编辑、审查或改进现有营销文案时使用。触发词：edit this copy、review my copy、copy feedback、proofread、polish this、make this better、copy sweep。提供通过多次聚焦扫描系统化编辑营销文案的方法。

Review and edit copy for grammar, style, and clarity. Works with project style guides or uses sensible defaults. Use when reviewing marketing copy, blog posts, documentation, emails, or any business writing that needs polish.

Pre-computed action manuals for browser automation. Agents receive structured page information instead of parsing entire HTML.

Universal code quality rules. Extends nothing — this is the base skill every project should include. Use when writing or reviewing any code.

Core principles and project structure for React 19 SPA development. Covers stack overview, project organization, agent execution rules, and authoritative sources. Use when planning new projects, onboarding, or reviewing architectural decisions.

Code review and quality assurance specialist for ensuring code quality, security, and maintainability

Comprehensive testing and quality assurance specialist for ensuring code quality through testing strategies

Strategic review of your Resume Corpus against market data. Identifies high-demand skill gaps and strengthens your career story.

Review system costs and propose reductions. Use when a senior developer needs cost-saving recommendations.

1. 코딩 테스트 문제 풀이를 제출하면, 코드를 검토합니다.

Multi-model AI council for actionable project advice. Leverages Gemini 3 Flash and GPT-5.2 skills in parallel, then synthesizes through an Opus Judge for stage-appropriate, non-overkill recommendations. Use when seeking architectural guidance, code review synthesis, or implementation planning.

Comprehensive code review with both Codex (GPT-5.2) and Gemini for quality, security, and best practices.

Orchestrates multi-model LLM consensus through a three-phase deliberation protocol. Use when you need collaborative AI review, multi-model problem-solving, code review from multiple perspectives, or consensus-based decision making. Coordinates OpenAI Codex, Google Gemini, and Claude CLIs for opinion collection, peer review, and chairman synthesis.

council-review

Route code reviews to appropriate council members. Use when reviewing PRs, architecture decisions, or significant code changes that need expert perspective.

Simulate expert perspectives for code guidance, style, and debates.

Countdown - pre-implementation validation. Runs oracle (Opus) for planning, then Go Poll with review agents (Haiku) to validate before coding starts.

Expert guidance on writing in Chamath Palihapitiya's communication style across 5 formats (Annual Letters, Customer Briefs, Emails, Policy Ideas Briefs, Learn with Me Presentations). Use when helping with any writing task, document creation, editing, reviewing communications, or answering questions about how to write something. Includes 10 universal principles, format-specific playbooks, internal team email guidance, templates, decision frameworks, and quality control checklists. MODULAR ARCHITECTURE: Optimized for LLM consumption with selective context loading (core + format).

C++ coding standards and best practices.

Analyze code coverage and CRAP (Change Risk Anti-Patterns) scores to identify high-risk code. Use OpenCover format with ReportGenerator for Risk Hotspots showing cyclomatic complexity and untested code paths.

Meta-skill for generating SOP skills that autonomous agents can execute without human intervention.

Analyze git changes and create changesets for package releases. Use when preparing pull requests, creating PRs, when branch has commits ready for review, or when user mentions changeset or version bump.

Generate comprehensive coverage report with requirement traceability mapping. Shows coverage per REQ-*, gaps, trends, and recommendations. Use for status dashboards, quality reviews, or compliance audits.

Create a GitHub issue with extra review and triage detail; use when a thorough or multi-perspective issue write-up is needed.

Generate structured LaTeX exam cheat sheets from course materials. Extracts key concepts, definitions, formulas from PDFs, Jupyter notebooks, and markdown files. Compiles to PDF with error checking.

Scaffolds a new design in the design-inspirations repo with preview component, detail page, and main page entry. Use when creating a new design, adding a design inspiration, or scaffolding design files.

Create an Azure DevOps pull request using az devops tooling; include the repo’s linear-history merge preference and ask the Maintainer if merge options differ.

Create comprehensive GitHub pull requests with quality validation

Create and (optionally) merge a GitHub pull request (prefer GitHub chat tools; gh/wrappers are fallback), following the repo policy to use rebase and merge for a linear history.

Creates GitHub pull requests with properly formatted titles that pass the check-pr-title CI validation. Use when creating PRs, submitting changes for review, or when the user says /pr or asks to create a pull request.

Create GitHub pull requests with proper issue linking, comprehensive descriptions, and quality metrics for WescoBar project

Use to create QA task documents. Generates test specifications and validation requirements for QA team.

Build interactive CLI questionnaires with validation, conditional logic, parameter mapping, and review capabilities using the question-and-answer library

Detailed implementation guide for generating bug fix release notes from Jira and GitHub PRs

Generate review checklists for different change types. Use to customize review focus based on what was changed.

Use when creating or updating pull requests with comprehensive descriptions and meaningful commits - streamlines PR workflow with branch management and commit best practices

**YOU MUST NEVER add Claude Code attribution to pull requests.**

Use when creating a pull request or preparing changes for review. Ensures PR titles and descriptions accurately reflect ALL changes in the branch AND link to related GitHub issues. Prevents accidentally omitting files, changes, or issue references from PR descriptions.

Creates high-quality pull requests with comprehensive descriptions, test plans, and context. Activates when user wants to create PR, says 'ready to merge', or has completed feature work. Analyzes commits and changes to generate meaningful PR descriptions.

Establish workflow boundary checklists with clear pass/fail criteria and escalation procedures

Subagents are specialized AI instances with focused expertise, isolated context,

Use to verify creative assets meet brand, accessibility, and localization

Use when understanding and fixing common Credo check issues for Elixir code quality and consistency.

Use when configuring Credo static analysis for Elixir projects requiring customized code quality rules and settings.

Use when creating custom Credo checks for project-specific code quality rules and standards in Elixir.

Write data-driven, evidence-first long-form Twitter posts on medicine and cardiology. Use when the user wants to: (1) Create thought leadership content in the style of Eric Topol, Peter Attia, Andrew Huberman, or Rhonda Patrick, (2) Present clinical evidence with charts, data, and Q1 journal citations for educated non-specialist audiences, (3) Write confident, matter-of-fact medical content that is rigorous without being inaccessible, (4) Explain trials, drugs, or medical phenomena using data visualization and systematic evidence review, (5) Build authority through methodological rigor and clear conclusions backed by evidence. NOT for newsletters or Substack. For Twitter long-form posts only.

Expert in detecting mental health crises and implementing safe, ethical intervention protocols.