NLP

Context management tools for Claude Code - provides intelligent codebase mapping with Python, Rust, and C++ parsing, duplicate detection, and MCP-powered symbol queries. Use this skill when working with large codebases that need automated indexing and context management.

Update and maintain Memory Bank files (activeContext, progress, decisionLog). Triggers: MB, memory, 記憶, 進度, 更新記憶, update memory, 記錄進度, 更新上下文.

Transcribe audio files with speaker diarization using VoxScriber. Use when the user wants to transcribe a meeting, podcast, interview, or any audio file, or when they mention "transcribe", "diarization", "who said what", "meeting transcript", or "audio to text".

Create or update comprehensive GitHub issues that capture ALL context, requirements, and implementation details. Use when creating or updating tickets, issues, feature requests, or bug reports. Ensures no context is lost between ticket creation and implementation - the moment you ask for a ticket, there's maximum context available that will be lost if not captured now.

M3-compliant UI components (buttons, cards, forms, inputs).USE WHEN: creating components <300 lines, M3 migrations, Design System work.NOT FOR: complete screens, features with business logic (use flutter-developer).Always validate M3 components with MCP tools before creating custom.Examples:<example>Context: Need to migrate a button component to M3.user: "Migrate BukeerButton to Material Design 3"assistant: "I'll use flutter-ui-components to migrate BukeerButton to M3."<commentary>UI component migration is flutter-ui-components specialty.</commentary></example><example>Context: Create a new reusable form field.user: "Create a new date picker input component following M3"assistant: "I'll use flutter-ui-components to create the M3-compliant date picker."<commentary>Single UI components should be handled by flutter-ui-components.</commentary></example>

Analyze videos using Google's Gemini API - describe content, answer questions, transcribe audio with visual descriptions, reference timestamps, clip videos, and process YouTube URLs. Supports 9 video formats, multiple models (Gemini 2.5/2.0), and context windows up to 2M tokens (6 hours of video).

Comprehensive guide for building functional tools for LiveKit voice agents using the @function_tool decorator. Use when creating tools for LiveKit agents to enable capabilities like API calls, database queries, multi-agent coordination, or any external integrations. Covers tool design, RunContext handling, interruption patterns, parameter documentation, testing, and production best practices.

⚡ PRIMARY TOOL for: 'why is X broken', 'find bug source', 'root cause analysis', 'trace error', 'debug issue', 'find where X fails'. Uses claudemem v0.3.0 AST with context command for call chain analysis. GREP/FIND/GLOB ARE FORBIDDEN.

Coordinate all subagents in the Physical AI & Humanoid Robotics textbook project. Assign tasks, validate outputs, and track progress to determine eligibility for extra points and reusable intelligence.

Context-driven development methodology. Understands projects set up with Conductor (via Gemini CLI or Claude Code). Use when working with conductor/ directories, tracks, specs, plans, or when user mentions context-driven development.

Expert in PDF content extraction and analysis. **Use whenever the user mentions PDFs, .pdf files, or requests to extract, read, parse, analyze, convert, or process PDF documents.** Handles text extraction, image extraction, converting PDFs to markdown or other formats, batch PDF processing, and analyzing PDF document structure for AI processing. Uses a fast Go binary with Vertex AI Gemini for intelligent image analysis. Supports two methods - preferred binary-based extraction (default) and alternative image-based extraction (when explicitly requested). (project, gitignored)

Manages session state and context handoffs for multi-session projects using the Session Handoff Protocol. Creates and maintains SESSION.md to track phase progress, git checkpoints, and next actions across context clears. Integrates with project-planning skill to convert IMPLEMENTATION_PHASES.md into trackable session state. Use when starting new projects after planning, resuming work after context clear, or managing complex multi-phase implementations.Keywords: session management, SESSION.md, session handoff protocol, context handoff, multi-session projects, phase tracking, git checkpoints, session state tracking, resume work, context clear, phase progress tracking, implementation phases, verification stage, debugging stage, next action tracking, work continuity, session recovery, context management, phased implementation tracking

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Given an API description and a docs bundle (e.g. from skill.context7_docs), generate a MOVA skill skeleton for a connector: ds/env schemas, manifest, prompt profile, runtime binding stub, cases, and docs.

Pattern for efficiently exploring codebases using parallel subagents. Use when you need to understand code structure, find patterns, or gather context.

Automatically detects Jira issue mentions (EC-1234, IS-8046, URLs) and intelligently fetches context via jira-analyzer subagent when needed for the conversation

Enterprise EARS (Evaluate, Analyze, Recommend, Synthesize) Framework with AI-powered requirements engineering, Context7 integration, and intelligent solution orchestration for systematic problem-solving

Normalize raw innovation ideas into structured backlog entries for the CustomGPT.ai Labs Innovation workbook, using consistent Why/How/What, success metrics, and ownership fields.

Capture conversation summaries and web content to daily notes. Use when user says "save this", "summarize", "capture notes", or pastes a URL without context.

Create product requirement documents when user wants to plan features, write specs, or document new functionality. Supports minimal core features, focused expansions, and task-based changes. Automatically loads context from related PRDs to maintain consistency.