code▌

A disciplined approach to writing code that communicates intent, minimizes surprises, and welcomes change. Apply these principles when writing new code, reviewing pull requests, refactoring legacy systems, or advising on code quality improvements.

Generate production-ready Python code for Dataverse SDK with error handling and best practices. \n \n Implements comprehensive error handling using DataverseError hierarchy with retry logic and exponential backoff for transient failures \n Enforces singleton client pattern for connection management and includes structured logging for audit trails and debugging \n Applies OData optimization techniques: server-side filtering, column selection, and pagination to reduce data transfer \n Provides typ

Export Pencil .pen designs to production React/Tailwind code.

PostgreSQL code review assistant covering JSONB, arrays, custom types, schema design, and security best practices. \n \n Reviews JSONB operations for indexing efficiency, array usage with GIN indexes, and proper containment operators \n Evaluates schema design including ENUM types, CITEXT for case-insensitive data, TIMESTAMPTZ usage, and CHECK constraints \n Identifies anti-patterns in function optimization, trigger design, and extension usage \n Assesses Row Level Security (RLS) implementation,

Code review and refactoring guidance based on Robert C. Martin's Clean Code principles. \n \n Covers nine core areas: meaningful naming conventions, function design (size, single responsibility, argument limits), comment best practices, formatting standards, object and data structure patterns, error handling strategies, unit testing discipline, class design, and code smell identification \n Provides actionable guidance for writing new code, reviewing pull requests, refactoring legacy code, and e

Use this skill for the specific workaround where Claude Code keeps its Anthropic-shaped client behavior, but the actual backend traffic is sent to a local LiteLLM proxy and then forwarded to GitHub Copilot.

Extract and recover content from Claude Code's session history files stored in ~/.claude/projects/.

Autonomously analyze the entire codebase to understand its architecture, patterns, and purpose, then systematically transform it into production-grade, corporate-level professional code. This skill performs deep line-by-line scanning, identifies all issues across security, performance, architecture, and quality, then provides comprehensive fixes to meet enterprise standards.

$22

CRITICAL SKILL - Be concise, direct, and solution-focused.