Convert Roc code to idiomatic Elixir. Use when migrating Roc platform-based applications to Elixir/BEAM, translating statically-typed functional code to dynamic functional style,…
Convert Roc code to idiomatic F#. Use when migrating Roc projects to F#, translating Roc patterns to idiomatic F#, or refactoring Roc codebases.
Convert Roc code to idiomatic Scala. Use when migrating Roc projects to JVM/Scala, translating pure functional patterns to object-functional hybrid, or refactoring Roc codebases.
Delegate a coding task to the GitHub Copilot CLI (`copilot`) as a background implementer, then review its diff and land it yourself.
Arquitetura de debate multiagente com verificacao simbolica (Cora: Cognitive ORchestrated Argumentation).
Domain, UseCase, Service, Command, Query 클래스를 구현할 때 반드시 사용. 도메인 로직, 비즈니스 로직, 서비스 구현 시 TDD(Red-Green-Refactor) 방식으로 진행.
Get a help or a second opinion from other agents. Bundle a prompt and a curated file set, then ask other LLMs for advice (debug, refactor, design, ...).
Canonical reference for yellow-council CLI invocation, redaction, and output-parsing conventions. Use when authoring or modifying gemini-reviewer, opencode-reviewer, or the…
Map module coupling via import graph analysis. Identifies high fan-in (many callers) and high fan-out (many dependencies) nodes, and surfaces cycles.
中文优先：用于C++codingstandards相关任务，帮助识别、设计、实现或验证对应工作流。English keywords: C++ coding standards based on the C++ Core Guidelines (isocpp.github.io).
AUTOSAR C++14およびCERT C++コーディング規約に準拠したC++14コードレビュー。安全性重視のC++システムのコードレビュー、セキュリティ監査、品質評価、静的解析ツール設定を行う際に使用。
Analyze changed code for complex, under-tested functions using CRAP scoring; produce ranked refactor and test recommendations.
Design command-line interface parameters and UX: arguments, flags, subcommands, help text, output formats, error messages, exit codes, prompts, config/env precedence, and — from…
Use when creating, scaffolding, or refactoring a Rails engine. Covers engine types (Plain, Railtie, Engine, Mountable), namespace isolation, host-app contract definition — from…
Create or update a living ExecPlan under docs/exec-plans/active/ for any feature, migration, investigation, or refactor that spans multiple files or requires design choices.
Create comprehensive implementation plan in .plans directory based on analysis or report. Use when user asks to create a plan, plan implementation, design a solution, or structure…
Create a new business use case (Request + UseCase + Test) following TDD workflow. Use when user asks to implement new business logic, domain operations, or create…
Create a well-structured GitHub Issue following the project template. Use when the user wants to file a new Issue for a feature, bug, refactoring, docs change, or AI config change.
Creates isolated git worktrees in .claude/worktrees/ with intelligent branch naming, auto-incrementing, and commit type detection (feat/fix/refactor).
Tạo file SKILL.md hoàn chỉnh cho Claude Code từ bất kỳ workflow nào, phiên đã thực thi hoặc ý tưởng mới.
Review code changes in crit's multi-file TUI with syntax highlighting and diff markers. After the review, address any comments.
Perform critical code review with automated fix suggestions. Use when reviewing code changes, pull requests, specific files, or branch diffs.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my…
Curmudgeonly engineering advisor that provides grounded skepticism, evidence-linked judgment, and constructive progress on architectural decisions, legacy refactors, tooling…
Analyzes code diffs and files to identify bugs, security vulnerabilities (SQL injection, XSS, insecure deserialization), code smells, N+1 queries, naming issues, and architectural…
refactor 流程的超轻量通道——直接识别 1-3 条低风险优化、一次确认、原地改、跑测试自证。触发：用户说"快速重构"、"小重构"、"简单优化下 XX 函数"、"别那么多步骤"，且改动在单函数 / 单组件局部、有测试可自证。
Advanced Cursor Composer techniques: agent mode, parallel agents, complex refactoring, and multi-step orchestration.
Read-only delegate to cursor-agent (Composer) for questions, investigation, design discussion, and adversarial sanity checks.
Master Cursor Composer for multi-file AI editing, scaffolding, and refactoring. Triggers on "cursor composer", "multi-file edit", "cursor generate files", "composer workflow",…
Delegate a coding task to the Cursor Agent CLI (`cursor-agent`) as a background implementer, then review its diff and land it yourself.
Best practices for agents managing PostHog skills via the MCP `llma-skill-*` tools — how to discover, read, create, update, and refactor skills efficiently, especially large…
Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading.
Apply when sequencing an addition, refactor, or rewrite. Remove dead weight, redundant validators, and stub references first, then build on the simpler base.
Use this agent when a major project step has been completed and needs to be reviewed against the original plan and coding standards.
Use when completing tasks, implementing major features, or before merging to verify work meets requirements — from KunanonJ/ai-skills-hub
[AI & Tools] Create, verify, or enhance Claude Code custom agents (.claude/agents/*.md). Triggers on: create agent, new agent, agent schema, audit agent, verify agent, review…
Creates custom React hooks for SideDish. Use when the user asks to create a new hook, extract shared logic into a hook, or refactor component logic into reusable hooks.
Cyclomatic complexity measurement for JavaScript/TypeScript. Function complexity scoring, threshold enforcement, refactor detection, and per-file complexity reports.
Use when adding, refactoring, or auditing TUI code in daft — pickers, inline renderers, modal screens, key handling, terminal lifecycle, or anywhere `enable_raw_mode` /…
Generate a daily code review report showing stale PRs, items needing your attention, and active work for your team.
Apply Dart 3 language features including patterns, sealed classes, switch expressions, records, and if-case syntax.
Guidelines and best practices for refactoring consecutive prints, single-line string concatenations, and complex output blocks into triple-quoted multi-line string literals ('''…
Use when planning a product feature, fix, or prioritization task where Pendo usage data, signals, issues, or customer feedback could ground the plan in real product behavior —…
Analyze and Refactor TypeScript data models. Detect duplication, improve type safety, and validate relationships in interfaces/types.
DBIO-Klassenpattern mit CAG (Class::Accessor::Grouped). Nutze wenn du DBIO-Klassen baust oder refactorst.
Remove duplicated code and tech debt by keeping code DRY. Use when asked to de-duplicate logic, extract shared utilities, or refactor repeated patterns ("keep code DRY", "remove…
Use when the user asks about unused code, cleanup, deleting files or exports, refactoring old areas, reducing bundle size, code hygiene, technical debt, or maintenance in a…
Use when removing, flagging, or evaluating any code that appears unused, unreferenced, or commented out — before deletion
Safely remove dead code left by agents or refactors. Use when deleting exports, unused files, or Chinese "删死代码", "unused", "安全删除". Evidence before delete.
Use when the user asks to design or refactor a declaration contract, such as a function signature, type shape, schema, or generic parameter list, and wants guidance on grouping,…
Identify misplaced files and organize project structure following open-source best practices, while delegating refactoring to specialized skills
Analyze large source files and produce decomposition plans, optionally executing refactoring with import updates and test verification
Aciona o Revisor Profundo (sub-agent) pra tasks sensíveis — lê código além do diff antes da Mariana
Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by deepening shallow modules.
Use when refactoring into deep modules, choosing seams, classifying dependencies, deciding adapter strategy, or planning tests around a refactor.
Reviews Deep Agents code for bugs, anti-patterns, and improvements. Use when reviewing code that uses create_deep_agent, backends, subagents, middleware, or human-in-the-loop…
Development workflow for features, bugs, refactoring. Auto-activates for multi-file implementations. — from engineering/code-quality
Manifest builder. Plan work, scope tasks, spec out requirements, break down complex tasks before implementation.
Use as the mandatory front door for ALL planning, brainstorming, design, and "let's build/add/change/plan X" work — including prompts that claim the problem statement is already…
Generates a Mermaid dependency graph showing import relationships between modules. Use when analyzing coupling, finding circular deps, or planning refactors.