自然語言處理

Use sgrep for semantic code search. Use when you need to find code by meaning rather than exact text matching. Perfect for finding concepts like "authentication logic", "error handling patterns", or "database connection pooling".

自然语言接口，理解用户意图并映射到对应的命令

Provide effective context to Claude for Symfony development with relevant files, patterns, and constraints

Build NLP applications using transformers library, BERT, GPT, text classification, named entity recognition, and sentiment analysis

Create or update continuity ledger for state preservation across /clear operations. Ledgers maintain session state externally, surviving context resets with full fidelity.

Classify text sentiment using NLP techniques, lexicon-based analysis, and machine learning for opinion mining, brand monitoring, and customer feedback analysis

Apply cryptanalysis techniques to break ciphers without knowing the key. Use this skill when performing known-plaintext attacks, chosen-plaintext attacks, or statistical analysis to recover encryption keys.

Read and write files efficiently. Use for processing text files, binary data, or large files.

System for externalizing large task context to .scratch/tasks/ files to maintain continuity across context compactions and session resets. Use this skill when starting large/complex tasks, after /compact or /new commands, or when context window is getting full during multi-file work.

Create 3D CAD models using build123d, a modern Python CAD library with builder pattern. Use for parametric modeling, assemblies, and STEP/STL export. Offers cleaner syntax than CadQuery with context managers.

Create UV mappings and parameterize mesh surfaces to 2D domains. Use for texture mapping, surface flattening, and geometry processing. Supports conformal, harmonic, and LSCM parameterization methods.

Use large language models to summarize and analyze text content. Use when generating summaries, extracting key points, or analyzing aggregated content. NOT needed for simple data extraction or aggregation tasks.

Conduct context-driven code reviews focusing on quality, testability, and maintainability. Use when reviewing code, providing feedback, or establishing review practices.

Creates vision documents through structured 5-phase discovery process. Guides through problem discovery, solution exploration, user needs analysis, future & scope planning, and document generation. Use when user wants to create a vision document for a feature, needs to define strategic context and high-level goals, or is starting feature development and needs to establish the "why" and "what" before technical details. Follows established feature development process with lean, focused documents (100-150 lines max) that flow from general problems to specific scope.

Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge

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.

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.

Find, install, and configure Model Context Protocol (MCP) servers for OpenCode. Use when user asks about finding MCP servers, installing them, configuring OAuth, or troubleshooting MCP issues.

Configure and build Model Context Protocol (MCP) servers for Claude Code integration. Set up database, filesystem, git, and API connections. Build custom MCP servers with TypeScript/Python SDK, implement tools and resources, configure transports (stdio, HTTP), and deploy for production.

Configure CLAUDE.md project memory files for persistent context, coding standards, architecture decisions, and team conventions. Reference for the 4-tier memory hierarchy and quick-add commands.