Explore and investigate ideas before committing to a change. Trigger: When the orchestrator launches you to think through a feature, investigate the codebase, or clarify requirements.
Create technical design document with architecture decisions and approach. Trigger: When the orchestrator launches you to write or update the technical design for a change.
Parallel adversarial review protocol that launches two independent blind judge sub-agents simultaneously to review the same target, synthesizes their findings, applies fixes, and re-judges until both pass or escalates after 2 iterations. Trigger: When user says "judgment day", "judgment-day", "review adversarial", "dual review", "doble review", "juzgar", "que lo juzguen".
Validate that implementation matches specs, design, and tasks. Trigger: When the orchestrator launches you to verify a completed (or partially completed) change.
Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team sizing, task decomposition, and when to use teams vs sub-agents vs worktrees.
Complete AI coding workflow system. Orchestration patterns, 18 hook events, 5 agents, cross-agent support, reference guides, and searchable learnings. Works with Claude Code, Cursor, and 32+ agents.
Remove AI-generated code slop, unnecessary comments, and over-engineering from the current branch diff. Cleans up boilerplate, simplifies abstractions, and strips defensive code. Use when cleaning up code, simplifying, removing boilerplate, or before committing.
Write tests for Neuron AI agents, RAG systems, workflows, and tools using the built-in testing utilities. Use this skill when the user mentions testing agents, writing unit tests, mocking AI providers, testing tool execution, verifying RAG retrieval, testing workflow behavior, or creating test cases for Neuron AI components. Also trigger for any task involving PHPUnit tests, fake providers, test assertions, or quality assurance in Neuron AI projects.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
Maintain the OpenVMM Guide and its code-sync mapping. Load when: (1) adding, removing, or moving Guide pages, (2) adding new device crates or CLI args that need doc coverage, (3) updating the doc-code-sync mapping table, or (4) auditing Guide freshness against code changes.
Investigate CI failures on OpenVMM PRs. Load when a PR has failing CI checks, you need to download and analyze test artifacts, or you need to diagnose build, fmt, clippy, or VMM test failures.
VeOmni-specific checklist for feature development and refactoring. Covers impact analysis across modalities, trainer hierarchy, data pipeline, and distributed code. Use before implementing any non-trivial change. For model-specific or ops-specific work, use veomni-new-model or veomni-new-op instead. Trigger: 'add feature', 'implement', 'refactor', 'reorganize', 'new capability'.
Use this skill when adding support for a new model to VeOmni. Covers the full lifecycle: analyzing the HuggingFace model, creating model patches, defining parallel plans, writing configs, integrating with the trainer, and testing. Trigger: 'add model', 'support new model', 'integrate <model_name>', 'new model support'.
Use this skill when updating dependencies managed by uv: bumping a package version, upgrading the uv tool itself, updating torch/CUDA stack, switching transformers version, or regenerating the lockfile. Trigger: 'update dependency', 'bump version', 'upgrade uv', 'update torch', 'update lockfile', 'uv sync fails'.
Use this skill before committing ANY code change — this is a mandatory gate in the commit flow. Also trigger proactively when: you've made changes across multiple files and want to check consistency, you're unsure if a fix is safe, a change touches shared infrastructure (BaseTrainer, distributed, model loading, data pipeline), or a change is larger than a few lines. The review launches a subagent that checks implementation quality, multi-file consistency, and known constraint violations, then rates the change as safe/needs-attention/risky.
Synchronizes EFCore.PG to use the latest EF daily build for the current preview being targeted. Bumps the dependency and ensures the provider builds and all tests pass.
Use Set and Map for O(1) membership lookups instead of array.includes(). Apply when checking membership repeatedly or performing frequent lookups against a collection.
