NLP

Implement speech-to-text (ASR/automatic speech recognition) capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to transcribe audio files, convert speech to text, build voice input features, or process audio recordings. Supports base64 encoded audio files and returns accurate text transcriptions.

Use this skill when analyzing large codebases, multiple files, or directories that exceed context limits. Leverages Google Gemini's massive context window with @ syntax for file inclusion to handle comprehensive codebase analysis, implementation verification, and architectural understanding.

Parse and structure information from screenshots, meeting notes, or text, then save to Second Brain Supabase database. Extracts contacts, tasks, and ideas automatically. Use when user wants to save information for later.

Implement fixes for specific CodeRabbit review issues. Runs in isolated subagent context with focused task. Verifies fixes with tests before returning. Use one per issue from triage task list.

Create Architecture Decision Records (ADRs) documenting significant technical decisions for the FF Analytics platform. This skill should be used when making architectural choices, evaluating alternatives for data models or infrastructure, documenting trade-offs, or when the user asks "should we use X or Y approach?" Guides through the ADR creation workflow from context gathering to documentation.

User interface pattern. When Claude needs to create an editable text region that contains inline pills or tokens, along with the ability to add them using a mention menu.

Optimize input context for AI consumption using context engineering principles. Use when: (1) User wants to optimize content for AI/Claude explicitly, (2) User invokes with --foryou flag.

Guidelines for working with LLM context stored in the .llm/ directory.

Session state management, runtime state tracking, session handoff protocols, and context continuity for Alfred workflows

Applies Fabric AI prompt patterns for summarization, analysis, extraction, code review, and content creation. Use when asked to summarize content, analyze documents, extract insights, review code, create documentation, or transform text. Patterns are in data/patterns/.

Medical document OCR processing for extracting structured clinical data from medical images (prescriptions, lab results, clinical notes). Uses Google Cloud Vision for text extraction and medical NLP for entity recognition. Deploy when processing healthcare documents, extracting patient data, or converting medical images to structured formats.

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.

Guide for implementing client-side state management in React applications. Use when building state architecture, selecting state libraries (Context, Zustand, Redux, Jotai), implementing caching strategies (React Query, SWR), optimistic updates, state persistence, or optimizing re-renders. Triggers on questions about global vs local state, state normalization, or selector patterns.

Specialized codebase understanding agent for multi-repository analysis, searching remote codebases, retrieving official documentation, and finding implementation examples using GitHub CLI, Context7, and Web Search.

Ruthless concision for AI prompts and context - "Not One Word Wasted"

Guidance for configuring MCP servers in Claude Code projects. Covers transport selection, scopes, authentication, and security patterns. Use whenever adding MCP servers - projects, plugins, or any context.

MiniMax API via curl. Use this skill for Chinese LLM chat, text-to-speech, and AI video generation.

Enterprise Neon Serverless PostgreSQL Platform with AI-powered database architecture, Context7 integration, and intelligent branching orchestration for scalable modern applications

Creates README.md navigation maps for agent consumption. README IS the map - no human READMEs exist. Use when mapping directories, creating navigation structures, or preparing codebases for agentic workflows.

Process and validate bilingual content for Bulgarian and German language pairs, ensuring accuracy, consistency, and appropriate cultural context. Use for content creation, translation verification, and cultural adaptation.