../../../engineering/pr-review-expert/SKILL.md

Cria Architecture Decision Records (ADRs) para decisões técnicas. Inclui alternativas, justificativa e consequências.

Enforces an opinionated UI baseline to prevent AI-generated interface slop.

Use when designing new system architecture, reviewing existing designs, or making architectural decisions. Invoke for system design, architecture review, design patterns, ADRs, scalability planning.

Use when creating or planning weekly GitHub Issues from github-projects/week*_issues_complete.csv or similar weekly CSV files and adding them to a GitHub Project. Trigger for tasks that mention GitHub Projects, weekly issues, week_n labels, CSV issue files, sprint/week setup, repository/project issue import, or adding the corresponding week's issues to a project with gh CLI.

Orquesta notificaciones de NEXO AV hacia Microsoft 365 manteniendo trazabilidad en el ERP. Use when implementing or reviewing Outlook, Teams or Power Automate notifications for planning, assignments, visits, ready-to-invoice states, incidents or approval requests that must stay linked to ERP tasks and notifications.

**Tier:** POWERFUL

GitHub operations via gh CLI for pull requests/PRs, GitHub code search, and drafting exact gh commands. Always use instead of WebFetch for github.com.

Maintain and debug existing LabOne Q experiment/analysis workflows in this repository. Use for bug fixes, review follow-ups, and minor behavior changes under qubit_experiment/, experiments/, analysis/, and qpu_types/.

Manage — When the user wants to edit, review, or improve existing marketing copy. Also use when the user mentions

Code Reviewer — Protocols and standards for performing thorough, structured code reviews. Covers the reviewer's core mandate, step-by-step review protocol, and all review lenses: security (secret scanning), code quality (SOLID, DRY, KISS), architecture (Separation of Concerns, Atomic Design), and testing (AAA pattern). Use when reviewing pull requests, merge requests, or any code changes across any language or framework.

Create a concise pull request with conventional commit title, summary, and labels

Review the current diff for bugs, security issues, and code quality concerns

Essay and writing review with structure analysis, coherence checks, and style improvement

Use when work is ready to push and open a pull request, or when asked to create/submit a PR.

Integrate the Kodus CLI with AI coding agents for autonomous review-fix loops.

Thirteen agent personas live in `.claude/agents/` for use with Agent Teams.

Code simplification suggestions — clarity, unnecessary complexity, redundant

Review completed implementation work and update task status.

Run a comprehensive code review on recent changes using the code-reviewer and security-reviewer agents

Orchestrates Story tasks. Prioritizes To Review -> To Rework -> Todo, delegates to ln-401/402/403/404. Sets Story to To Review when all tasks Done. Metadata-only loading.

Full project audit orchestration - Architecture + Security + Code Quality → consolidated report → optional remediation. Use when user invokes /audit command, for pre-release health checks, when onboarding to an unfamiliar codebase, for periodic project quality reviews, or before/after a major architectural change. Covers scope detection, severity aggregation, report format, health scoring, and remediation routing.

>

Comprehensive Git workflow automation including branching strategies, pull request creation, code reviews, merge strategies, and release management. Use when Claude needs to help with Git operations, branching models (Git Flow, GitHub Flow), pull request creation, code reviews, merge conflicts, or release processes.

>-

Run the AI Voice Analyzer on blog content to detect AI-sounding patterns and get actionable rewrite suggestions. Use when reviewing or improving blog articles before publishing.

This skill should be used when documenting significant technical decisions, reviewing past architectural choices, or establishing decision processes. It provides ADR templates and best practices.

Track and evaluate AI predictions over time to assess accuracy. Use when reviewing past predictions to determine if they came true, failed, or remain uncertain.

Start the multi-AI pipeline with a given request. Guides through plan -> review -> implement -> review workflow.

Use when scanning code, skills, dependencies, or configurations for security vulnerabilities, threat modeling, secrets exposure, insecure defaults, auth issues, and hardening opportunities.

Start work on a new PR — review context and propose a mid-level approach

Best practices and patterns for generating clean, secure, maintainable code

Reference for agents working with the workflow checkpoint system.

Generate or review least-privilege MCP configs for this project.

Describes the sub-agent pipeline: task-decomposer breaks a task into subtasks, task-worker implements them, work-reviewer checks the result; on issues feedback goes back to the worker. Use when orchestrating multi-step work with task-decomposer, task-worker, and work-reviewer agents, or when the user asks how these agents work together.

Commit, push, branch, and manage version control with GitButler. Use for: commit my changes, check what changed, create a PR, push my branch, view diff, create branches, stage files, edit commit history, squash commits, amend commits, undo commits, pull requests, merge, stash work. Replaces git - use 'but' instead of git commit, git status, git push, git checkout, git add, git diff, git branch, git rebase, git stash, git merge. Covers all git, version control, and source control operations.

Brand voice, visual identity, messaging frameworks, asset management, brand consistency. Activate for branded content, tone of voice, marketing assets, brand compliance, style guides.

Translates discovery and product design artifacts into implementation-ready backend specifications. Produces API contracts (OpenAPI), schema design, auth model, and integration point specs for human r

Goal: build a skill that finds real vulnerabilities while minimizing false positives.

Rosetta ad-hoc adaptive meta-workflow that constructs, tracks, reviews, and executes a tailored execution plan per user request. Use when no other specific workflow matches the request.

Performs a structured engineering code review focusing on design quality, coupling, performance (especially mobile), and maintainability. Use when the user asks to review code, 检查代码, 审阅代码, 代码评估, or analyze code design/quality.

Autonomous PR creation from a worktree branch.

Reviews code changes with findings-first output focused on correctness, security, regression risk, and test gaps. Use when reviewing diffs, commits, pull requests, or when the user asks for a code review.

Reviews UI foundation, UI generation, and frontend implementation outputs or produced frontend code for consistency, usability, accessibility, responsiveness, correctness, and implementation readiness, then produces a structured QA verdict with required revisions.

Test Architect & Quality Advisor (Quinn). Use for comprehensive test architecture review, quality gate decisions, and code improvement. Provides thorough analysis including requ...

Review a change set for correctness, regressions, security risks, and test coverage gaps.

Generate or update backend CRUD slices for SeeSpec ABP/.NET 8 features. Use when adding or changing a domain entity and its full backend path: Core entity, EntityFrameworkCore registration, DTOs, application service, service interface, permission hooks, migrations checklist, and related documentation/tests.