Loading...
Loading...
Found 817 Skills
Systematic debugging that identifies root causes rather than treating symptoms. Uses sequential thinking for complex analysis, web search for research, and structured investigation to avoid circular reasoning and whack-a-mole fixes.
Provides refactoring recommendations and step-by-step improvement plans. Use when planning refactoring, improving code structure, or reducing technical debt.
Technical solution evaluation and code review in the style of Linus Torvalds. Only use this when the user explicitly requests a Linus-style review or explicitly asks for a rigorous evaluation of code changes/technical solutions (e.g., "review changes/code", "evaluate if the solution is appropriate", "check submission standards", "linus-tech-review").
This skill guides systematic code refactoring following the DRY (Don't Repeat Yourself) principle. Use it when users request to eliminate code duplication, refactor repetitive code, apply the DRY principle, or mention code smells like copy-paste code, magic numbers, or repeated logic. It implements a 4-step workflow from identifying repetition to verified refactoring.
Run a comprehensive pull request review using multiple specialized agents. Each agent focuses on a different aspect of code quality, such as comments, tests, error handling, type design, and general code review. The skill aggregates results and provides a clear action plan for improvements. Triggers include "review PR", "analyze pull request", "code review", and "PR quality check".
Review one change set in one mode (`pr` or `local`) for correctness, security, tests, and scope, and return a clear go/no-go decision. Triggers: review pr, review local, readiness check, pre-merge review.
Use after code review - implement ALL findings; any finding not fixed MUST have tracking issue created; no finding disappears without trace
Detect hardcoded values, magic numbers, and leaked secrets. TRIGGERS - hardcode audit, magic numbers, PLR2004, secret scanning.
Use when pylint configuration including pylintrc, message control, plugins, and scoring system.
Use when reviewing or scoring AI-generated business/application code quality in any language, especially when a numeric score, risk level, or must-fix checklist is requested, or when C++ code must comply with OpenHarmony C++ and security standards
TypeScript-specific coding conventions and type system patterns. Always load this skill when writing or reviewing TypeScript code.
Intelligently analyze code changes and split them into multiple logical commits based on functionality and change types. This skill should be used when users want to commit code changes, especially when there are multiple unrelated changes in the working directory.