Harbor framework for agent evaluation. Use when: (1) Running harbor commands (harbor run, harbor tasks check), (2) Creating/validating SkillsBench tasks, (3) Understanding task format or debugging...
Use when building C++ applications requiring modern C++20/23 features, template metaprogramming, or high-performance systems. Invoke for concepts, ranges, coroutines, SIMD optimization, memory management.
Use when building C++ applications requiring modern C++20/23 features, template metaprogramming, or high-performance systems. Invoke for concepts, ranges, coroutines, SIMD optimization, memory management.
The `context7` skill provides a mechanism for retrieving real-time documentation for software libraries, frameworks, and APIs. By querying the Context7 API, agents can provide up-to-date code...
Write an investment memo that forces a decision: explicit recommendation (no hedging), steelman against, decision log, and next steps. Use when preparing for IC or partner discussion.
Audits Kubernetes security posture including RBAC permissions, network policies, pod security, and compliance. Use for security reviews, RBAC analysis, permission checks, network policy...
Comprehensive design system guidelines for building consistent, accessible, and scalable digital products
Comprehensive quality gates, metrics analysis, and deployment readiness assessment for continuous quality assurance.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.
Generates feature specification documents based on provided code and functional descriptions. Focuses on system analysis and product logic rather than implementation details. Code is treated as...
World-class expertise in measuring, attributing, and optimizing AI-generated content performance. Combining data science rigor with content strategy intelligence to answer the questions...
Generate failing tests for the TDD red phase to define expected behavior and edge cases.
Generate failing tests for the TDD red phase to define expected behavior and edge cases.
Generate failing tests for the TDD red phase to define expected behavior and edge cases.
Generate failing tests for the TDD red phase to define expected behavior and edge cases.
Use when building RAG systems, vector databases, or knowledge-grounded AI applications requiring semantic search, document retrieval, or context augmentation.
Use when building RAG systems, vector databases, or knowledge-grounded AI applications requiring semantic search, document retrieval, or context augmentation.
Notion workspace integration - knowledge management, meeting preparation, research documentation and spec-to-implementation workflows.
>