ai-dumping-ground

Strict operational protocol with 5 modes (Research, Innovate, Plan, Execute, Review) for controlled, step-by-step code changes. Use when the user invokes /riper or says "ENTER RESEARCH MODE", "ENTER INNOVATE MODE", "ENTER PLAN MODE", "ENTER EXECUTE MODE", or "ENTER REVIEW MODE". This protocol prevents unauthorized modifications by requiring explicit mode transitions.

Configures metals-mcp for the current Scala project so it works identically in the Claude Code CLI and in "Code" inside the Claude Desktop app. Writes a committed self-locating wrapper script plus a machine-local .mcp.json. Use when the user wants to add metals-mcp to a project, says "setup metals-mcp", "add metals-mcp config", "configure metals-mcp here", or is in a Scala project and asks to wire up any metals MCP integration.

Configures the serena MCP server for the current project so it works identically in the Claude Code CLI and in "Code" inside the Claude Desktop app. Writes a committed self-locating wrapper script plus a machine-local .mcp.json. Invoke only when the user explicitly runs the `/setup-serena-mcp` slash command — do not trigger on general phrases like "set up serena" or "add an MCP server" unless that exact slash command is used.

Refactor Scala code and apply good practices from 2020 Hindsight Scala (https://2020-hindsight-scala.kevinly.dev/docs/). Use this skill whenever writing new Scala code, reviewing Scala code, or refactoring existing Scala code. Also trigger when the user mentions Scala best practices, ADTs, type safety, Option/Either usage, or asks to clean up / improve Scala code quality. This skill applies even if the user doesn't explicitly mention "2020 hindsight" — any Scala code writing or refactoring should follow these practices.