NLP

Fetch the latest, docs-grounded API details and best practices for a library/framework using Context7 MCP tools `resolve-library-id` and `get-library-docs`. Use when a user asks for “最新用法/最新寫法/最佳實務/latest usage/current best practice/latest API” of a package, or asks how to implement a feature with a library and wants the newest docs-based guidance.

Load the full content of a previous Claude Code conversation into current context. Use when user asks to "load conversation <uuid>" or "show me conversation <uuid>" or references loading/viewing a past conversation by its ID.

Display comprehensive project and session information including Git status, SPEC progress, version details, and system resources. Use when starting new sessions, checking project status, reviewing project context, or when users ask "what's the status", "show project info", or "where are we".

This skill provides comprehensive knowledge for building type-safe APIs with Hono, focusing on routing patterns, middleware composition, request validation, RPC client/server patterns, error handling, and context management.Use when: building APIs with Hono (any runtime), setting up request validation with Zod/Valibot/Typia/ArkType validators, creating type-safe RPC client/server communication, implementing custom middleware, handling errors with HTTPException, extending Hono context with custom variables, or encountering middleware type inference issues, validation hook confusion, or RPC performance problems.Keywords: hono, hono routing, hono middleware, hono rpc, hono validator, zod validator, valibot validator, type-safe api, hono context, hono error handling, HTTPException, c.req.valid, middleware composition, hono hooks, typed routes, hono client, middleware response not typed, hono validation failed, hono rpc type inference

Transform and export data using DuckDB SQL. Read CSV/Parquet/JSON/Excel/databases, apply SQL transformations (joins, aggregations, PIVOT/UNPIVOT, sampling), and optionally write results to files. Use when the user wants to: (1) Clean, filter, or transform data, (2) Join multiple data sources, (3) Convert between formats (CSV→Parquet, etc.), (4) Create partitioned datasets, (5) Sample large datasets, (6) Export query results. Prefer this over in-context reasoning for datasets with thousands of rows or complex transformations.

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).

Implements new modules, agents, or features using TDD methodology. Used when adding any new functionality to the table2image multi-agent system. Follows six-phase workflow: context loading, test writing, implementation, verification, documentation, and protocol completion.

Convert AI-written text to more human-like writing through subtle edits. Use when text reads "too AI", when the user mentions "humanize", "sounds robotic", "AI-written", "make it natural", or when editing for a more conversational voice.

Transform ideas into actionable implementation plans. Combines Socratic questioning for requirements discovery with detailed task breakdown for zero-context engineers. Use before any feature development.

Delegates test pattern detection to a lightweight agent. Use when you need to understand existing test conventions without loading test files into context.

MCP (Model Context Protocol) server evaluation guide for creating comprehensive test suites with read-only, independent questions

Managing session continuity across Claude conversations by saving structured context (tasks, files, errors, git state) to JSON and loading in new sessions. Use when user asks how session continuity works, explaining session protocol functionality, understanding session state management, describing what gets saved in sessions, ending a session with unfinished work, starting a session with existing session-protocol.json, or when user mentions 'save progress', 'save session', 'save my work', 'continue later', 'session context', 'pick up where left off', 'load session', 'restore session', or explicitly invokes /save-session-protocol or /load-session-protocol commands.

Store knowledge, entries, errors, and context in the worklog database

Build React applications with CopilotKit and LangGraph for AI-powered collaborative editing. Creates production-ready editor applications (text, document, or node-based) with real-time AI assistance, shared state management, and agentic workflows. Use this skill when users want to build intelligent editing interfaces with AI collaboration features.

Use when the animation domain is unclear or spans multiple contexts—provides general-purpose Disney animation principle guidance.

Ask the oracle (GPT-5.2 with deep reasoning) strategic technical questions. Use for architecture decisions, complex debugging, security analysis, or when you need a second expert opinion. Supports background execution for long-running queries.

Enterprise Application Monitoring with AI-powered observability architecture, Context7 integration, and intelligent performance orchestration for scalable modern applications

Transcribe Vaam videos using Google Gemini AI. Takes a Vaam share URL, downloads the video, and returns a full text transcription. Supports any language without translation.

AI-assisted development workflow with TDD, context management, and incremental implementation. Use when developing features with AI assistance, managing code context for AI tools, implementing features step-by-step, or when encountering repeated errors needing web search for resolution.

React 19's use() API for reading Promises/Context conditionally. For async data fetching, Suspense, conditional context access, useContext migration.