This skill should be used when the user asks to "design agent tools", "create tool descriptions", "reduce tool complexity", "implement MCP tools", or mentions tool consolidation, architectural...
This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context...
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to...
Select the right strategic framework for your situation through exploratory dialogue. Use when user describes a problem, decision, or challenge; needs structured thinking approach; mentions...
This skill should be used when the user asks to "offload context to files", "implement dynamic context discovery", "use filesystem for agent memory", "reduce context window bloat", or mentions...
This skill should be used when the user asks to "design multi-agent system", "implement supervisor pattern", "create swarm architecture", "coordinate multiple agents", or mentions multi-agent...
This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge,...
Research and add new strategic frameworks to the system (meta-skill). Use when user wants to add framework not in library; discovered new framework in their domain; asks "Can you add...
PostgreSQL + Redis database design patterns. Use for data modeling, indexing, caching strategies. Covers JSONB, tiered storage, cache consistency.
Capture API response test fixture.
Use when adapting large language models to specific tasks, domains, or behaviors - covers LoRA, QLoRA, PEFT, instruction tuning, and full fine-tuning strategiesUse when ", " mentioned.
Use when constructing portfolios, implementing mean-variance optimization, factor models, risk parity, or Black-Litterman allocation - covers modern portfolio theory and practical enhancementsUse...
Use when automating model architecture design, optimizing hyperparameters, or exploring neural network configurations - covers NAS algorithms, search spaces, Bayesian optimization, and AutoML...
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support
Provides a Model Context Protocol (MCP) server interface to the skills library, allowing any MCP-compliant agent (e.g. Claude Desktop) to invoke Antigravity skills as native tools.
Patterns for protein structure prediction using AlphaFold2/ColabFold, structural analysis, model quality assessment, and integration with experimental data. Covers best practices and critical...
Use when implementing attention mechanisms, building custom transformer models, understanding positional encoding, or optimizing transformer inference - covers self-attention, multi-head...
Design RESTful APIs following best practices for resource modeling, HTTP methods, status codes, versioning, and documentation. Use when creating new APIs, designing endpoints, or improving...
Jujutsu (jj) version control workflow. Use this skill when working with jj commands, commits, bookmarks, rebasing, or GitHub integration. Jujutsu is a modern VCS that uses Git as storage backend...