Agent skills

Scalable data processing for ML workloads.

Aggregate research-corpus radar sidecars into a corpus or per-cluster freshness report — totals, overdue count, per-cluster / per-GRADE /…

Performs command-line binary analysis, reverse engineering, and security research using the radare2 toolchain.

Use when working with the Radio Mast Streaming Network: hosting Icecast-compatible internet radio streams, choosing codecs (MP3, AAC…

Produce or audit a radiomics / tabular clinical-ML study — imaging or clinical features → any classical learner (penalised logistic [LASSO…

Expert in building Retrieval-Augmented Generation systems.

Chunking strategies, embedding model selection, hybrid search, reranking, eval metrics

Retrieval-Augmented Generation patterns for grounded LLM responses.

Review code changes against project conventions, specs, and definition-of-done — parallel review directions merged into one station review.

Use when adding polymorphic activity timelines with live Turbo Stream updates to any Rails model.

Research how production Rails apps solve architectural problems using the Real World Rails repository.

When to activate: Rails, MVC conventions, ActiveRecord associations, service objects, strong parameters, concerns, callbacks, form…

Deploys and manages Qdrant vector databases on Railway for AI-powered semantic search and RAG applications.

This skill should be used when the user asks "railway status", "is it running", "what's deployed", "deployment status", or about uptime.

Commit, rebase, and merge the current branch.

Rebase the current branch with smart conflict resolution.

Queue processing with fresh context per phase.

Run, monitor, resume, merge, and debug Ralph loops.

Explain the Ralph Wiggum iterative loop methodology, configuration flags, prompt writing patterns, and available commands.

Run an autonomous, iterative development loop using the Ralph Wiggum technique.