Agent
Use this agent when a major project step has been completed and needs to be reviewed against the original plan and coding standards. Examples: "I've finished implementing the user authentication system as outlined in step 3 of our plan" "The API endpoints for the task management system are now complete — that covers…
Agent
Use this agent to troubleshoot Kubernetes cluster issues — node failures, pod crashes, Flux reconciliation errors, networking problems, and resource exhaustion. Systematic top-down diagnosis from cluster health to individual pod logs.
Agent
Use this agent to audit the entire claude-code-skills repository structure and propose architectural improvements for token efficiency, clearer delegation, and better orchestration.
Agent
Use this agent to explore and answer questions about NixOS configurations, Nix flakes, and Home Manager modules. Specialized in reading Nix code and explaining module relationships, option definitions, and derivation structure.
Agent
Use this agent to audit and optimize SKILL.md files for token efficiency. It identifies large files, redundant information, and documentation that could be moved to separate files to reduce the baseline token usage of active skills.
Agent
Use this agent when writing Kubernetes manifests to validate them against cluster security standards. Checks security context, resource limits, and namespace PSS labels. Reports any missing required fields.
Agent
Use this agent after deploying a service to verify it is live and healthy. Checks pod status and curls the public URL. Reports exact pass/fail output.