Fetches a Jira ticket and starts implementation with a branch and plan. Use when (1) starting work on a Jira ticket, (2) creating a feature branch from a Jira issue, (3) beginning implementation of a story or task, (4) picking up a ticket from the backlog, or (5) user provides a Jira ticket ID to work on.
Cleans up code files by removing dead code, simplifying structure, and eliminating redundancy without changing behavior. Use when (1) cleaning up code after implementation, (2) reducing complexity in a file or function, (3) removing dead code and unused imports, (4) simplifying control flow and expressions, (5) applying modern language idioms to legacy patterns, or (6) improving readability of dense or convoluted code.
Resolve open PR review discussions by evaluating applicability and value, then fixing valid feedback with conventional commits. Use when (1) addressing reviewer feedback on a pull request, (2) resolving open PR discussions systematically, (3) triaging PR review comments for actionability, (4) batch-fixing code review feedback, or (5) cleaning up unresolved PR conversations.
Optimizes markdown documents for token efficiency, clarity, and LLM consumption. Use when (1) a markdown file needs streamlining for use as LLM context, (2) reducing token count in documentation without losing meaning, (3) converting verbose docs into concise reference material, (4) improving structure and scannability of markdown files, or (5) preparing best-practices or knowledge docs for agent consumption.
Convert complex implementation plans into focused, autonomous agent sprints with measurable acceptance criteria. Use when (1) decomposing a large plan into agent-executable chunks, (2) breaking down multi-endpoint migrations or multi-step projects, (3) creating sprint definitions with acceptance criteria for autonomous agents, (4) planning dependency chains across implementation sprints, or (5) structuring work for parallel agent execution.
Analyzes and improves LLM prompts and agent instructions for token efficiency, determinism, and clarity. Use when (1) writing a new system prompt, skill, or CLAUDE.md file, (2) reviewing or improving an existing prompt for clarity and efficiency, (3) diagnosing why a prompt produces inconsistent or unexpected results, (4) converting natural language instructions into imperative LLM directives, or (5) evaluating prompt anti-patterns and suggesting fixes. Applies to all LLM platforms (Claude, GPT, Gemini, Llama).
Write feature specifications that capture requirements and acceptance criteria. Use when (1) writing a new feature spec, (2) documenting functional requirements, (3) defining acceptance criteria for a feature, (4) capturing design goals and constraints for planned work, or (5) structuring a product idea into a formal specification.
Write and review production-ready Kubernetes manifests with security, resource management, and operational best practices. Use when (1) creating new Kubernetes Deployment, Service, or Ingress manifests, (2) reviewing existing manifests for production readiness, (3) adding health probes, security contexts, or resource limits, (4) setting up Kustomize base/overlay structure, (5) containerizing .NET or React apps for Kubernetes, or (6) configuring PodDisruptionBudgets, topology spread, or autoscaling.