productivity▌

Role: RAG Systems Architect

Analyzes codebases to generate comprehensive architectural documentation with diagrams and implementation patterns. \n \n Auto-detects technology stacks (.NET, Java, React, Angular, Python, Node.js, Flutter) and architectural patterns (Clean Architecture, Microservices, Layered, MVVM, Hexagonal, Event-Driven, Serverless, Monolithic) \n Generates C4, UML, Flow, or Component diagrams at multiple abstraction levels showing subsystems, dependencies, and data flow \n Documents core components, layers

Iterative evaluation and refinement patterns for improving AI agent outputs through self-critique loops. \n \n Provides three core patterns: basic reflection (self-critique loops), evaluator-optimizer (separated generation and evaluation), and code-specific test-driven refinement \n Supports multiple evaluation strategies including outcome-based assessment, LLM-as-judge comparison, and rubric-based scoring with weighted dimensions \n Includes practical Python implementations with structured JSON

When agent sessions generate millions of tokens of conversation history, compression becomes mandatory. The naive approach is aggressive compression to minimize tokens per request. The correct optimization target is tokens per task: total tokens consumed to complete a task, including re-fetching costs when compression loses critical information.

Production-grade code standards emphasizing correctness, crash-safety, and Rust idioms over convenience. \n \n Prioritizes data integrity: crash on invalid state rather than corrupt data; assert invariants aggressively; handle all errors explicitly \n Rust-specific patterns: make illegal states unrepresentable, use exhaustive pattern matching and enums over strings, minimize allocations \n Comments document why , not what ; avoid temporal markers, AI conversation references, and code-repeating e

You are an elite Developer Productivity Analyst and Strategic Coach. Your goal is to analyze the user's OpenCode session history to generate a "OpenCode Insights" HTML report.

Python SQL toolkit and ORM with modern query builder, relationship mapping, and async support. \n \n Supports SQLAlchemy 2.0 modern API with type hints, select() queries, and Mapped[T] declarative models; includes async support via AsyncSession and AsyncSessionLocal \n Covers one-to-many and many-to-many relationships with eager loading patterns ( selectinload , joinedload ) to prevent N+1 query problems \n Integrates with FastAPI via dependency injection, Alembic for schema migrations, and conn

Production-ready skill for building beautiful terminal user interfaces with Go, Bubbletea, and Lipgloss.

Build, test, and automate Android applications using accessibility-driven navigation and structured data instead of pixel coordinates.

Search the web and extract content via inference.sh CLI.