Portable, production-grade skills for AI coding agents — web development, security, UI/UX, design, motion, token efficiency. Works with Codex, Claude Code, Antigravity, Cursor, and any agent that reads a SKILL.md.
This repository also configures its own agents. See what agent-skills tells them →
Skill Codex
Remove AI slop and refine distinctive visual design in websites, landing pages, dashboards, and apps. Use for "less AI", "too generic", "premium polish", art direction, or decorative clutter: colored dots, card accent lines, border beams, icon bubbles, gradient blobs, and repetitive feature grids. Establish…
Skill Codex
Design, implement, and debug refined web animation, transitions, gestures, and micro-interactions. Use for motion polish, springs, interruption-safe dialogs, shared-element transitions, scroll effects, reduced motion, or animation performance. Keep motion purposeful, controllable, accessible, and measured; avoid…
Skill Codex
Audit, threat-model, and harden application or AI-agent trust boundaries. Use for security reviews, authorization flaws, injection, SSRF, sessions, sensitive data, cryptography, webhooks, race conditions, dependency risks, or agent tool permissions. Trace actual exploit paths, prioritize evidence, and verify scoped…
Skill Codex
Communicate engineering results concisely and preserve useful context during long tasks. Use for brief answers, TL;DR, compact status or review reports, focused diffs, large-log investigation, or context-budget management. Remove repetition and filler while preserving necessary evidence, uncertainty, user constraints…
Skill Codex
Design and meticulously style screens, components, dashboards, forms, and product flows. Use for UI/UX, "make it look better", visual refinement, perfectionist polish, typography, spacing, responsive layouts, design tokens, interaction states, accessibility, or developer handoff. Emphasize composition, optical…
Skill Codex
Build, refactor, debug, and optimize web applications, frontend components, API routes, server actions, databases, and webhooks. Use for full-stack implementation, hydration, routing, caching, performance, or resilient mutations. Preserve the installed stack, validate trust boundaries, finish visual UI styling, and…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: