Audit unsafe blocks by verifying documented invariants, minimizing surface, and testing under sanitizers and Miri.
Reviews URLSession networking code for iOS/macOS. Covers async/await patterns, request building, error handling, caching, and background sessions.
Use when optimizing, refactoring, simplifying, automating, or making trade-offs could accidentally remove or weaken something the user explicitly asked for.
Use when mcp-language-server tools are available and you need semantic code intelligence for navigation, refactoring, or type analysis
Use when starting work in a project that uses minerva (a `.minerva/` directory exists at the project root, or the user has invoked any `minerva:` skill in this session), or when…
Refactor existing V2 code to follow ideal SOLID pattern. Use when user says "refactor", "fix violations", "cleanup V2", or "/v2-refactor
".
\"Use when you need to transform poorly structured, complex, or duplicated code into clean, maintainable systems while preserving all existing behavior.\".
Scientific validation protocol for verifying fixes work through observation, not assumption. Use when claiming a bug fix, code change, refactoring, or implementation is complete —…
Run a formal code review for safety, intent, and quality. Use to verify completed work before marking it done.
Use after implementation is complete to verify the code covers every requirement from the plan / design spec — runs alongside code-review as the second pass in the Code Review…
Orchestrator-workers generalization of verify-against-rubric to N=many artifacts against ONE locked rubric.
Confirms or rejects findings from review-llm-artifacts before deletes or risky refactors. Loads review-verification-protocol-style checks per finding.
요구사항을 체크리스트로 구조화하고 구현 충실도를 검증한다. 구현 전 요구사항을 [REQ-카테고리-번호] ID로 추출해 체크리스트를 만들고(checklist 모드), 구현 후 diff와 대조해 커버리지 갭을 심각도별로 보고한다(verify 모드).
Re-verify prior `/review-pr` findings on a linq2db PR against the current PR HEAD. Collects all prior reviews, parses findings by severity-ID, reruns code-reviewer and…
Use when designing or maintaining the shape of a repository's git history — choosing a branching model, deciding rebase vs merge, sizing commits, linking commits to tracker…
Delegate a coding task to the Mistral Vibe CLI (`vibe`) as a background implementer, then review its diff and land it yourself.
Run the vibe-to-production pipeline on any Python project. Assesses code quality, generates characterization tests, prioritizes refactoring targets, and dispatches BOI specs for…
Run /code-review on the current diff and post the findings as inline comments in VibeDiff, tagged as agent:reviewer.
Human review workflow for AI-generated GitHub projects with spec-based feedback, security review, and follow-up PRs from the Vibers service.
Refactor macOS SwiftUI views and scenes with strong defaults for small dedicated subviews, stable sidebar and selection structure, explicit command and toolbar ownership,…
Reviews vMCP code changes for known anti-patterns that make the codebase harder to understand or more brittle. Use when reviewing PRs, planning features, or refactoring vMCP code.
Оркестрация разработки фичи через SpecKit + Superpowers (speckit-команды). КЛЮЧЕВАЯ ФРАЗА АКТИВАЦИИ — «метод Void» (Void method, «по методу Void», «погнали по методу Void»): как…
Monitorea el repositorio GitHub actual en busca de PRs nuevos y ejecuta el code-review nativo de Claude Code sobre cada uno de forma secuencial.
Comprehensive PR review with multi-agent swarm specialization for security, performance, style, tests, and documentation
Comprehensive GitHub pull request code review using multi-agent swarm with specialized reviewers for security, performance, style, tests, and documentation.
Reviews WidgetKit code for timeline management, view composition, configurable intents, and performance.
Use when the user asks to create a refactoring plan from wiki documentation, generate implementation prompts, uses "/wiki-refactor", or wants DORA remediation planning.
Manage multi-file edits with Cascade coordination. Activate when users mention "multi-file edit", "edit multiple files", "cross-file changes", "refactor across files", or "batch…
Manage large-scale refactoring with Cascade coordination. Activate when users mention "large refactoring", "codebase migration", "architecture refactor", "major refactoring", or…
Reviews Wish SSH server code for proper middleware, session handling, and security patterns. Use when reviewing SSH server code using charmbracelet/wish.
Audit and fix visual hierarchy, spacing, color, and depth in web UIs. Use when the user mentions "my UI looks off", "fix the design", "Tailwind styling", "color palette" — from…
Review WooCommerce code changes for coding standards compliance. Use when reviewing code locally, performing automated PR reviews, or checking code quality.
Automatically execute all Tasks in a Feature. Creates an Agent Team with Worker/Verifier teammates, enables bidirectional communication via SendMessage, and handles Review &…
Findings-first review discipline for code, diffs, task plans, live workflow changes, and implementation evidence.
Focused task execution for persistent team workers. Use when implementing features, following scope constraints, using TDD red-green-refactor, validating with browser/API/unit…
Guide for refactoring code to improve quality without changing behavior. Use when refactoring, cleaning up code, reducing duplication, improving readability, or restructuring…
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and — from…
Use when completing tasks, implementing major features, or before merging to verify work meets requirements — from hamzabellouch/agent-skills
Best practices for agents managing PostHog skills via the MCP `skill-*` tools — how to discover, read, create, update, and refactor skills efficiently, especially large skills…
Create a git worktree for a new TASK. Use when starting a new feature, fix, or refactor task that requires isolated development.
Manages git worktrees for isolated feature development. MUST be used when: - A plan has been approved and implementation is about to begin - User says "implement", "let's build",…
Use when reviewing Wow framework code, PR diffs, or pre-merge changes involving aggregates, commands, events, sourcing, sagas, projections, command gateway, Query DSL, starter…
Core principles for writing simple, readable, and maintainable code. You MUST use this before generating, refactoring, or reviewing code to keep implementations simple, readable,…
Write production-grade Ash Framework code with lead-engineer precision. Use when creating Ash resources, domains, actions, policies, calculations, aggregates, or relationships.
Dispatch the wtf-code-reviewer agent after any lighthouse-guard implementation. Checks Chrome safety, rate limiting, TypeScript types, and async correctness.
Use BEFORE dispatching @kai on a greenfield build (no existing code) with estimated budget >4 hours. Walks GitHub spec-kit's constitution -> spec -> plan -> tasks -> analyze…
Review React code for unnecessary useEffect usage based on react.dev guidelines. Analyses code for useEffect anti-patterns and optionally applies fixes.
Delegate a coding task to the Z.AI ZCode CLI as a background implementer, then review its diff and land it yourself.
How to deliver pure executable code blocks and unified diffs with zero conversational commentary during automated refactoring tasks, enabling direct IDE parsing and cutting output…
Rebuild a feature as if the correct product architecture existed from day one — remove compatibility cruft, dead abstractions, and historical compromises instead of preserving…
Autonomous orchestrator that scans, refactors, and eradicates technical debt at the end of the development lifecycle to achieve a Zero Debt codebase / Orkestrator otonom untuk…
Comprehensive PR code review for OneKey monorepo. Use when reviewing PRs, code changes, or diffs — covers security (secrets/PII leakage, supply-chain, AuthN/AuthZ), code quality…
Use this skill when scoping a redesign or refactor — choosing which existing surfaces deserve full attention and which can be left mostly alone.
Protocol and playbook for refactoring bloated controllers, tangled views, and paying down technical debt in the AB-Socks project.
Use this skill whenever the user wants a coding task carried out by an AI coding agent or model that is NOT Claude — for example OpenCode, GLM, Qwen, DeepSeek, Kimi, MiniMax,…
Use when the user asks to refactor, clean up, simplify, modularize, deduplicate, rename, or improve the structure of existing code WITHOUT changing behavior.
Run an exhaustive adversarial code review only when the user explicitly requests an adversarial review or asks to use this skill.
Governs how the agent confirms a change actually works before declaring a task complete. Use this skill at the end of every implementation pass and whenever the agent is about to…
Orchestrates the end-to-end analysis workflow from planning through implementation and review to finalized results.
Agent が anpop notify CLI を使ってユーザーにリアルタイム通知を送信する。Use when: (1) Long-running tasks complete (build, test, refactoring, git operations), (2) User input required (questions,…