A collection of Claude Code skills for evaluating LLM applications end-to-end: prompts, RAG pipelines, tool calls, and agents. Built for prompt engineers, AI builders, and teams who want a repeatable loop of "edit → eval → see scores → improve" instead of vibes-based iteration.
npx add-skill vukhanhtruong/claude-eval-skillA collection of Claude Code skills for evaluating LLM applications end-to-end: prompts, RAG pipelines, tool calls, and agents. Built for prompt engineers, AI builders, and teams who want a repeatable loop of "edit → eval → see scores → improve" instead of vibes-based iteration.
Source: https://github.com/vukhanhtruong/claude-eval-skill
Pushed: 2026-05-12T10:07:30Z Stars: 0
⚔️ Claude Skill: Virtual AAA gamedev strike team
Opinionated, battle-tested agentic skills for highly productive product-design-engineering teams
🚀 Automate self-healing and root cause analysis for financial services with this Kubernetes-native operator designed to enhance system reliability and resilience.
OpenClaw skill for web-grounded factual answers with citations and sourced images
Improve AI coding assistants by providing accurate Swift concurrency guidance, covering async/await, actors, task groups, and common LLM errors.
ClawGuard security assistant skill for OpenClaw. Reads scan reports, explains findings, analyzes fix impact, and guides remediation.