By amirudinR
The ultimate AI coding skill collection β covering the full development lifecycle: spec, plan, build, verify, review, ship, and more.
Senior code reviewer that evaluates changes across five dimensions β correctness, readability, architecture, security, and performance. Use for thorough code review before merge.
Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.
QA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.
Web performance engineer focused on Core Web Vitals, loading, rendering, and network optimization. Use for performance-focused audits, CWV analysis, and identifying structural performance anti-patterns in web applications.
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Instruments code so production behavior is visible and diagnosable. Use when adding logging, metrics, tracing, or alerting. Use when shipping any feature that runs in production and you need evidence it works. Use when production issues are reported but you can't tell what happened from the available data.
Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.
Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when deciding whether to maintain or sunset existing code.
Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
The Ultimate AI Coding Super-Skill
The first AI coding skill that covers the entire SDLC β from idea to shipped product, with YAGNI philosophy, TDD discipline, and design intelligence built in.
Ultra Skill is the first unified AI coding super-skill β a complete, professionally-crafted system that guides AI coding agents through the full software engineering lifecycle, from idea to shipped product. It combines battle-tested workflows, strict quality gates, a lazy senior dev philosophy, and an AI-powered design intelligence engine into one cohesive, plug-and-play skill collection.
Unlike fragmented toolkits that cover only one phase of development, Ultra Skill delivers everything you need:
| What You Get | Details |
|---|---|
| π§ 40+ Skills | Spec, plan, build, test, debug, review, ship, design β every phase covered |
| π§ 14 Slash Commands | One-command access to every workflow phase |
| π€ 11+ Platforms | Claude Code, Cursor, Windsurf, OpenCode, Gemini, Copilot, and more |
| βοΈ 3 Iron Laws | Non-negotiable quality gates enforced at every step |
| π΄ YAGNI Philosophy | Never write code you don't need |
| π¨ Design Engine | 67 UI styles, 161 color palettes, 22 tech stacks |
| π₯ 4 Agent Personas | Parallel review with dedicated specialists |
| Category | What You Get |
|---|---|
| π§ 40+ Skills | 11 categories covering the entire SDLC β spec, plan, build, test, debug, review, ship, and beyond |
| π§ 14 Slash Commands | One-command access to every workflow phase: /spec, /plan, /build, /test, /review, /ship, and more |
| π€ 11+ Platform Support | Claude Code, Cursor, Windsurf, Gemini CLI, OpenCode, Cursor, GitHub Copilot, Devin, Cline, Codex, Kiro, Antigravity, and more |
| βοΈ 3 Iron Laws | TDD, Verification, and Debugging β non-negotiable quality gates enforced at every step |
| π΄ 7-Rung Ponytail Ladder | YAGNI-first approach: ask "does this need to exist?" before writing a single line |
| ποΈ SPECβPLANβBUILDβVERIFYβREVIEWβSHIP | A structured lifecycle that turns chaos into a repeatable delivery pipeline |
| π¨ Design Intelligence Engine | 67 UI styles, 161 color palettes, 57 font pairings, 22 tech stacks β AI-powered design at your fingertips |
| π₯ 4 Agent Personas | code-reviewer, security-auditor, test-engineer, web-performance-auditor β parallel review with /ship fan-out |
| π§© Subagent-Driven Dev | Parallel agent dispatch with two-stage review (spec compliance β code quality) |
| π 7 Reference Checklists | Security, performance, accessibility, testing patterns, observability, definition of done, orchestration |
| πͺ Runtime Hooks | Session activation, mode tracking, status line, and lifecycle hooks for every major platform |
| Category | Skills |
|---|---|
| π§ meta/ | ultra-using-skills, ultra-writing-skills |
| π΄ philosophy/ | ultra-ponytail, ultra-yagni-audit, ultra-yagni-debt, ultra-impact-gain |
| π‘ ideation/ | ultra-brainstorming, ultra-interview-me, ultra-spec-driven-dev |
| π planning/ | ultra-planning, ultra-writing-plans |
| ποΈ implementation/ | ultra-incremental-impl, ultra-subagent-dev, ultra-parallel-agents, ultra-api-design, ultra-context-engineering, ultra-source-driven-dev |
| π§ͺ testing/ | ultra-tdd, ultra-browser-testing, ultra-doubt-driven-dev |
| π debugging/ | ultra-debugging, ultra-observability |
| β quality/ | ultra-code-review, ultra-code-simplify, ultra-performance, ultra-security, ultra-verify-before-done |
| π git-workflow/ | ultra-git-workflow, ultra-git-worktrees, ultra-finishing-branch |
| π¦ delivery/ | ultra-ci-cd, ultra-shipping, ultra-documentation, ultra-deprecation |
| π¨ ui-design/ | ultra-frontend-eng, ultra-ui-styling, ultra-design-system, ultra-brand-identity, ultra-banner-design, ultra-slides |
npx claudepluginhub amirudinr/ultra-skillHarness-native ECC operator layer - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Matt Pocock's agent skills for real engineering β grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review