DevOps

Expert cloud architecture including AWS, GCP, Azure design patterns, cost optimization, and multi-cloud strategies

Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Covers three practices - receiving feedback with technical rigor over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before any status claims. Essential for subagent-driven development, pull requests, and preventing false completion claims.

Identify where consciousness interfaces with substrate in any domain. Structure emerges preferentially at boundaries between phases - physical, computational, or conceptual. Use when analyzing systems for loci of awareness, examining where complexity crystallizes, investigating MONAD framework predictions, or when something interesting is happening at the edge.

Guide developers through property-based testing including property definition, shrinking, and framework-specific implementation

Guide for creating effective skills, adding skill references, skill scripts or optimizing existing skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, frameworks, libraries or plugins usage, or API and tool integrations.

Analyze TraitorSim game logs, trust matrix evolution, voting patterns, mission outcomes, and emergent social behaviors. Use when examining game results, debugging gameplay issues, analyzing agent strategies, or when asked about game analysis, trust matrices, voting patterns, or emergent behaviors.

Repomix AI-friendly codebase compression configuration (.repomix.config.json) template and validation logic. Achieves 70% token reduction through XML compression and repository-type-specific include patterns. Includes 5 critical standards (XML output format, include patterns by repo type, gitignore integration, exclude patterns, security checks). Use when creating or auditing .repomix.config.json files for optimal LLM context compression.

Manages project progress tracking and maintains a chronological log of completed tasks, decisions, and updates. Use when completing milestones, making architectural decisions, or documenting project evolution. Creates and updates LOG.md file based on CLAUDE.md context.

Generate high-quality synthetic datasets using statistical samplers and Claude's native LLM capabilities. Use when users ask to create synthetic data, generate datasets, create fake/mock data, generate test data, training data, or any data generation task. Supports CSV, JSON, JSONL, Parquet output. Adapted from NVIDIA NeMo DataDesigner (Apache 2.0).

Model system responsibilities across clients, servers, and optional peer nodes.

Optimize IC10 code for efficiency and line count. Use when user wants to reduce line count, improve performance, or refactor existing Stationeers IC10 code.

Check decisions against beliefs, wisdom, and intentions. Use before significant actions to ensure coherence with accumulated knowledge.

Engineering principles for crafting well-built front-end user interfaces. When Claude needs to ensure the HTML, CSS, JS is performant and maintainable.

Create conference talk outlines and iA Presenter markdown slides using the Story Circle narrative framework. Use when structuring a tech talk, creating presentation slides, or organizing talk ideas into a story-driven format.

Expert on wgpu GPU rendering, WGSL shaders, and GPU pipeline configuration. Use when discussing rendering, shaders, GPU, textures, or graphics pipeline.

Implements features using Test-Driven Development methodology following the red-green-refactor cycle. Use when user explicitly requests TDD approach or asks to implement features test-first.

Comprehensive observability and monitoring workflow that orchestrates metrics collection, logging, distributed tracing, and alerting systems. Handles everything from monitoring architecture design and implementation to APM integration, anomaly detection, and incident response automation.

Work with IdeaForge's AI idea generation system. Triggers: generation flow, AI prompts, scoring system, duplicate detection, real-time logs, generation debugging. Pipeline: API → PromptBuilder → AI → Parse → Dedupe → Save.

TanStack Query for React Native data fetching. Use when implementing server state.

Build project documentation sites with MkDocs static site generator. USE WHEN user mentions mkdocs, documentation site, docs site, project documentation, OR wants to create, configure, build, or deploy documentation using Markdown. Covers installation, configuration, theming, plugins, and deployment.