all publishers

MarcoAntolini

@marcoantolini source repo

28 published skills

  1. ▌
    Design Taste Frontend · marcoantolini
    Anti-slop frontend skill for marketing landing pages, portfolios, and promotional redesigns only — not dashboards, data tables, or multi-step product UI (use impeccable for those). Reads the brief, infers design direction, ships non-templated interfaces. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
    1 repo stars
  2. ▌
    Caveman 2 · marcoantolini bundle
    Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
    1 repo stars
  3. ▌
    Readme Wizard 2 · marcoantolini bundle
    Generate a polished, professional README.md for any project — from scratch or by improving an existing one. Use this skill whenever the user mentions README, wants to improve their repo's first impression, asks about shields.io badges, wants a star history chart, contributor avatars, documentation tables, project structure trees, or mermaid architecture diagrams in their README. Also use it when someone wants their GitHub repo to "look more professional", "look legit", or make a better first impression — even if they never say the word "README". Covers badge generation, README rewrites for new versions, fork customization, and adapting README structure to different project types (libraries, apps, docs repos, monorepos). Does NOT cover: CONTRIBUTING.md, CHANGELOG, API documentation, CI/CD setup, GitHub profile READMEs, or generating docs for individual components.
    1 repo stars
  4. ▌
    Deslop 2 · marcoantolini
    Remove AI-generated code slop and clean up code style
    1 repo stars
  5. ▌
    Playwright Best Practices 2 · marcoantolini bundle
    Use when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, configuring CI/CD, optimizing performance, mocking APIs, handling authentication or OAuth, testing accessibility (axe-core), file uploads/downloads, date/time mocking, WebSockets, geolocation, permissions, multi-tab/popup flows, mobile/responsive layouts, touch gestures, GraphQL, error handling, offline mode, multi-user collaboration, third-party services (payments, email verification), console error monitoring, global setup/teardown, test annotations (skip, fixme, slow), test tags (@smoke, @fast, @critical, filtering with --grep), project dependencies, security testing (XSS, CSRF, auth), performance budgets (Web Vitals, Lighthouse), iframes, component testing, canvas/WebGL, service workers/PWA, test coverage, i18n/localization, Electron apps, or browser extension testing. Covers E2E, component, API, visual, accessibility, security, Electron, and extension testing.
    1 repo stars
  6. ▌
    Caveman · marcoantolini bundle
    Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
    1 repo stars
  7. ▌
    Readme Wizard · marcoantolini bundle
    Generate a polished, professional README.md for any project — from scratch or by improving an existing one. Use this skill whenever the user mentions README, wants to improve their repo's first impression, asks about shields.io badges, wants a star history chart, contributor avatars, documentation tables, project structure trees, or mermaid architecture diagrams in their README. Also use it when someone wants their GitHub repo to "look more professional", "look legit", or make a better first impression — even if they never say the word "README". Covers badge generation, README rewrites for new versions, fork customization, and adapting README structure to different project types (libraries, apps, docs repos, monorepos). Does NOT cover: CONTRIBUTING.md, CHANGELOG, API documentation, CI/CD setup, GitHub profile READMEs, or generating docs for individual components.
    1 repo stars
  8. ▌
    Deslop · marcoantolini
    Remove AI-generated code slop and clean up code style
    1 repo stars
  9. ▌
    Find Skills · marcoantolini
    Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
    1 repo stars
  10. ▌
    Playwright Best Practices · marcoantolini bundle
    Use when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, configuring CI/CD, optimizing performance, mocking APIs, handling authentication or OAuth, testing accessibility (axe-core), file uploads/downloads, date/time mocking, WebSockets, geolocation, permissions, multi-tab/popup flows, mobile/responsive layouts, touch gestures, GraphQL, error handling, offline mode, multi-user collaboration, third-party services (payments, email verification), console error monitoring, global setup/teardown, test annotations (skip, fixme, slow), test tags (@smoke, @fast, @critical, filtering with --grep), project dependencies, security testing (XSS, CSRF, auth), performance budgets (Web Vitals, Lighthouse), iframes, component testing, canvas/WebGL, service workers/PWA, test coverage, i18n/localization, Electron apps, or browser extension testing. Covers E2E, component, API, visual, accessibility, security, Electron, and extension testing.
    1 repo stars
  11. ▌
    UI UX Pro Max · marcoantolini bundle
    Opt-in only — invoke by name when you want a lookup from the local UI/UX reference database (styles, palettes, fonts, product types, UX guidelines, icons, GSAP presets, charts). Do not auto-use for ordinary UI design or review; prefer impeccable, design-taste-frontend, or web-design-guidelines.
    1 repo stars
  12. ▌
    Frontend Design · marcoantolini bundle
    Opt-in only — invoke by name. Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. Prefer impeccable or design-taste-frontend unless the user explicitly asks for this skill.
    1 repo stars
  13. ▌
    Gpt Taste · marcoantolini
    Opt-in only — invoke by name for Awwwards-style GSAP-heavy layouts. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.
    1 repo stars
  14. ▌
    Minimalist UI · marcoantolini
    Opt-in only — invoke by name for a minimalist editorial style preset. Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.
    1 repo stars
  15. ▌
    High End Visual Design · marcoantolini
    Opt-in only — invoke by name when you want agency / Linear-tier aesthetics. Defines fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks common defaults that make AI designs look cheap or generic.
    1 repo stars
  16. ▌
    Industrial Brutalist UI · marcoantolini
    Opt-in only — invoke by name for an industrial brutalist style preset. Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects.
    1 repo stars
  17. ▌
    Redesign Existing Projects · marcoantolini
    Opt-in only — invoke by name. Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Prefer impeccable or design-taste-frontend for routine redesigns unless the user explicitly asks for this skill.
    1 repo stars
  18. ▌
    Git · marcoantolini
    Router for user-invoked git skills — commit, push, sync, switch branch, land onto another branch.
    1 repo stars
  19. ▌
    Goal · marcoantolini
    Define concrete, measurable goals before work begins, including success criteria, evidence, scope, and stop conditions. Use when explicitly invoked as /goal, goal, goal skill, or when the user asks to create a goal, set an objective, clarify success criteria, or turn a fuzzy intention into a verifiable outcome.
    1 repo stars
  20. ▌
    Git Commit · marcoantolini bundle
    Stages all changes and creates one Conventional Commits 1.0.0 commit. Does not push.
    1 repo stars
  21. ▌
    Git Fetch Pull · marcoantolini
    Fetches all remotes then pulls the current branch’s upstream.
    1 repo stars
  22. ▌
    Git Push Branch · marcoantolini
    Pushes existing commits on the current branch to its upstream. No stage, commit, or history rewrite.
    1 repo stars
  23. ▌
    Update Changelog · marcoantolini bundle
    Maintains CHANGELOG.md per Keep a Changelog 1.1.0. Two workflows: refresh [Unreleased] from git (update-changelog command), or cut a semver release and bump version manifests (update-changelog-release command). Use when the user invokes those commands, asks to update the changelog, refresh Unreleased, or release a new version with aligned package versions.
    1 repo stars
  24. ▌
    Multi Agent Runner · marcoantolini
    Run a manually-invoked workflow where multiple agents, optionally with user-specified models, attempt the same task and compare results. Use only when the user explicitly invokes this skill or asks to run a task with N models, best-of-N agents, multiple agent attempts, parallel proposals, competing implementations, or multi-agent task runs.
    1 repo stars
  25. ▌
    Fallow · marcoantolini bundle
    Codebase intelligence for TypeScript and JavaScript. Static analysis of code and styles reports changed-code risk, cleanup opportunities, duplication, circular dependencies, complexity hotspots, architecture boundaries, design-system drift, feature flags, and opt-in security candidates. Runtime coverage can merge production execution data for hot-path review, cold-path deletion confidence, and stale-flag evidence. 123 framework plugins, zero configuration, sub-second static analysis. Use when asked to audit PR risk, find unused code or dependencies, detect duplicates, check styling consistency, inspect architecture boundaries, merge runtime coverage, auto-fix supported issues, or run fallow.
    1 repo stars
  26. ▌
    Impeccable · marcoantolini bundle
    Default skill for app UI, dashboards, product surfaces, app shells, components, forms, settings, onboarding, and empty states — design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or iterate. Prefer design-taste-frontend for marketing landings and portfolios. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, spacing, layout, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and design tokens. Also use for bland designs that need to become bolder, loud designs that should become quieter, live browser iteration, or ambitious visual effects. Not for backend-only or non-UI tasks.
    1 repo stars
  27. ▌
    Git Checkout Branch · marcoantolini
    Switches to a named branch; creates a new local branch only after explicit confirmation.
    1 repo stars
  28. ▌
    Git Merge Into Branch · marcoantolini
    Merges the branch you started on into a named target, pushes the target, then switches back.
    1 repo stars