productivity-kit

Configure Git user for current repository (personal or work)

I have features developed in parallel worktrees that I need to integrate: $ARGUMENTS

I want to develop features in parallel for my app using Git worktrees: $ARGUMENTS

Refactor $ARGUMENTS through small, reviewable steps with explanations.

Reorganize documentation in $ARGUMENTS to clearly distinguish permanent project docs from temporary ones.

Cleanup Project Structure Command

Restart tmux team with state preservation via SM

Use this agent when the user needs to research a topic, gather information from multiple sources, find facts, explore concepts, or needs comprehensive answers based on current web information. This includes questions about current events, technical topics, market research, fact-checking, or any inquiry requiring external knowledge gathering. Examples: <example> Context: User wants to understand a technical concept they're unfamiliar with. user: "What are the latest best practices for implementing RAG systems in 2024?" assistant: "I'll use the research-assistant agent to gather current information on RAG implementation best practices." <commentary> Since the user is asking about current best practices which require up-to-date web research, use the Task tool to launch the research-assistant agent to conduct comprehensive research on the topic. </commentary> </example> <example> Context: User needs factual information about a current event or topic. user: "Can you research the recent developments in quantum computing?" assistant: "Let me use the research-assistant agent to find the latest information on quantum computing developments." <commentary> The user explicitly requested research on a topic requiring current information. Use the research-assistant agent to gather relevant sources and synthesize findings. </commentary> </example> <example> Context: User is working on a project and needs background information. user: "I'm building a fintech app. What are the main regulatory requirements I should know about?" assistant: "I'll launch the research-assistant agent to research fintech regulatory requirements for your app development." <commentary> The user needs comprehensive research on regulatory requirements which requires gathering information from multiple authoritative sources. Use the research-assistant agent to conduct this research. </commentary> </example>

Retrieve universal coding patterns from vector database using true two-stage retrieval. Auto-invokes before complex tasks or when user says "--recall". Searches relevant role collections based on task context.

Store universal coding patterns into vector database. Auto-invokes after difficult tasks with broadly-applicable lessons. Trigger with "--store" or when user expresses frustration (strong learning signals). Uses true two-stage retrieval with MCP server v2.

This skill should be used when users need comprehensive research on a topic requiring exploration of multiple sources, synthesis of findings, and a well-structured report with citations. Use for complex research queries like "Research the latest developments in X", "Compare A vs B vs C", "Find the top N candidates for Y", or any request requiring deep exploration beyond a simple web search.

This skill should be used when users want to create a multi-agent tmux team for their project. It provides battle-tested templates for setting up autonomous AI agent teams that collaborate via tmux. Use this skill when users ask to create AI teams, set up multi-agent workflows, or build autonomous coding teams. The skill includes 4 sample team templates (2 software development + 2 research) that can be customized for any domain.