executing-plans

Filesystem-based context engineering skill for offloading agent context to files, enabling dynamic context discovery, just-in-time context loading, and effectively unlimited memory through file-based storage and retrieval patterns

Generates comprehensive UI/UX design recommendations with 50+ styles, 21 color palettes, font pairings, and best practices across multiple tech stacks.

Designs distinctive, production-grade frontend interfaces with creative aesthetics, generating polished web components and UI that avoid generic AI looks.

Memory systems design skill for implementing agent memory with persistence across sessions, including temporal knowledge graphs, vector stores, entity memory, and layered memory architectures.

A Claude Code skill for LLM project development methodology, covering task-model fit evaluation, batch pipeline design, agent architecture, and cost estimation.

Generates structured markdown files for complex task planning, tracking progress, and automatically managing multi-step workflows with session recovery.

A Claude Code skill for building MCP servers, part of an antigravity skills collection focused on LLM project development and multi-agent architectures.

A Claude Code skill for systematic debugging approaches, part of an antigravity skills collection covering LLM project development and agent-assisted workflows.

A Claude Code skill for creating new skills, part of an antigravity skills collection that covers LLM project development and agent-assisted workflows.

Guides collaborative brainstorming by systematically exploring ideas, refining requirements, and designing solutions through structured, incremental dialogue.