This skill should be used when the user asks to "create a subagent", "validate a subagent", "generate subagent schema", "check subagent configuration", "write subagent specification", or mentions subagent development, validation, or protocol documentation for Claude Code.
This skill should be used when the user asks to "create a skill", "write a skill", "build a skill", or wants to add new capabilities to Claude Code. Use when developing SKILL.md files, organizing skill content, or improving existing skills.
The Ralph Wiggum technique for minimal, declarative prompts that enable loop-based autonomous execution.
Complete guide for local agent development using kubani-dev CLI, unified configuration, MCP integration, and seamless iteration.
MUST USE when searching for official Claude Code or Anthropic platform documentation links (MCP, hooks, skills, CLI). Provides fast fuzzy-search CLI for authoritative Claude documentation.
Expert knowledge for Business Layer modeling in Documentation Robotics
智能文档学习和内容模仿技能。当需要：(1) 分析和学习优秀文档的结构、风格和写作模式，(2) 从文档中提炼关键要素和模板，(3) 基于学习内容生成模仿材料，或 (4) 创建新的提示词或技术文档时使用此技能。支持提示词工程、技术文档、API文档、用户手册等多种文档类型的学习和模仿。
Guide for creating and editing Agent Skills. Use this skill when you need to create or modify a skill.
Apply covenant principles as design constraints across all core systems. Use when building agents, prompts, recipes, artifacts, or multi-agent architectures.
Integrate LLMs into applications - APIs, prompting, fine-tuning, and context management
Build self-hosted speech-to-text APIs using Hugging Face models (Whisper, Wav2Vec2) and create LiveKit voice agent plugins. Use when building STT infrastructure, creating custom LiveKit plugins, deploying self-hosted transcription services, or integrating Whisper/HF models with LiveKit agents. Includes FastAPI server templates, LiveKit plugin implementation, model selection guides, and production deployment patterns.
Expert knowledge for Application Layer modeling in Documentation Robotics
Self-improvement and learning skill that helps Claude learn from user interactions, corrections, and preferences
Foundational SPARQL patterns covering RDF querying, triple patterns, graph patterns, and semantic web fundamentals. Use when querying RDF data or working with knowledge graphs. This is the entry point for SPARQL development.
Initialize a new vibecoding session with proper context and planning
Provide a reusable pattern for memoizing deterministic function calls to reduce latency and repeated computation. Backed by the `python` diskcache package. Use skill when updating or editing everything.
Multi-agent coordination patterns for building effective AI teams
Search the hierarchical memory system for relevant memories. Searches across all tiers (working, episodic, semantic) and returns ranked results. Use for context retrieval and pattern matching. Keywords: memory, search, retrieve, recall, context, similarity.
BEFORE dispatching any implementation agent or starting to code - if you're about to write "Task(subagent_type=..., prompt=...)" for implementation, or about to implement a plan yourself, STOP and review first. The prompt you're about to send IS a brief - review it for design flaws before the agent implements garbage.
Orchestrate multiple LLMs as a council, generating collective intelligence through peer review and chairman synthesis
Tools and frameworks for AI red teaming including PyRIT, garak, Counterfit, and custom attack automation
