agentctl

Use when researching state-of-the-art algorithms for a problem, finding academic papers, comparing algorithm approaches, needing paper citations, or user invokes /algorithm-research

Use when researching algorithms, data structures, optimization, performance, or need modern alternatives to classic algorithms

Use when creating benchmarks, measuring performance, comparing implementations, or user invokes /benchmark. Provides step-by-step workflow for benchmark creation, data generation, and results interpretation.

Use when analyzing code cognitive load, onboarding difficulty, or user invokes /cognitive-audit for complexity analysis and refactoring recommendations

Use when analyzing cognitive load, code complexity, onboarding difficulty, readability concerns, maintainability issues, or applying Ousterhout principles for deep modules, reducing complexity, and strategic programming approaches

Use when implementing concurrent operations, choosing between concurrency models, designing async workflows, or working with parallel data processing

Use when validating input data, implementing parse-don't-validate patterns, designing validation pipelines, or handling external data safely

Use when reviewing distributed system code, checking for distributed bugs (split-brain, quorum errors, clock drift), or user invokes /distributed-review

Use when working with distributed systems, clustering, consensus algorithms, network partitions, CAP tradeoffs, or multi-language distributed patterns

Use when organizing code by business domain, designing bounded contexts, creating aggregate roots, or establishing clear module boundaries

Elixir-specific language patterns including pattern matching, immutability, protocols, behaviours, and macros

Use when implementing error handling strategies, choosing between exceptions and result types, designing error propagation patterns, or implementing railway-oriented programming

Use when implementing new features, adding functionality, building new capabilities, or when user invokes /feature. Provides guided TDD workflow with architecture planning, parallel codebase exploration, and multi-lens review.

Canonical language detection logic and reference paths. Load this skill when you need to detect project language or find language-specific resources.

Use when documenting project-specific patterns, capturing gotchas, recording architectural decisions, or building a project knowledge base in project-learnings.md

Use when analyzing performance issues, creating benchmarks, or optimizing code

Diagnose pi chain and subagent failures. Use when a chain stalled, looped, or produced unexpected results.

Use when reviewing GitHub pull requests, checking PR quality, analyzing PR changes, or user invokes /pr-review

Use when running quality checks before commits, validating code passes compilation/formatting/linting/tests, or when user invokes /precommit

Use when preparing for production deployment, conducting code reviews, setting up precommit workflows, adding type annotations, implementing testing strategies, addressing security concerns, or ensuring documentation quality and best practices across any language

Use when conducting comprehensive code reviews, checking code quality against production standards, analyzing files for issues and project convention violations

Rust-specific language patterns including ownership, lifetimes, traits, and common idioms

Use when upgrading SPIKE code to production quality, migrating prototypes, converting experimental code to production-ready implementations, or when user invokes /spike-migrate

Use for rapid prototyping, experiments, exploring ideas without production quality requirements, validating technical feasibility, or when user invokes /spike