Expert guidance for creating, writing, and refining Antigravity Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.
Master effective prompting techniques for Claude Code. Use when learning prompt patterns, improving task descriptions, optimizing Claude interactions, or troubleshooting why Claude misunderstood a request. Covers @ mentions, thinking keywords, task framing, and iterative refinement.
Structured reasoning for complex problems using Sequential Thinking MCP. Break down problems into stages, track thought progression, identify connections, and generate insights. Use for architectural decisions, complex debugging, research planning, or any problem requiring deep analysis.
This skill should be used when commands need to generate specifications or implementation plans, when the user asks about "how to write specs", "how to create plans", "spec structure", "plan hierarchy", or when working with track creation. Provides patterns for interactive questioning, spec structure, and hierarchical plan generation.
Dynamic problem-solving through structured sequential thoughts. Use when breaking down complex problems, planning multi-step solutions, analyzing ambiguous requirements, debugging intricate issues, exploring design alternatives, or tackling problems where the full scope is unclear. Enables thought revision, branching, and iterative refinement.
Manages long-term memory for users across conversations. Automatically queries relevant memories when starting a new topic, and saves important personal information, habits, schedules, and user-requested memories. Use this when discussing user background, preferences, or plans; starting a new task or project; users mention personal details or ask to remember something.
This skill should be used when the user asks to "create a memory", "read memories", "manage memories", "document patterns", or when starting work on a Serena project with existing memories. Essential for maintaining project knowledge across conversation sessions and distinguishing documentation from agent-focused memories.
Meta-skill for creating and improving agent skills. Use when designing new skills, refining existing skills, or understanding skill architecture patterns. Provides progressive disclosure, context efficiency principles, and skill anatomy guidelines.
Brainstorm and advise on technical decisions using structured process. EXCLUSIVE to brainstormer agent. Does NOT implement — only advises.
Evaluates skill effectiveness, suggests improvements to instructions, identifies missing edge cases, and recommends structure changes.
This skill should be used when the user mentions "burn", "tensor", "module", "backend", "training", "ONNX", "autodiff", "deep learning in Rust", or any Burn framework related query. Routes to appropriate domain skills and enforces evidence-seeking behavior.
한글 기반 클로드 스킬 자동 생성 도구. 사용자가 "클로드 스킬을 만들어줘" 또는 "[요구사항] 스킬 만들어줘"라고 요청할 때 사용. Progressive disclosure 원칙을 따르는 한글 문서 구조(SKILL.md + references/)를 자동으로 생성하고, 실전 예시를 포함한 일관성 있는 스킬 템플릿을 제공.
Externalize detailed memory to Memory Bank before conversation summarization to prevent context loss. Triggers: CP, checkpoint, save, 存檔, 記一下, 保存, sync memory, dump, 先記著.
Master writing plugins including agent implementation, skill creation, command development, and hook scripting. Learn best practices for plugin coding.
This skill should be used when the user asks about "error messages", "did you mean", "similar tools", "parameter suggestions", "schema hints", "MCP error handling", "guide the client", "helpful errors", "fuzzy matching", or discusses how MCP servers should guide clients with progressive error enhancement and corrective feedback.
Guides the creation of effective Claude Agent Skills. Use when creating new skills, improving existing skills, or reviewing skill quality. Covers naming conventions, file structure, progressive disclosure, and evaluation-driven development.
Condenses Claude Code session transcripts into readable summaries by filtering metadata, system notifications, and command artifacts. Use when the user wants to review, analyze, or understand what happened in a Claude Code session, view tool usage patterns, or export session data. Triggers when user mentions "analyze session", "review transcript", "condense logs", "what tools did I use", or similar workflow analysis requests.
Guide for managing Claude Code memory effectively. Use when setting up project memory, optimizing CLAUDE.md files, configuring rules directories, or establishing cross-session knowledge patterns. Covers memory hierarchy, best practices, and context optimization.
Setup vector embeddings and semantic search for document collections. Use for AI-powered similarity search, finding related documents, and preparing knowledge bases for RAG systems.
Genera contenuti didattici interattivi per bambini di 10 anni su qualsiasi argomento. Include spiegazioni semplici, quiz, esperimenti, attività pratiche e prompt per immagini AI. Usa quando vuoi spiegare un concetto a un bambino in modo divertente e coinvolgente.
Capture lessons from conversation after Claude made mistakes or needed correction. Trigger phrases include "reflect", "review our mistakes", "learn from this", "capture this lesson", "remember this for next time". Analyzes the conversation to extract actionable guidance and persists it to ~/.claude/lessons/ with triggers in ~/.claude/CLAUDE.md.
This skill allows the agent to create new coding problems for the DerpCode platform. This skill should be used when asked to create new DerpCode coding problems.
Search Claude Code conversation history. Use when user asks "where did I discuss X", "when did we talk about X", "find the conversation about X", or wants to continue previous work.
