By Liohtml
Design & frontend-taste skills — brief-aware design direction, image-to-code, redesign audits, design-reference image generation, and production UI engineering.
Builds production-quality UIs. Use when building or modifying user-facing interfaces. Use when creating components, implementing layouts, managing state, or when the output needs to look and feel production-quality rather than AI-generated.
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards, generate fresh standalone images for sections or detail views instead of cropping old ones, avoid lazy under-generation, avoid cards-inside-cards-inside-cards UI, and keep the hero clean, spacious, readable, and visible on a small laptop.
Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not always left-text / right-image), background-image freedom, varied CTAs, varied hero scales (giant / mid / mini minimalist), narrative concept spine, second-read moments, and a single consistent palette across all images. Optimized for landing pages, marketing sites, and product comps that developers or coding models can accurately recreate.
Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.
Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.
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.
One opinionated, deduplicated marketplace of the best Claude Code skills — distilled from five community skill repos (109 skills → 39 keepers) and regrouped into four discipline plugins: engineering · product · design · research.
This is a curation, not original work. Every skill keeps its original author and license — see NOTICE.md and PROVENANCE.csv. It was assembled by a small team of specialist reviewers (engineer, product/marketing, UX, repo expert) with a devil's-advocate pass to cut redundancy.
| Plugin | Skills | License | Focus |
|---|---|---|---|
engineering | 16 | MIT | Spec → plan → build → test → debug → review → harden → ship |
product | 13 | MIT | Discovery, strategy, prioritization, PRDs, pricing, metrics |
design | 6 | MIT | Anti-slop frontend taste, image-to-code, redesign, UI engineering |
research | 4 | CC-BY-NC-4.0 | Deep research, academic writing, peer review |
⚠️ Mixed licensing.
engineering,product, anddesignare MIT (commercial use OK).researchis CC-BY-NC-4.0 — non-commercial only, isolated in its own plugin so it can be dropped cleanly. SeeNOTICE.md.
# Add this marketplace (from GitHub)
/plugin marketplace add Liohtml/ultimate-skills
# …or from a local clone
/plugin marketplace add /path/to/ultimate-skills
# Then install the plugins you want
/plugin install engineering@ultimate-skills
/plugin install product@ultimate-skills
/plugin install design@ultimate-skills
/plugin install research@ultimate-skills # CC-BY-NC — non-commercial
Each skill activates automatically when its trigger matches your task; you can also name it explicitly (e.g. "use the strategy-red-team skill on this PRD").
| Skill | What it does |
|---|---|
spec-driven-development | Write a spec before coding when requirements are unclear or work is significant. |
planning-and-task-breakdown | Break a spec into ordered, independently verifiable tasks. |
incremental-implementation | Ship multi-file changes as small, safe vertical slices. |
test-driven-development | Drive logic and bug-fixes with tests; prove code works. |
debugging-and-error-recovery | Systematic root-cause debugging when things break. |
code-review-and-quality | Multi-axis review with severity labels before merge. |
code-simplification | Refactor for clarity without changing behavior. |
security-and-hardening | Harden input handling, auth, storage, and integrations (incl. LLM). |
performance-optimization | Measure-first optimization, budgets, Core Web Vitals. |
api-and-interface-design | Stable, contract-first API and module-boundary design. |
git-workflow-and-versioning | Commits, branching, conflicts, bisect-driven debugging. |
ci-cd-and-automation | Quality-gated build/deploy pipelines and rollout/rollback. |
doubt-driven-development | In-flight fresh-context adversarial review of key decisions. |
documentation-and-adrs | ADRs, READMEs, and changelogs that record context. |
browser-testing-with-devtools | Verify behavior in a real browser via Chrome DevTools MCP. |
karpathy-guidelines | Lightweight behavioral rules to avoid common LLM-coding mistakes. |
| Skill | What it does |
|---|---|
strategy-red-team | Steelman then attack a PRD/roadmap's load-bearing assumptions. |
opportunity-solution-tree | Torres-style discovery: outcome → opportunities → solutions → experiments. |
prioritization-frameworks | 9 frameworks (RICE, ICE, Kano, MoSCoW…) with formulas and when-to-use. |
pre-mortem | Imagine the launch failed; triage Tigers / Paper Tigers / Elephants. |
create-prd | 8-section Product Requirements Document. |
pricing-strategy | Pricing models, value metric, Van Westendorp, experiments. |
ab-test-analysis | Significance, sample size, SRM, guardrails → ship/extend/stop. |
north-star-metric | Define the NSM + input-metric constellation by business game. |
value-proposition | 6-part JTBD value-proposition design. |
competitor-analysis | Research-driven competitive landscape and differentiation. |
interview-script | Mom-Test / JTBD customer-discovery interview script. |
user-personas | Research-grounded personas with JTBD, pains, gains. |
intended-vs-implemented | Audit the gap between intended behavior and shipped code. |
npx claudepluginhub liohtml/ultimate-skills --plugin designProduct management skills — continuous discovery, strategy red-teaming, prioritization frameworks, PRDs, pricing, A/B analysis, positioning, and metrics.
Production-grade engineering skills for AI coding agents — spec, plan, build incrementally, test-drive, debug to root cause, review, harden, optimize, and ship.
Rigorous research & academic-writing pipelines — universal deep-research, multi-agent paper writing, peer-review simulation, and the full research orchestrator. Self-contained across the 4 research skills; some notes cite the upstream project's design docs for context only.
Editorial "Web Designer" bundle for Claude Code from Antigravity Awesome Skills.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Memory compression system for Claude Code - persist context across sessions
Marketing skills for AI agents — conversion optimization, copywriting, SEO, paid ads, ad creative, and growth