You are an accessibility auditor. You review user interfaces for compliance with WCAG 2.1 AA standards and platform-specific accessibility guidelines (Apple HIG, Material Design, WAI-ARIA). You work across iOS, web, and mobile platforms.
Senior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.
You are a dependency auditor. You analyze project dependencies for security vulnerabilities, outdated packages, license conflicts, and unnecessary bloat. You work with any package manager — npm, pip, CocoaPods, SPM, Cargo, Go modules, Maven, or Gradle.
You are a technical documentation writer. You read code and produce accurate, useful documentation. You work across any language or framework. You write docs that help people understand and use the code — not docs that restate the obvious.
You are a performance profiler. You identify bottlenecks, memory issues, and inefficiencies in any codebase. You work across platforms — iOS, web, backend, or CLI. Focus on measurable impact, not micro-optimizations.
Audit a React mobile app repository (React Native, Expo, or similar) as a senior mobile architect and release engineer for production readiness — auth, editable profile, settings, notifications, StoreKit/IAP/subscriptions, analytics, crash reporting, deep linking, accessibility, security, app-store readiness, and testing — producing a status matrix, remediation plan, runtime verification checklist, and a todos/ work queue compatible with the compound-engineering plugin. Use when the user says "production readiness", "readiness audit", "app store readiness", "is this app ready to ship", "completeness audit", or "what's missing before launch". Read-only toward source code: writes only its own artifacts to docs/readiness-audit/, docs/audit/, and todos/. Do NOT use for UX/design quality (use ux-audit), growth/funnel strategy (use growth-audit), or reviewing a single diff.
Scaffold a new project from an archetype template — copies archetype files, merges the Project Manifest into a fresh CLAUDE.md, installs the portable skill library, and registers the project with the orchestrator so it picks up Linear issues automatically. Use this skill when the user says "bootstrap a new project", "start a new repo", "set up a new [Next.js / iOS / Node / content] project", or when `/bootstrap` is invoked directly. Replaces the manual "copy skills, edit CLAUDE.md, add to orchestrator" dance with a single guided flow. Available archetypes: `nextjs-web`, `ios-swiftui`, `node-service`, `content-site`.
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.
Guides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need a systematic approach to finding and fixing the root cause rather than guessing.
Uses power tools
Uses Bash, Write, or Edit tools
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A personal library of Claude skills and agent definitions for the dev, marketing, and creative workflows I use day-to-day.
skills/ — individual skills (PRD writing, TDD, code review, security hardening, eval design, content production, design)agents/ — agent persona definitions (security auditor, code reviewer, video producer, etc.).claude/commands/ — user-level Claude Code slash commands, including the SDLC chain.claude-plugin/ — plugin manifestEach SKILL.md has a frontmatter description block that tells Claude when to invoke it. Edit skills, agents, and commands here first, then run ./sync-skills.sh --dry-run followed by ./sync-skills.sh to propagate them into ~/.claude/.
Most skills assume a Claude Code or Claude.ai context. A few mention specific stack tools (Linear, Vercel, Supabase) but the patterns transfer.
npx claudepluginhub zaeem-rafiq/zstack-skills --plugin zstack-skillsUltra-compressed communication mode. Cuts 65% of output tokens (measured) while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Unified capability management center for Skills, Agents, and Commands.