Find the perfect capability for your agent.
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, 備份, backup, snapshot, 快照, 記錄, 等等, 先停, pause, 離開前, before leaving, 收工.
AI-powered browser automation for web scraping, form filling, data extraction, research, and any task requiring browser interaction. Executes natural language instructions as browser actions using vision and LLM reasoning in the cloud. Use when tasks require: (1) Navigating websites and extracting information, (2) Filling forms or interacting with web UIs, (3) Scraping data from multiple pages, (4) Automated web research, (5) Testing web applications, (6) Any task that would normally require manual browser use. Environment variable BROWSER_USE_API_KEY must be set.
Expert guidance for creating, building, and using Claude Code subagents and the Task tool. Use when working with subagents, setting up agent configurations, understanding how agents work, or using the Task tool to launch specialized agents.
AI agent specialist for Faiston NEXO. Use PROACTIVELY for Google ADK agents, Bedrock AgentCore, Gemini API, ElevenLabs TTS, and AI-powered features.
Specification-driven development workflow for AI agents. Use when tasks are too large for a single session, require multi-step implementation, span multiple files/features, or need persistent requirements tracking. Provides structured specification management with token-optimized artifacts for complex feature development, brownfield modifications, and cross-session continuity.
LlamaIndex implementation patterns with templates, scripts, and examples for building RAG applications. Use when implementing LlamaIndex, building RAG pipelines, creating vector indices, setting up query engines, implementing chat engines, integrating LlamaCloud, or when user mentions LlamaIndex, RAG, VectorStoreIndex, document indexing, semantic search, or question answering systems.
Use PROACTIVELY this agent when you need to design and create optimal Claude Code subagents, update existing agents with new capabilities, revise agent configurations, analyze project requirements to identify specialized roles, or craft precise agent configurations with appropriate tool permissions and model tiers. When the user specify "Create or Update subagent [name]", this skill must be triggered.
Quantitative framework for detecting AI-generated "slop" in prose through systematic analysis of structural, lexical, rhetorical, and logical patterns. Use when analyzing text authenticity, evaluating writing quality, detecting AI-generated content, or assessing whether prose has characteristic AI patterns like excessive parallelism, abstraction laddering, chiasmus abuse, platitudes, tautologies, or rhetorical overengineering.
Advanced AI capabilities for paracle_meta including web search, code execution, MCP integration, and autonomous agent spawning. Use when you need enhanced AI functionality beyond basic generation.
Comprehensive guide to evaluating Retrieval-Augmented Generation systems including retrieval metrics, generation quality, faithfulness, and end-to-end evaluation frameworks
Expert CSS and frontend styling specialist that analyzes codebases, maintains style guides, suggests improvements, and stays current with modern design patterns. Use when working on frontend styling, creating design systems, ensuring visual consistency, or need expert CSS/styling guidance. Integrates with oracle, summoner, and wizard.
Autonomous AI coding loop with PRD-based task tracking. Use when user says "leo-wiggum", "/leo-wiggum", "start leo loop", "autonomous coding", "run leo", or wants to implement a feature using iterative AI sessions that spawn fresh Claude Code instances. Takes a feature description, breaks it into user stories in a PRD, and runs an external loop where each iteration picks the next incomplete story.
Manages Claude Code skills - creates, updates, and maintains skills following established design principles. Use when the user asks to create a skill, update a skill, refactor a skill, or wants to teach Claude a new capability.
Expert system for AgentMaestro that helps decide when and how to delegate tasks to specialized AI agents (Claude, Codex, Gemini). Use when you need to determine which agent is best suited for a task, or when a task should be broken down and delegated to multiple agents.
Guide for creating custom skills in SaaS Factory. Use when you need to create a new skill to extend Claude's capabilities with specialized knowledge, workflows, or tools.
Brainstorm and advise on technical decisions using structured process and MCP helpers. EXCLUSIVE to brainstormer agent. Does NOT implement — only advises.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
