NLP

Implement JSON-based structured logging for observability. Use when setting up logging, debugging production issues, or preparing for log aggregation (ELK, Datadog). Covers log levels, context, and best practices.

Enforce ThemeGPT complexity budgets and prevent over-engineering. Activates automatically when writing, reviewing, or refactoring code. Validates against 6 anti-patterns from SynthAI archaeology (Specification Inflation, Enterprise Pattern Obsession, Premature Abstraction, Configuration Explosion, Framework Absorption, Test Suite Inflation). Use when creating features, adding abstractions, writing tests, or configuring projects.

Build interactive AI chat widgets with buttons, forms, and bidirectional actions. Use when creating agentic UIs with clickable widgets, entity tagging (@mentions), composer tools, or server-handled widget actions. Covers full widget lifecycle. NOT when building simple text-only chat without interactive elements.

This skill should be used when the user asks about "token efficiency", "compress responses", "reduce token usage", "minimize context", "compact format", "token optimization", or discusses reducing token consumption in MCP responses while maintaining value.

CLI tool for OpenAI text-to-speech synthesis

Search and reference past conversations, plans, realisations, and insights from previous Claude Code sessions to maintain context continuity and avoid re-discovering solutions.

Guide for writing integration tests with Vitest and Testing Library. Use when testing multi-component workflows, database interactions, React components with context providers, or full user flows. Covers the Testing Trophy philosophy (integration > unit), factory patterns for test data, MSW for network mocking, async testing patterns (waitFor, findBy), and custom render with providers. Use this for tests that cross multiple modules or layers of the application.

Context-efficient MCP integration using code execution patterns. Use when building agents that interact with MCP servers, need to manage large tool sets (50+ tools), process large datasets through tools, or require multi-step workflows with intermediate results. Enables progressive tool loading, data filtering before context, and reusable skill persistence.

Download and aggregate web pages/docs into timestamped scratchpad files. Use when user asks to "concatenate all these resources", "get all these links", "checkout all these resources", or wants to gather fresh context from documentation URLs. All URLs from one prompt go into single file at docs/scratchpad/<timestamp>.md.

Extract and explain formulas used in Physical AI and Humanoid Robotics from text, lecture notes, or papers. Use when user asks to identify or understand relevant formulas.

Optimizes outputs by interpreting underspecified prompts before execution. Analyzes user input, infers missing context and specifications, then executes an enhanced version. Produces better results directly rather than outputting optimized prompt text.

Enterprise Frontend Development with AI-powered modern architecture, Context7 integration, and intelligent component orchestration for scalable user interfaces

Comprehensive guidance for the AIdev workflow system used for structured software project management with Claude Code. Covers AIdev commands (/constitution, /prd, /plan, /work, /check, /verify, /reflect, /new, /spec), file structure (spec/ directory with constitution, PRD, units), task execution with evidence-based completion, constitutional governance, quality gates, Single Source of Truth principle, Context Discipline, pre-implementation checks, task schema format, automation hooks, template management, and workflow sequences for feature planning and implementation. Use when working with spec/, creating product requirements, designing features, managing tasks, or validating project alignment.

Detects and removes AI writing patterns from text. Use when polishing drafts, cleaning AI-generated content, or ensuring writing sounds authentically human. Invoke with "run through slop detector", "clean this up", or "remove AI fingerprints".

Expert deployment automation for cloud platforms. Handles CI/CD pipelines, container orchestration, infrastructure setup, and production deployments with battle-tested configurations. Specializes in GitHub Actions, Docker, HuggingFace Spaces, and GitHub Pages.

Set up and use MCP (Model Context Protocol) servers to extend Claude Code capabilities including PRISM semantic memory, filesystem access, and database integration. Use when setting up MCP servers, debugging MCP connections, or understanding MCP tool usage.

Guide for implementing Google Gemini API image generation - create high-quality images from text prompts using gemini-2.5-flash-image model. Use when generating images, creating visual content, or implementing text-to-image features. Supports text-to-image, image editing, multi-image composition, and iterative refinement.

Persistent memory system for AI agents with semantic, episodic, and procedural memory types. Use when users want to (1) remember facts, preferences, or context across sessions, (2) track interaction history and experiences, (3) store reusable workflows or procedures, (4) build personalized agents that learn from conversations, or (5) implement any form of long-term memory for AI applications.

Retrieve and summarize current international and Singapore news stories with headlines, brief context, and source links in a professional executive format. Use when you need a quick daily news briefing with verified sources.

Use when you need to fully restore working context from a previous session - loads STATUS.json, reads key files, rebuilds mental model of current work state. Do NOT use for quick questions or when starting fresh unrelated work - the full context restoration adds overhead that isn't needed for standalone tasks.