Strategic checkpoint primitive – invoke at high-leverage moments to consult the Opus 4.7 advisor agent for a short course correction. Use early in a task (before substantive work), before declaring done, when stuck, or when changing approach. Quotes Anthropic's advisor-tool docs verbatim for timing and treatment.
Sets up a specialized agent pipeline for AI-assisted development with context analysis, planning, implementation, and auditing phases. Use when configuring agent-driven development workflows for a new project.
Generates and maintains a comprehensive CLAUDE.md file for any project. Use when setting up a new project, when the project has evolved significantly, or when switching tech stacks.
Stack-agnostic component gallery scaffolder and updater. Creates a single-page visual catalog of every component in the project (all variants, source-labelled, real production styles). Adapts to the project's framework via context7 MCP – never carries a hardcoded stack table. Used by frontend-implementer to keep the…
Automates Git workflow – commits, branches, PRs, and merges. Use when committing changes, or invoked automatically during plan execution after each approved phase. Do NOT use for Git concept education; see the github-for-designers.md reference instead.
Guides setup of essential MCP integrations for AI-assisted development. Use when configuring a new development environment or choosing which MCP servers to install.
Generates a single-file HTML prototype directly in Claude Code. One-pass approach: gather context, agree on a brief, generate the interactive prototype, iterate. Use for new products (after planning), new features for existing products, or redesigns. Pulls design context from planning documents or Figma designs.
Generates kick-start prompts for beginning development in any IDE. Use when transitioning from planning to coding or when starting a new project and needing structured initial prompts.
Teaches and implements context management for long-running development projects. Use when context loss becomes a problem or when setting up status tracking for AI-assisted workflows.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Documents knowledge and engineers context for design projects. Stores project status, maintains living context files, and tracks cross-deliverable dependencies. Use when completing a major phase or when context needs to be preserved across sessions. Do NOT use for development context management; see…
Controls the full design pipeline across discovery, strategy, planning, and validation phases. Manages autonomous, guided, and direct access modes while tracking project state. Use when running the end-to-end design workflow via /design-engineer:discovery.
Smart entry point for the design-engineer plugin. Detects project state and routes to the right flow: new projects get full setup, returning projects resume where they left off, existing projects get a capability guide. Use as the first command for any project.
Installs, uninstalls, or checks the design-engineer status line. Copies the statusline script to /.claude/hooks/ and configures settings.json. Use when running /design-engineer:launch.
Explores cognitive biases and self-perception psychology principles (Laws 81-90) for UX design. Covers thinking errors that affect both users and designers. Use when auditing interfaces for knowledge gaps, planning fallacies, or survey and research validity. Do NOT use for design-level UX audits (see ux-bias-audit) or…
Explores cognitive interaction fundamentals (Laws 1-10) for UX design. Covers cognitive load, choice architecture, information grouping, and discoverability. Use when analyzing how an interface manages mental effort and attention. Do NOT use for navigation simplification or form reduction; see psych-simplification…
Explores core decision-making psychology principles (Laws 21-25) for UX design. Covers loss aversion, decision fatigue, anchoring, and defaults. Use when auditing interfaces where users must choose between options, such as pricing, forms, or filter systems. Do NOT use for social proof, scarcity, or persuasion tactics…
Explores advanced decision-making psychology principles (Laws 26-30) for UX design. Covers persuasion, scarcity, social proof, and the boundary between ethical influence and manipulation. Use when auditing pricing pages, urgency tactics, or social proof elements. Do NOT use for basic decision fatigue, defaults, or…
Explores foundational emotional design psychology principles (Laws 41-45) for UX design. Covers how peak moments, micro-delighters, and perceived effort shape user memory and value. Use when auditing emotional touchpoints, celebration moments, loading states, or personalization flows. Do NOT use for retention…
Explores advanced emotional design psychology principles (Laws 46-50) for UX design. Covers responsible emotional triggers for retention, re-engagement, and comprehension. Use when auditing trial-to-paid conversion, re-engagement campaigns, or narrative onboarding flows. Do NOT use for in-moment delight, loading…
Explores engagement and motivation psychology principles (Laws 31-40) for UX design. Covers flow states, variable rewards, triggers, and feedback loops. Use when auditing onboarding flows, gamification, retention mechanics, or notification systems. Do NOT use for social dynamics or group behavior; see…