All skills
Verification & Quality Assurance
Scores output truthfulness, checks code quality and rolls back changes that fall below a 0.95 threshold.
- Part of ruvnet/RuView
- AI Engineering · Evals and monitoring
More Evals and monitoring skills
See all- ai-prompt-engineering-safety-review10.5kReviews prompts for safety, bias, security and effectiveness, then suggests concrete improvements.
- agentic-eval10.3kSets up evaluation and self-critique loops to measure and improve AI agent output quality.
- agent-platform-prompt-management10kCreates, versions, retrieves and deletes managed prompts in Agent Platform.
- agent-platform-eval-flywheel9.8kBuilds evaluation datasets and measures AI model and agent quality with repeatable scoring.
Also in this pack
- browser49Automates a web browser and captures AI-friendly page snapshots for agents.
- Pair Programming44Pairs with you on coding in driver, navigator or switch modes, with continuous review, testing and security scanning.
- Skill Builder44Creates new Claude Code skills with correct frontmatter, progressive disclosure and directory layout.
- AgentDB Memory Patterns41Adds persistent memory to agents with AgentDB, covering session memory, long-term storage and context management.