PDCA quality audit of LLM features: traces, prompts, costs, evals, grounding, hallucination. Use for "audit LLM quality", "check Langfuse", or "audit AI costs". Jailbreaks → audit-llm-security. Cost caps → plan-llm-cost-guardrails.
安装
npx skills add kensaurus/skills --skill audit-langfuse-llmnpx skills add kensaurus/skills --skill audit-langfuse-llm -a claude-code -gnpx skills add kensaurus/skills --skill audit-langfuse-llm -a codex -ggemini skills install https://github.com/kensaurus/skills.git --path skills/audit-langfuse-llmgh skill install kensaurus/skills audit-langfuse-llmgit clone --depth 1 https://github.com/kensaurus/skills /tmp/kensaurus__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/kensaurus__skills/skills/audit-langfuse-llm ~/.claude/skills/audit-langfuse-llm # Claude Code
cp -R /tmp/kensaurus__skills/skills/audit-langfuse-llm ~/.agents/skills/audit-langfuse-llm # Codex, Cursor, Gemini CLI, Copilot, OpenCode