Laya — Development skill for Claude Code
Check laya local judge status with a live smoke judgment.
How to install Laya
Installs to ~/.claude/skills/f0rextasy-omp-laya-judge-laya/SKILL.md
mkdir -p ~/.claude/skills/f0rextasy-omp-laya-judge-laya && curl -fsSL https://raw.githubusercontent.com/F0Rextasy/omp-laya-judge/HEAD/commands/laya.md -o ~/.claude/skills/f0rextasy-omp-laya-judge-laya/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Laya does
description: Check laya local judge status with a live smoke judgment.
Report laya-judge status:
- Call the
judge_infotool (mcp__laya-judge__judge_info) and show its exact output (model, device). - Run one live smoke judgment: call
mcp__laya-judge__judgewith state{"message": "You were charged twice, refund please"}and achoicequestion routing to billing/support/security. Show the picked label, confidence, and latency. - Verdict in one line:
● laya active(both calls
Alternatives in Development
- Dario — A local OpenAI- and Anthropic-compatible proxy that brings your Claude Pro/Max subscription to Cursor, Cline 485 ★
- Dashclaw Quality — Recurring find-and-fix quality pass over the whole DashClaw app — browser smoke (frontend-verify) + code gates 297 ★
- Agent Blackbox — Local-first flight recorder for coding agents : replay every run as a live session map, score the context bill 74 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Websearch Status
Read-only health check across all five web search providers — key presence, CLI versions, installed skills. Pa
Audio Compare
Advisory before/after audio judgment — measure → compare → judge two renders and weigh in on a DSP change with
Agent Session Status
Live OpenCode, Claude Code, and Codex session state for Ironbar and Waybar. Provider events are reduced to a s
Smoke Check
Fast MCP tool connectivity check. Tests 10 tools across protoLabs Studio and external integrations, outputs a
Laya Codex
Ranked code retrieval for Claude Code: tree-sitter + BM25 + the Laya re-ranker, delivered through hooks and MC
Laya MCP
A single forward pass answers a set of "typed questions," returning calibrated probabilities alongside a decis
Related Agents
Habit Judge
Read-only verifier that scores a session, a diff, or a transcript against a habit set and returns an evidence-
Laya Scout
Researches the best skills, agents, plugins and MCP servers for a task using local marketplaces, skills.sh, Gi
Ccxt PR Reviewer
End-to-end review of a CCXT pull request. Reads the diff, transpiles and builds in all six languages (TS/JS, P