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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.6 KB |
| agents/openai.yaml | config | 219 B |
| assets/icon.svg | other | 2.9 KB |
| references/AGENTS.md | markdown | 1.1 KB |
| references/AGENT_E2E.md | markdown | 8.2 KB |
| references/ARCHITECTURE.md | markdown | 1.2 KB |
| references/BACKENDS.md | markdown | 967 B |
| references/RC_VALIDATION.md | markdown | 5.0 KB |
| scripts/decide.py | script | 561 B |
| scripts/decide.shexecutable | script | 64 B |
| scripts/healthcheck.py | script | 3.3 KB |
| scripts/healthcheck.shexecutable | script | 69 B |
| scripts/install.ps1 | script | 226 B |
| scripts/install.py | script | 12.3 KB |
| scripts/install.shexecutable | script | 65 B |
| scripts/uninstall.py | script | 6.5 KB |
| scripts/uninstall.shexecutable | script | 73 B |
references/AGENTS.md
View on GitHub# Agent integrations
Official discovery paths checked in September 2026:
- Codex CLI and ChatGPT Desktop (Codex): `~/.agents/skills/<name>/SKILL.md`; Codex CLI also supports `codex mcp add`.
- Claude Code: `~/.claude/skills/<name>/SKILL.md`. Its `/laya-router` skill command is an explicit invocation.
- OpenCode: `~/.agents/skills/<name>/SKILL.md` is supported as a compatibility location.
- Pi: `~/.agents/skills/<name>/SKILL.md`; `/skill:laya-router` explicitly loads it when skill commands are enabled.
The installer installs shared skill discovery for Codex, OpenCode, and Pi, and a separate Claude Code link. Only Codex MCP auto-registration is implemented and only if its public CLI is available. Other agents can use the universal CLI; MCP registration for them is manual and depends on the installed agent version.
Sources: [OpenAI Skills](https://learn.chatgpt.com/docs/build-skills), [Claude Code Skills](https://code.claude.com/docs/en/skills), [OpenCode Skills](https://opencode.ai/docs/skills), [Pi Skills](https://github.com/badlogic/pi-mono/blob/main/packages/coding-agent/docs/skills.md).
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: 472k | 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 |