Shire31/agent-eval-ops-coach
Portable Codex skill for Langfuse eval ops, experiment runs, attribution, and evidence-backed agent iteration
Portable Codex skill for Langfuse eval ops, experiment runs, attribution, and evidence-backed agent iteration
npx skills add Shire31/agent-eval-ops-coachPortable Codex skill for Langfuse eval ops, experiment runs, attribution, and evidence-backed agent iteration
Yuanli-OS Company Brain v0.1 · Sentra-style memory system as a Claude Code skill: right-time surface + three-circle boundaries + typed edges + anti-hallucination 4-tuple extraction + dual-axis maturity rubric.
Claude skill for tuning a car-audio DSP with REW — portable method (intake → crossovers → phase → EQ → staging → voicing) via a Generator↔Critic↔Arbiter loop. Any car, any DSP.
Universal spec for AI agent tool discipline and instrumentation
Codex AI Coding Agent for Android - Native app with deep system integration
线下健身/瑜伽/普拉提/SPA 连锁经营诊断顾问 Agent Skill：开箱自带行业基准，三阶段交付对标差异表/风险清单/降本测算
Benchmark Claude Code plugins/skills/agents/MCPs by A/B comparing versions with LLM-judged evaluation prompts