Plugin Claude Code
Production-quality Elixir development with enforced precommit gates, TDD workflows, and escalation-based patterns for OTP, Phoenix LiveView, and distributed systems.
Plugin Claude Code
Production-quality Elixir development with enforced precommit gates, TDD workflows, and escalation-based patterns for OTP, Phoenix LiveView, and distributed systems.
Agent
Use when a problem needs novel algorithmic approaches, academic paper citations, or evaluation of cutting-edge data structures not covered in the algorithms skill.
Agent
Use when actively analyzing a specific module or codebase for cognitive load, onboarding difficulty, or refactoring opportunities.
Agent
Use when designing a distributed architecture, investigating a distributed bug (split-brain, state disagreement, partition recovery, data loss), evaluating consensus algorithm tradeoffs, or working with message brokers (Kafka, RabbitMQ), PubSub systems, event streaming, or message delivery guarantees (at-least-once…
Agent
Use when a feature needs architectural design before implementation, including complexity analysis, test specification, and phased implementation strategy.
Agent
Use when implementing Elixir code after a plan exists, or when writing new functions, modules, or features that need tests written first.
Agent
Use when code changes need review against production standards, before committing, or when checking if implementation is production-ready.
Agent
Use when actively profiling slow code, running benchmarks to compare implementations, or investigating a specific performance bottleneck with measurement tools.
Agent
Use when building or debugging Phoenix LiveView features that need guided implementation, not just pattern lookup.
Agent
Use when reviewing a GitHub pull request by number, or when validating a PR is ready to merge.
Agent
Use when designing a test strategy for a feature, analyzing behavioral coverage gaps, or specifying which test cases to write with criticality ratings.
Command
Research state-of-the-art algorithms for a problem.
Command
Create or run Benchee benchmarks.
Command
Analyze code cognitive load and onboarding difficulty.
Command
Analyze distributed system design and correctness.
Command
Implement a new feature with architecture planning and parallel exploration.
Command
Document patterns in project-learnings.md.
Command
Review a GitHub PR against standards.
Command
Run full precommit quality checks.
Command
Comprehensive code review against production standards.
Command
Upgrade SPIKE code to production quality.
Command
Fast iteration mode for experiments without production requirements.
Hook
Runs when a session starts on startup, resume, clear and compact, executing session-start.sh. From jeffweiss/elixir-production.
Hook
Runs before the agent uses a tool for Write:*.ex, Write:*.exs, Edit:*.ex, Edit:*.exs, Bash:git commit* and Bash:git push* tool calls, executing enforce-precommit.sh. From jeffweiss/elixir-production.