nullmastermind

Analyze codebase using GitNexus knowledge graph + codebase-retrieval. Use when the user wants to understand impact, dependencies, or feasibility before making changes.

Implement tasks from OpenSpec change or conversation plan. Use when the user wants to start implementing, continue implementation, or work through tasks.

Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.

Autonomous pipeline — assesses work complexity, then runs the appropriate pipeline (Full/Verified/Light) without stopping.

Reproduce bugs, explore apps, or run QA test flows via dev-browser. Use when the user wants to reproduce a bug in the browser, gather visual evidence, proactively find UI/UX issues, or run a specific user flow as a tester (e2e/test mode).

Execute maintenance work directly. Brief mini-plan, then carry out the change.

Plan and implement CI/CD pipeline changes. Explore scope, deployment strategy, and automation, then implement with optional spec creation.

Plan and implement Docker/containerization work. Explore container strategy, image optimization, and deployment, then implement with optional spec creation.

Implement tasks from OpenSpec change or conversation plan. Use when the user wants to start implementing, continue implementation, or work through tasks.

Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.

Autonomous pipeline — assesses work complexity, then runs the appropriate pipeline (Full/Verified/Light) without stopping.

Execute maintenance work directly. Brief mini-plan, then carry out the change.

Port a feature from an external git repo into the current project. Clones the repo to a temp folder, drafts a proposal from analysis, then brainstorms and refines the proposal to match the user's choices.

Shared explore/plan mode behavior for all planning commands (feat, fix, chore, refactor, perf, docs, test, ci, docker). Provides the stance, continuous verification, fluid workflow, subagent protocols, OpenSpec awareness, and guardrails.

Execute UI/UX work directly (refine UI, optimize, fix UX). Reads or bootstraps the project's UI DNA before any change.

Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.

Game design brainstorm and research. Use when the user wants to design a game, research a genre, or learn from existing games before building.

Shared explore/plan mode behavior for Unity game builder commands. Provides the stance, Feynman technique, continuous verification, subagent protocols, and guardrails.

Launch Unity game builder. Usage: /unity [args]

Auto-install and configure unity-mcp from scratch. Run before first use of /unity.

Help non-tech users create custom Claude skills through guided conversation.

Automate browser tasks using dev-browser — a sandboxed browser automation tool for AI agents. Use when user asks to browse, scrape, interact with web pages, or automate browser workflows via dev-browser.

Automate browser tasks using Playwright MCP — email, messaging, marketing, data extraction, and daily workflows.

Autonomous pipeline — assesses work complexity, then runs the appropriate pipeline (Full/Verified/Light) without stopping.

Launch any kit skill by name. Usage: /osf [skill] [args]