Agent skills for Claude Code

Build accessible design systems with Radix UI primitives.

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts.

Maintains conversational memory in ~/.cursor/memory.md (global) and .cursor/memory.md (project).

NVIDIA RAG Blueprint — deploy, configure, troubleshoot and manage any RAG action: agentic RAG, VLM, guardrails, query rewriting…

Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality) for a deployed NVIDIA RAG Blueprint.

When to activate: RAG, retrieval augmented generation, LangChain, LlamaIndex, vector stores, embeddings, retrieval, chunking, reranking…

Analyze Rails apps and provide upgrade assessments

Commit, rebase, and merge the current branch.

Rebase the current branch with smart conflict resolution.

Automates browser interactions for web testing, form filling, screenshots, and data extraction.

Automate Raisely tasks via Rube MCP (Composio).

Create, inspect, validate, explain, and improve Ralph hat collections.

Explain the Ralph Loop plugin, how it works, and available skills.

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

Run a sequential three-tier code review on a finished implementation branch — Haiku (surface) → Sonnet (logic) → Opus (deep).

Manage tasks across GitHub and Linear with ralph-starter

Consensus-driven implementation planning via strict Planner/Architect/Critic iteration.

Ramp cost tuning \u2014 corporate card and expense management API integration.\n\

Ramp deploy integration \u2014 corporate card and expense management\

Ramp migration deep dive \u2014 corporate card and expense management\

Ramp performance tuning \u2014 corporate card and expense management\