🏗️ Architecture

Create production-quality Android applications following Google's official architecture guidance and NowInAndroid best practices. Use when building Android apps with Kotlin, Jetpack Compose, MVVM architecture, Hilt dependency injection, Room database, or multi-module projects. Triggers on requests to create Android projects, screens, ViewModels, repositories, feature modules, or when asked about Android architecture patterns.

Spec-driven development workflow. Interactive phase-by-phase confirmation from proposal to implementation. Trigger: 'spec-flow', 'spec mode', 'need a plan', 'structured development', 'write a spec', 'feature spec', 'technical spec', '需求文档', '技术方案', '任务拆解', '规格驱动', '写个方案', '做个规划', '结构化开发', 'plan this feature', 'break this down', 'design doc'. Creates .spec-flow/ directory with proposal, requirements, design, and tasks.

CONTEXT: Cognitive Order Normalized in Transformer EXtract Truncated. Cross-model context handoff via Progressive Density Layering, MLDoE expert compression, Japanese semantic density, and Negentropic Coherence Lattice validation. Creates portable carry-packets that transfer cognitive state between AI sessions. Use when context reaches 80%, switching models, ending sessions, user says save, quicksave, handoff, transfer, continue later, /qs, /context, or needs session continuity.

Every AI output has structural blind spots determined by the generation process itself. Future Tokens operations are named, composable instruments that target specific blind spots. They surface new information on every pass because expanding the output changes the blind spot geometry.

Build stateful AI agents and agentic workflows with LangGraph in Python. Covers tool-using agents with LLM-tool loops, branching workflows, conversation memory, human-in-the-loop oversight, and production monitoring. Use when - (1) building agents that use tools and loop until task complete, (2) creating multi-step workflows with conditional branches, (3) adding persistence/memory across turns with checkpointers, (4) implementing human approval with interrupt(), (5) debugging via time-travel or LangSmith. Covers StateGraph, nodes, edges, add_conditional_edges, MessagesState, thread_id, Command objects, and ToolMessage handling. Examples include chatbots, calculator agents, and structured workflows.

Interactive system flow tracing across CODE, API, AUTH, DATA, NETWORK layers with SQLite persistence and Mermaid export. Use for security audits, compliance documentation, flow tracing, feature ideation, brainstorming, debugging, architecture reviews, or incident post-mortems. Triggers on audit, trace flow, document flow, security review, debug flow, brainstorm, architecture review, post-mortem, incident review.

Autonomous quality engineering swarm that forges production-ready code through continuous behavioral verification, exhaustive E2E testing, and self-healing fix loops. Combines DDD+ADR+TDD methodology with BDD/Gherkin specifications, 7 quality gates, defect prediction, chaos testing, and cross-context dependency awareness. Architecture-agnostic - works with monoliths, microservices, modular monoliths, and any bounded-context topology.

Generate PlantUML diagrams from text descriptions and convert them to PNG/SVG images. Use when asked to "create a diagram", "generate PlantUML", "convert puml to image", "extract diagrams from markdown", or "prepare markdown for Confluence". Supports all PlantUML diagram types including UML (sequence, class, activity, state, component, deployment, use case, object, timing) and non-UML (ER diagrams, Gantt charts, JSON/YAML visualization, mindmaps, WBS, network diagrams, wireframes, and more).

Scientific research engine with agentic tree search. Infinite loops until discovery, rigorous tracking, adversarial review, serendipity preserved.

Build type-safe LLM applications with DSPy.rb - Ruby's programmatic prompt framework with signatures, modules, agents, and optimization

>

Build and extend brownfield features in an existing codebase. Use when a request requires understanding module dependencies, researching the latest official docs for current tech stacks/APIs/external dependencies, and implementing tested changes in a mature project. For multi-module changes, produce a PRD and obtain explicit user approval before coding.

Analyze, plan, review, and optimize any codebase across 4 modes: Discovery (understand architecture and risks), Review (validate changes and detect breaking changes), Optimization (find bottlenecks and vulnerabilities), Implementation Planning (generate step-by-step guidance). Works with React, Django, Rails, Go, Rust, and 30+ frameworks. Use when analyzing codebase structure, assessing feature safety, finding security issues, planning implementations, or discovering performance problems.

PRD-first feature development workflow that generates a PRD file from a reference template, captures requirements, business flow, clarification questions, and test plans, then waits for user confirmation before implementation. Use when users ask to design or implement new features, change product behavior, request a PRD-driven process, or ask for a greenfield feature that is complex and has no existing base (plan before action).

Use when the user needs to query, analyze, or collaborate with another project's codebase by spawning a second Claude CLI instance. Enables cross-project communication between a frontend and backend, microservices, or any two codebases. Triggers on phrases like "ask backend", "bridge to", "check the other project", "query project X".

Multi-model agent implementation workflow for software development. Orchestrates research, evaluation, design baseline, implementation, RCA, structured decomposition, constraint discovery, model selection, and agent-driven Stage 3 codemap exploration across external AI models (GPT, GLM, Claude). Use when implementing features through a structured multi-phase pipeline with worktrees, dynamic scheduling, and SQLite-backed agent coordination.

Use when designing, building, or reviewing a command-line interface (CLI) tool. Provides a checklist of standard CLI conventions. Do not use for non-CLI applications.

Expert SurrealDB 3 architect and developer skill. SurrealQL mastery, multi-model data modeling (document, graph, vector, time-series, geospatial), schema design, security, deployment, performance tuning, SDK integration (JS, Python, Go, Rust), Surrealism WASM extensions, and full ecosystem (Surrealist, Surreal-Sync, SurrealFS). Universal skill for 30+ AI agents.

Autonomous meta-orchestrator that continuously discovers work, dispatches agents, reviews results, and manages the full lifecycle across the user's workspace. Use when the user wants hands-off autonomous operation. Triggers on: 'autonomous', 'auto-pilot', 'run continuously', 'take over', 'autopilot'.

Install and integrate Tether's Wallet Development Kit (WDK) into any project. Supports Node.js, React Native, and browser environments. Use when the user wants to build self-custodial wallets, integrate multi-chain cryptocurrency support, or perform blockchain operations like sending transactions, token swaps, cross-chain bridges, or DeFi lending.