🎯Skills53
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 structured markdown files for complex task planning, tracking progress, and automatically managing multi-step workflows with session recovery.
Designs distinctive, production-grade frontend interfaces with creative aesthetics, generating polished web components and UI that avoid generic AI looks.
Context compression skill for summarizing conversation history, implementing compaction, and reducing token usage.
A Claude Code skill for creating PowerPoint (PPTX) presentations, part of an antigravity skills collection for LLM project development workflows.
Generates unique design philosophies and transforms them into visually stunning artworks in .png and .pdf formats, emphasizing original artistic expression.
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 building web artifacts, part of an antigravity skills collection covering LLM project development and agent-assisted workflows.
A Claude Code skill for leveraging superpowers capabilities, part of an antigravity skills collection focused on LLM project development and agent architectures.
Designs and coordinates multi-agent systems by distributing complex tasks across specialized agents with isolated contexts for enhanced problem-solving capabilities.
Applies Anthropic's brand colors, typography, and design standards to visual artifacts for consistent corporate identity.
A styling toolkit that applies professional font and color themes to artifacts like slides, docs, reports, and landing pages, offering 10 pre-set themes with curated color palettes and font pairings.
Remotion best practices skill from the Antigravity Skills collection, providing patterns for programmatic video creation with the Remotion framework.
Verification-before-completion skill that ensures thorough testing and validation before marking tasks as done.
A Claude Code skill for building MCP servers, part of an antigravity skills collection focused on LLM project development and multi-agent architectures.
Skill for executing implementation plans by dispatching fresh subagents per task, with two-stage review (spec compliance + code quality) after each completion.
Skill for completing development branches by presenting structured options for merge, PR, or cleanup after all tests pass, guiding the integration workflow.
A web design guidelines skill from the Antigravity Skills library, which empowers agents with professional capabilities in specific fields like full-stack development, complex logic planning, and multimedia processing through modular skill definitions.
Rigorously evaluates code review feedback by understanding, verifying technical correctness, and responding with technical reasoning before implementation.
Test-driven development skill that guides writing tests first, watching them fail, then writing minimal code to pass.
Context optimization skill for managing and reducing AI agent context window usage while maintaining effectiveness.
Modular skills library following the SKILL.md format for full-stack development, complex logic planning, and multimedia processing, compatible with multiple AI coding assistants.
Queries Google NotebookLM notebooks to retrieve source-grounded, citation-backed answers from Gemini using browser automation and library management.
JSON Canvas skill for creating and managing structured canvas-based visual representations of data and workflows.
Guides structured code review requests with templates for context, focus areas, and review criteria to get more effective feedback from reviewers.
Internal communications writing skill for drafting company communications using preferred formats and templates.
Web application testing skill from the Antigravity Skills collection, providing comprehensive testing patterns for web apps.
Educational skill covering context window fundamentals, attention mechanics, progressive disclosure, and context optimization strategies for AI agent architecture.
A skill from the Antigravity Skills library providing Vercel's official React and Next.js performance optimization guidelines, part of a modular skills collection compatible with Claude Code, Gemini CLI, Codex, Cursor, and other AI coding agents.
A cross-platform agent skills library following the SKILL.md format, compatible with Claude Code, Gemini CLI, Codex, Cursor, GitHub Copilot, and other AI coding assistants for specialized domain tasks.
Structured workflow for co-authoring documentation, proposals, and technical specs with AI, helping users efficiently transfer context and refine content iteratively.
Advanced evaluation skill from the Antigravity Skills collection, providing sophisticated assessment frameworks for code and architecture quality.
A Claude Code skill for LLM project development methodology, covering task-model fit evaluation, batch pipeline design, agent architecture, and cost estimation.
A skill from the Antigravity Skills library that teaches Git worktree workflows, enabling agents to work on multiple branches simultaneously through modular skill definitions for systematic problem-solving.
Skill for dispatching parallel agents, coordinating multi-agent workflows, and managing concurrent task execution.
Skill for creating animated GIFs optimized for Slack, providing size constraints, validation tools, and animation concepts for custom Slack-ready GIF creation.
A comprehensive Postgres performance optimization guide maintained by Supabase, covering 8 prioritized rule categories including query performance, connection management, security/RLS, schema design, concurrency, and monitoring with detailed SQL examples.
Extracts clean markdown content from web pages using the Defuddle CLI, removing navigation, ads, and clutter to reduce token usage. Preferred over WebFetch for standard web pages; not for URLs already ending in .md.
A Claude Code skill for managing hosted agents, part of an antigravity skills collection covering LLM project development and agent deployment workflows.
Tool design skill from the Antigravity Skills collection, providing patterns for designing effective developer tools and CLI interfaces.
BDI (Beliefs-Desires-Intentions) mental states skill from the Antigravity Skills collection, providing agent architecture patterns based on cognitive modeling.
An Antigravity skill that enables AI agents to interact with Obsidian vaults using the Obsidian CLI, providing capabilities to read, create, search, and manage notes from the command line across multiple compatible AI coding assistants.
Context degradation diagnosis skill for identifying lost-in-middle issues, context poisoning, attention pattern failures, and agent context problems.
Skill for evaluating AI agent performance using LLM-as-judge patterns, multi-dimensional evaluation rubrics, and quality gates for agent pipelines.
Template skill from Antigravity Skills for creating new skills with proper structure and configuration.
Part of the Antigravity Skills library, this skill provides modular instructions for working with the Claude API, enabling agents to handle full-stack development, complex logic planning, and multimedia processing tasks.
Part of the Antigravity Skills collection, a modular library of 79 AI agent skills covering creative design, full-stack development, documentation, planning, and cognitive architecture for Claude Code, Gemini CLI, Cursor, and other AI coding assistants.
Skill
Skill
Skill
Skill
Skill
Skill