTorch CPU or CUDA when available |

`backend=mlx` is rejected outside Apple Silicon. `backend=torch` is available on supported systems. `model=auto` delegates to the official Laya Router; `language=en` and `language=multilingual` pass a language hint. The default lazy load downloads only the selected checkpoint when first used. Checkpoint download requires access to Hugging Face unless weights are cached.

The basic checkpoint may be inaccurate on some zero-shot typed-decision tasks. Scores and confidence are advisory signals, not security verdicts.

Sources: [upstream Laya API](https://github.com/NandhaKishorM/laya/blob/main/README.md), [Laya-MLX API](https://github.com/mizorewww/laya-mlx/blob/main/README.md).
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall