Parallel execution patterns for cognitive reasoning tasks. Use when independent sub-problems can be solved simultaneously, multiple solution approaches need exploration, ensemble confidence is required, or time permits depth without sequential constraints. Integrates with ToT, BoT, HE, and AT for accelerated reasoning with fan-out/fan-in, MCTS-style search, and MoA aggregation patterns.
A clear description of what this skill does and when Claude should automatically invoke it
Define tools for the support agent. Use when adding new capabilities like refund processing, license transfer, knowledge lookup, or any agent action.
仕様駆動型開発スキル（Copilot版）。機能実装前に対話的なヒアリングで仕様を明確化し、implementation-plan.mdとtasks.mdを生成する。「機能を実装したい」「新しいコンポーネントを作りたい」「○○を追加したい」などの実装リクエスト時に使用。GitHub Copilot CLIによる自動レビューと修正ループで品質を担保する。
Retrieves 10 similar historical cases from AgentDB vector store for RAG-based diagnosis support
Reconnaissance techniques for exploring large contexts before reading them. Teaches agents to probe, filter, and map data structures without consuming context window.
Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent performance degrades unexpectedly, or debugging agent failures.
Implement and debug semantic/vector search with model2vec-rs and sqlite-vec. Use for embedding generation, vector queries, hybrid search, or RRF fusion.
SmartACE (Agentic Context Engineering) workflow engine with MCP-B (Master Client Bridge) and AMUM-QCI-ETHIC module. Dual database architecture using DuckDB (analytics) + SurrealDB (graph). Uses Blender 5.0 (bpy) and UE5 Remote Control. Use when (1) MCP-B agent-to-agent communication (INQC protocol), (2) AMUM 3→6→9 progressive alignment, (3) QCI quantum coherence states, (4) ETHIC principles enforcement (Marcel/Anthropic/EU AI Act), (5) SurrealDB graph relationships, (6) DuckDB SQL workflows, (7) ML inference with infera/vss, (8) Blender 5.0 headless processing, (9) UE5 scene control, (10) DuckLake time travel.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Build conversation history UI with sidebar, thread switching, and conversation CRUD operations. Implements conversation list, rename, delete, and persistence. Use when adding conversation management features for Phase 3.
LangChain Deep Agents framework for building autonomous coding agents. Use for agent harness, backends, subagents, human-in-the-loop, long-term memory, middleware, and CLI-based agent development.
Control Sonos speakers through MCP tools - search and play music, manage queue and playlists, adjust volume. Use when users request music playback, mention artists/songs/albums, want to control Sonos speakers, manage playlists, or ask about what's playing.
Build production AI agents with the Claude Agent SDK. Use when working with: (1) Creating autonomous agents with query() or ClaudeSDKClient, (2) Defining custom tools via in-process MCP servers, (3) Implementing hooks for tool interception and permissions, (4) Building multi-agent systems with subagents, (5) Managing sessions and state across queries, (6) Integrating MCP servers for external capabilities. Covers Python and TypeScript SDKs with production patterns.
Optimize Claude Code context usage through monitoring, reduction strategies, progressive disclosure, planning/execution separation, and file-based optimization. Task-based operations for context window management, token efficiency, and maintaining conversation quality. Use when managing token costs, optimizing context usage, preventing context overflow, or improving multi-turn conversation quality.
This skill should be used when analyzing a link to an AI tool and adding it to the awesome-ai-tools readme with proper categorization
Set up and use MCP (Model Context Protocol) servers to extend Claude Code capabilities including PRISM semantic memory, filesystem access, and database integration. Use when setting up MCP servers, debugging MCP connections, or understanding MCP tool usage.
Write hookify rules for pattern-based hook triggers in Claude Code. WHEN: MUST use for creating hookify rules. Invoke with "/claude-hookify-rules" or "create hookify rule", "pattern-based hook". WHEN NOT: Creating general hooks (use claude-hook-development), creating agents or commands.
Create .prompt files for LLM operations in Output SDK workflows. Use when designing prompts, configuring LLM providers, or using Liquid.js templating.
Memory preservation for Claude Code sessions. Use when approaching token limits, needing to /reset or /compact, switching between complex tasks, or preserving critical session state before context loss. Creates comprehensive memory dumps at /tmp/total-recall containing current state, decisions, artifacts, and next steps for seamless context restoration.
