All skills
agent-testing
Tests an agent before publishing it, suggesting questions to ask, failures to watch for and fixes to make.
- Part of vstorm-co/agenticos
- AI Engineering · Evals and monitoring
More Evals and monitoring skills
See all- agent-evaluationBuilds an evaluation system for your agent, covering metrics, test environments, rubrics, failure analysis and regression checks.
- agent-prompt-quality-barChecks an agent system prompt against a fixed rubric of contracts, fallbacks and anti-patterns.
- eval-dataset-designDesigns agent evaluation tasks and datasets, including validators, difficulty tiers, leak prevention and long-term upkeep.
- verify-secretsTests whether text marked secret can leak back through replies, errors, traces or written files.
Also in this pack
- abandoned-cart-follow-upWrites a follow-up message that addresses the customer's hesitation instead of repeating the same offer.
- accessibility-reviewChecks a public document or web page against accessibility standards and lists what to fix.
- agent-budgetsSets an agent's monthly spending budget and limits so mistakes stay cheap and busy months don't halt it.
- agent-capabilityAdds or changes what an agent can do, such as a new tool, knowledge source, web search or approval gate.