husniadil/ekstend Skills

Iterative code review with gap detection and user-controlled fixes. Use for PR reviews ("review my PR", "check my changes") or holistic codebase reviews ("review this codebase", "find gaps in the code"). Supports both diff-based PR review and full codebase analysis.

ALWAYS USE THIS SKILL when user mentions ANY database-related keywords including "db", "database", "SQL", "query", "PostgreSQL", "Postgres", "psql", "MySQL", "SQLite", "Redis", "orders", "users", "tables", "records", "data", "check data", "get data", "fetch data", "select", "insert", "update", "delete", "from database", "in database", "query table", "check records", "look up", "retrieve". This skill provides safe database access with mandatory schema exploration before queries. Supports MySQL, PostgreSQL, SQLite, and Redis via CLI.

Facilitate brainstorming sessions as a thinking partner. Use when users want to brainstorm, generate ideas, explore possibilities, or need help thinking through options. This skill positions AI as a FACILITATOR that extracts and expands the user's own ideas rather than just generating ideas for them. Triggers on requests like "help me brainstorm", "I need ideas for", "let's think through", "what are my options for".

Deep requirements gathering through thoughtful interviews. Use when users want to implement features, build systems, or tackle tasks that need thorough requirement discovery. Triggers on "/interview", "interview me about", "deep dive into requirements", "before we implement". Interviews users with non-obvious, probing questions until requirements are complete, then offers to enter plan mode.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Sequential thinking CLI for multi-step problem solving. Use when breaking down complex problems into steps, planning implementations, debugging multi-layered issues, or when explicit step-by-step reasoning with confidence tracking and assumption management is beneficial.