ultraship

Living Architecture Map — auto-generate Mermaid diagrams of your codebase

Deprecated - use the ultraship:brainstorming skill instead

Sprint workflow — structured pipeline from plan → build → test → review → ship → verify

Visual Regression Testing — screenshot comparison before and after changes

Deprecated - use the ultraship:writing-plans skill instead

Run all auditors and produce a ship-readiness scorecard

Deprecated - use the ultraship:executing-plans skill instead

Post-Ship Growth Intelligence — track SEO trajectory, uptime, deploy frequency, and project health

Safety guardrails — blocks destructive commands (rm -rf, DROP TABLE, force-push) and optionally restricts edits to a directory

Track bundle size, detect heavy dependencies, compare to previous builds

Post-deploy canary monitoring — verify production health, detect regressions after deployment

Learn From the Best — analyze patterns from any codebase and apply them to yours

Competitive X-Ray — compare your site against any competitor (tech stack, SEO, performance, security)

Content quality analysis (readability, keyword density, GEO scoring)

AI Build Cost Tracker — track how much AI costs per feature, task, and project

Demo-Ready Mode — clean up dev artifacts and prepare for demos/screenshots

Pre-flight checks then deploy (env validation, migrations, bundle size, ship audit, health check)

Detect unused and outdated dependencies

Health check a production URL (status, response time, SSL, security headers)

Diagnose and fix non-indexed pages using GSC and Bing data

Root cause investigation — structured debugging with module freeze, no fixes without evidence

Launch Day Autopilot — prepare Product Hunt, Twitter, LinkedIn, HN copy and launch checklist

Manage project learnings — save, search, prune, export knowledge that compounds across sessions

Instant Project Onboarding — generate a complete developer onboarding guide

Penetration testing — hack-test your app across web, API, browser, GitHub, and local code. Zero false positives.

Run Lighthouse performance audit with auto-fix

Static analysis for backend performance anti-patterns (N+1 queries, sync I/O, memory leaks)

Check URLs for redirect chains, loops, and mixed HTTP/HTTPS

Generate changelog, bump version, create GitHub release, publish to npm

Production Incident Commander — diagnose and recover from production outages

Sprint retrospective — analyzes git velocity, commit patterns, test health, and shipping cadence

Code review a pull request

Update CLAUDE.md with learnings from this session

Run security audit with auto-fix (dep audit, secret scan, OWASP, headers)

Run top 1% SEO strategy analysis with GSC, Bing, and GA4 data

Run SEO audit with AI visibility checks (GEO + AEO) and auto-fix

Uses Playwright MCP to smoke-test the running application in a browser. Dispatched by /ship for pass/fail verification.

Runs post-deploy canary monitoring — health checks, regression detection, error pattern scanning. Dispatched by /canary for production verification.

Use this agent when a major project step has been completed and needs to be reviewed against the original plan and coding standards. Examples: <example>Context: The user is creating a code-review agent that should be called after a logical chunk of code is written. user: "I've finished implementing the user authentication system as outlined in step 3 of our plan" assistant: "Great work! Now let me use the code-reviewer agent to review the implementation against our plan and coding standards" <commentary>Since a major project step has been completed, use the code-reviewer agent to validate the work against the plan and identify any issues.</commentary></example> <example>Context: User has completed a significant feature implementation. user: "The API endpoints for the task management system are now complete - that covers step 2 from our architecture document" assistant: "Excellent! Let me have the code-reviewer agent examine this implementation to ensure it aligns with our plan and follows best practices" <commentary>A numbered step from the planning document has been completed, so the code-reviewer agent should review the work.</commentary></example>

Runs competitive X-ray analysis comparing two sites. Dispatched by /compete for head-to-head comparison.

Runs post-ship growth intelligence check. Dispatched by /grow for growth metrics tracking.

Runs production incident diagnostics. Dispatched by /rescue for incident response.

Runs launch readiness audit on a project. Dispatched by /launch for launch preparation.

Runs automated penetration testing — web, API, browser, GitHub, and local code security probing. Dispatched by /pentest for vulnerability discovery.

Runs Lighthouse performance audit using the lighthouse-runner tool. Dispatched by /ship for scorecard generation.

Runs security audit — dependency vulnerabilities, secret scanning, and OWASP pattern detection. Dispatched by /ship for scorecard generation.

Runs SEO audit with AI visibility checks (GEO + AEO signals) on project files using the seo-scanner tool. Dispatched by /ship for scorecard generation.

Top 1% SEO strategist agent — analyzes GSC, Bing, and GA4 data to produce data-driven ranking strategies, keyword intelligence, and lead funnel plans. Dispatched by /seo-strategy.

Living Architecture Map — auto-generate Mermaid diagrams of your codebase. Use when user wants to visualize architecture, understand code structure, generate diagrams, or document system design.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Post-deploy canary monitoring — checks site health, detects regressions, monitors for errors after deployment. Use after deploying to verify production is healthy.

Learn From the Best — analyze patterns from any codebase and apply them to yours. Use when user wants to adopt best practices from another repo, compare code quality, or learn how top projects are structured.

Code review with principal-engineer-level depth. Reviews for correctness, performance, security, maintainability, and architecture. Use when completing tasks, reviewing PRs, or before merging.

Competitive X-Ray — analyze any competitor URL vs your site. Use when user wants to compare their site against a competitor, benchmark performance, or understand competitive positioning.

AI Build Cost Tracker — track how much AI is costing you per feature. Use when user wants to track AI spending, understand cost per feature, optimize AI usage, or budget their Claude/GPT costs.

Demo-Ready Mode — prepare your app for demos, screenshots, and presentations. Use when user wants to demo their app, take screenshots, prepare for a presentation, or clean up dev artifacts.

Pre-flight checks then deploy. Validates env vars, migrations, bundle size, runs /ship audit, then deploys via git push or platform CLI.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Create distinctive, production-grade frontend interfaces with top-tier product design and UI/UX quality. Use this skill when the user asks to build web components, pages, or applications. Combines product thinking, UX discipline, and creative visual design.

Post-Ship Growth Intelligence — track how your shipped product is performing. Use when user wants to check growth metrics, SEO trajectory, uptime, deploy frequency, or overall project health over time.

Safety guardrails — blocks destructive commands (rm -rf, DROP TABLE, force-push, git reset --hard) and optionally restricts file edits to a specific directory. Use when working on critical systems or when you want extra protection.

Diagnose and fix non-indexed pages using GSC and Bing Webmaster data. Finds exactly why each page isn't indexed and applies the fix.

Root cause investigation — structured debugging with module freeze. No fixes without investigation. Use when encountering any bug, error, or unexpected behavior.

Launch Day Autopilot — prepare everything for a product launch. Use when user wants to launch, go live, announce, or prepare for Product Hunt / Hacker News / social media launch.

Manage project learnings across sessions. Save, search, prune, and export learnings that compound over time. Use when user wants to record, recall, or share project knowledge.

Instant Project Onboarding — generate a complete onboarding guide for any project. Use when user wants to onboard a new developer, understand a new codebase, or generate project documentation.

Automated penetration testing — web, API, browser, GitHub, and local code. Zero false positives. Use when user wants to hack-test their app, find vulnerabilities, or run security pentesting.

Run Lighthouse performance audit with auto-fix for common issues. Use when user wants to check or improve site performance.

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Generate changelog from commits, bump version, create GitHub release, publish to npm. Use when user wants to release, publish, or ship a new version.

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Production Incident Commander — diagnose and recover from production incidents. Use when something is broken in production, site is down, errors spiking, or user reports a critical bug.

Sprint retrospective — analyzes git velocity, commit patterns, test health, and shipping cadence. Use after a sprint, at the end of the week, or when the user wants to reflect on progress.

Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project memory optimization".

Run security audit — dependency vulnerabilities, secret scanning, OWASP pattern detection, HTTP headers. Use when user wants to harden their project.

Run SEO audit (39 rules) with AI visibility checks — GEO (20 rules for AI bot access, snippet restrictions) and AEO (4 schema checks). Auto-fix included. Use when user wants to check or improve search visibility.

Top 1% SEO strategist — ruthlessly analyzes GSC, Bing, and GA4 data to dominate search rankings, win AI citations, and build lead funnels. Every recommendation backed by data.

Sprint workflow pipeline — chains plan → build → test → review → ship skills into a structured sprint. Use when starting a new feature or project iteration to follow the full lifecycle.

Use when executing implementation plans with independent tasks in the current session

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when implementing any feature or bugfix, before writing implementation code

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Visual Regression Testing — screenshot comparison before and after changes. Use when user wants to check for visual regressions, compare UI changes, or verify CSS/layout changes didn't break anything.

Use when you have a spec or requirements for a multi-step task, before touching code

Use when creating new skills, editing existing skills, or verifying skills work before deployment

2 hooks across 2 events