自然語言處理

This skill should be used when the user asks to search/send/draft email, check calendar, create events, schedule meetings, find/upload/share Drive files, read/edit Google Docs, read spreadsheet data, send texts/iMessages, send WhatsApp messages, send Signal messages, check messages, or create reminders. Manages Gmail, Google Calendar, Google Drive, Google Docs, Google Sheets, iMessage, WhatsApp, Signal, and Apple Reminders.

Template and guide for restructuring large documentation files into token-efficient directory structures. Reduces context bloat by 40-60% while maintaining accessibility.

Autonomous context extraction and structuring for converting unstructured information from multiple sources into AI-interpretable structured formats.

Create and manage AI agent skills following best practices. Use when creating new skills, optimizing context, designing multi-agent systems, or implementing progressive disclosure patterns.

Template for creating new skills in gptme-contrib. Use this as a starting point when creating your own skills.

Comprehensive R package for command-line interface styling, semantic messaging, and user communication. Use this skill when working with R code that needs to: (1) Format console output with inline markup and colors, (2) Display errors, warnings, or messages with cli_abort/cli_warn/cli_inform, (3) Show progress indicators for long-running operations, (4) Create semantic CLI elements (headers, lists, alerts, code blocks), (5) Apply themes and customize output styling, (6) Handle pluralization in user-facing text, (7) Work with ANSI strings, hyperlinks, or custom containers. Also use when migrating from base R message/warning/stop, debugging cli code, or improving existing cli usage.

Use when creating performance optimization plan for backend, API, or general system performance. Enforces BASELINE → PROFILE → OPTIMIZE → VALIDATE sequence. Triggers: "optimize API", "backend slow", "API latency", "database performance", "query optimization", "server response time". For "Core Web Vitals" in backend/API context, use this skill. For frontend UI accessibility + performance (WCAG, Lighthouse accessibility), use frontend-production-quality instead. If thinking "bottleneck is obvious" - profile first.

Row Level Security patterns for database operations. Use when writing Prisma/database code, creating API routes that access data, or implementing webhooks. Enforces withUserContext, withAdminContext, or withSystemContext helpers. NEVER use direct prisma calls.

Provides a consistent, reproducible workflow for creating, updating, and maintaining screenshots in the Auth0 docs-v2 monorepo. Use when capturing or modifying screenshots for Mintlify pages, Auth0 Dashboard interfaces, or UI surfaces within main, auth4genai, or ui. Ensures correct formatting, accessibility, alt text, paths, viewport, file size, cropping rules, and Playwright MCP usage.

Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation history, or when optimizing tokens-per-task rather than tokens-per-request.

Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.

Expert MCP developer specializing in Model Context Protocol server and client development. Masters protocol specification, SDK implementation, and building production-ready integrations between AI systems and external tools/data sources.

ChainGraph flow editing tRPC layer for visual flow editor operations. Use when working on apps/chaingraph-backend or packages/chaingraph-trpc/server. Covers flow CRUD, node/edge operations, port updates, real-time subscriptions, locking, version control. Triggers: flow procedure, addNode, removeNode, connectPorts, updatePortValue, subscribeToEvents, flowContextProcedure, chaingraph-backend, chaingraph-trpc, flowStore.

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).

Use when user wants to extract text from ebooks (EPUB, MOBI, PDF). Use for converting ebooks to plain text for analysis, processing, or reading. Handles all common ebook formats.

Types package architecture for ChainGraph core definitions. THE foundation package for all development. Use when working on packages/chaingraph-types, port system, decorators, node classes, flow definitions, execution context, propagation, or any type-related code. Contains 9 port types, decorator system, compositional node architecture, execution engine. Triggers: types, port, decorator, @Node, @Input, @Output, @PortString, @PortArray, @PortObject, BaseNode, INode, IPort, IEdge, IFlow, ExecutionEngine, ExecutionContext, propagation.

Activate when breaking down implementation plans into detailed task lists with agent contexts, acceptance criteria, and status tracking

Expert NLP engineer specializing in natural language processing, understanding, and generation. Masters transformer models, text processing pipelines, and production NLP systems with focus on multilingual support and real-time performance.

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.

Context and working knowledge for Calci’s prediction-market domain, which is powered by Kalshi. Use this skill whenever the user asks about Calci prediction markets, Kalshi markets, tickers, order books, pricing, settlement, or the Kalshi API/WebSocket.