hybrid-search-implementation
Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.
Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.
Specialized ML model development, training, and deployment workflow
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.
Chrome's built-in Prompt API implementation guide. Use Gemini Nano locally in browser for AI features - session management, multimodal input, structured output, streaming, Chrome Extensions. Reference for all Prompt API development.
Model Context Protocol (MCP) server patterns for building integrations with Claude Code. Triggers on: mcp server, model context protocol, tool handler, mcp resource, mcp tool.
Pattern for efficiently exploring codebases using parallel subagents. Use when you need to understand code structure, find patterns, or gather context.
Use when coordinating multiple AI agents in real-time - provides inter-agent messaging via tmux wrapper (sub-5ms latency) or file-based team inbox for async workflows
This skill should be used when coordinating multiple subagents, implementing orchestrator patterns, or managing parallel agent workflows. Trigger phrases: "orchestrate agents", "coordinate subagents", "parallel agents", "multi-agent workflow", "delegate to agents", "run agents in parallel", "launch multiple agents".
Auto-invoke after task completion to generate powerful resume bullet points from completed work.
Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.
Design reusable prompt templates that encode domain-specific patterns for recurring AI tasks. Use when you've executed similar prompts 2+ times and need to capture the pattern as reusable intelligence. NOT for one-off prompts or generic "ask AI a question" patterns.
Guides creation of effective Agent Skills with proper structure and validation. Use when users want to create a new skill, update an existing skill, or need guidance on skill design patterns, SKILL.md format, or verify.py implementation. NOT when just using existing skills (use those skills directly).
Capture solved problems as searchable documentation with pattern detection. This skill auto-triggers when users confirm a fix worked ("that worked", "it's fixed", "working now") or manually via /compound command.
Guide users on when to use Claude Code Web vs CLI and seamlessly teleport sessions between environments
Universal dataset import for FiftyOne supporting all media types (images, videos, point clouds, 3D scenes), all label formats (COCO, YOLO, VOC, CVAT, KITTI, etc.), and multimodal grouped datasets. Use when users want to import any dataset regardless of format, automatically detect folder structure, handle autonomous driving data with multiple cameras and LiDAR, or create grouped datasets from multimodal data. Requires FiftyOne MCP server.
Provides development principles, guidelines, and VibeCoder guidance. Use when user mentions 原則, principles, ガイドライン, guidelines, VibeCoder, 安全性, safety, 差分編集, diff-aware. Triggers: 原則, principles, ガイドライン, VibeCoder, 安全性, 差分編集. Do not use for actual implementation - use impl skill instead.
Spawn an AI coding agent in a new terminal (Claude, Codex, Gemini, Cursor, OpenCode, Copilot). Defaults to Claude Code if unspecified.
Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms
AI Runtime工具装备系统,支持8个内部专业工具和10+个外部CLI工具的整合管理,提供工具发现、执行和配置功能,遵循整合优于创造的设计理念