Loading...
Loading...
Found 1,194 Skills
Perform blunt, high-intensity code review in Ukrainian with a colloquial style inspired by Oleksandr Povoroznyuk. Use when users explicitly ask for a harsh/rough tone, slang-heavy feedback, or review comments "in style of Поворознюк", including optional profanity. Keep findings technically precise, actionable, and evidence-based.
Code review and quality analysis skill. Used to review code, identify potential issues, and provide improvement suggestions. Activated when users request code review, code quality analysis, or best practice recommendations.
This skill provides expert-level guidance for refactoring VS Code extension code. Use when extracting classes or functions, reducing code duplication, improving type safety, reorganizing module structure, applying design patterns, or optimizing performance. Covers systematic refactoring workflows, code smell detection, safe transformation techniques, and VS Code-specific patterns.
Validate specifications, implementations, constitution compliance, or understanding. Includes spec quality checks, drift detection, and constitution enforcement.
Run /check-quality, then fix the highest priority quality issue. Creates one fix per invocation. Invoke again for next issue. Use /log-quality-issues to create issues without fixing.
Comprehensive multi-stage code review using specialized subagents. Use when reviewing PRs with complex architectural impact, security concerns, or when thorough multi-perspective analysis is needed.
Pre-commit code quality review workflow. Use before committing changes to verify code quality, security, testing coverage, and adherence to project conventions. Supports both automated checking and interactive review modes.
Comprehensively reviews Python libraries for quality across project structure, packaging, code quality, testing, security, documentation, API design, and CI/CD. Provides actionable feedback and improvement recommendations. Use when evaluating library health, preparing for major releases, or auditing dependencies.
Execute implementation plan tasks with TDD workflow, auto-commit, and phase gates. Use when user says "build it", "start building", "execute plan", "implement tasks", "ship it", or references a track ID. Do NOT use for planning (use /plan) or scaffolding (use /scaffold).
Systematic 4-phase debugging: understand the failure, form hypotheses, test one change at a time, fix with confidence. Activate when tests fail unexpectedly, errors occur, behavior is wrong, or something that worked before is now broken. Triggers on: "debug", "why is this failing", "test failure", "unexpected error", "bug", "broken".
Respond to PR review comments with critical evaluation. Use when addressing code review feedback, responding to bot review comments (Gemini Code Assist, CodeRabbit, etc.), or handling PR suggestions. Fetches comments, evaluates each against project context, applies valid fixes, declines invalid suggestions with reasoning, and posts responses.
Orchestrate comprehensive code review across ~12 AI reviewers. 5 persona reviewers (Grug, Carmack, Ousterhout, Beck, Fowler) via Moonbridge, 4 domain specialists (security-sentinel MANDATORY, performance, data integrity, architecture) via Task, plus hindsight-reviewer and synthesis. Use when: code review, PR review, pre-merge quality check.