Skills

Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.

ios26-design

9769

seunghan91/ios26-design-system

Skill Claude CodeCodex

Build iOS 26 Liquid Glass interfaces on web and cross-platform. Source: Apple Figma Community Kit.

not rated 23 +1 1mo ago A 187 tokens original MIT

work-loop

9770

eugenelim/agent-ready-repo

Skill Claude Code

Use when implementing or resuming a non-trivial repository change: a feature, behavior-changing fix, refactor, migration, framework or dependency upgrade, schema or API change, performance work, infrastructure or build-system change, reversion, or an existing build spec under docs/specs/. Also use for bare…

not rated 23 +1 changed today A SkillSpector: warn 161 tokens original Apache-2.0

spss-academic-workflow

9771

EXIST-D/spss-academic-workflow

Skill Codex

Use when the user wants a complete SPSS or SPSS-MCP empirical research workflow: organize source data, prepare datasets, design variables and models, run SPSS analyses, export Chinese result paragraphs and tables, write a Chinese LaTeX paper, and compile the final PDF.

not rated 23 +1 4mo ago A 64 tokens original MIT

industry-research

9772

geekjourneyx/industry-research

Skill Claude CodeCodex

An industry-research engine that turns a broad business or market question into a sourced strategic report. It uses several research agents to check evidence, challenge conclusions, and assign confidence.

not rated 23 +1 2mo ago A 242 tokens original MIT

clone-website

9773

giang6283623/minimal-vibe-coding-kit

Skill Codex

Plan, build, and verify an authorized website clone or migration through one front-loaded requirements session and an optional autonomous A-to-Z run. Use for small marketing or content sites, corporate sites, web applications, and small, medium, or large ecommerce projects from local screenshots, mock JSON, owner…

not rated 23 22d ago A SkillSpector: pass 113 tokens original MIT

seo-llm-site-architect

9774

sergekostenchuk/ui-ux-agent-skill-system

Skill Codex

Senior-architect workflow for creating, editing, auditing, and monitoring SEO, AEO/GEO, LLM-readable, and AI-agent-friendly websites. Use when the user asks about SEO, technical SEO, organic visibility, AI search visibility, ChatGPT/Claude/Perplexity/Gemini readiness, robots.txt, sitemap.xml, llms.txt…

not rated 23 6d ago A 127 tokens original Apache-2.0

excalidraw

9775

eigent-ai/agent-skills

Skill Claude CodeCodex

Generate architecture diagrams as .excalidraw files from codebase analysis. Use when the user asks to create architecture diagrams, system diagrams, visualize codebase structure, or generate excalidraw files.

not rated 23 +4 3mo ago A 45 tokens original Apache-2.0

ios-design-agent-skill

9776

vermont42/iOS-Design-Agent-Skill

Skill Claude CodeCodex

Audit and improve iOS/SwiftUI app aesthetics — typography, color, spatial composition, motion, and atmospheric depth. Use when reviewing UI design, critiquing screenshots, or improving SwiftUI view code beyond functional correctness.

not rated 23 +1 6mo ago A 51 tokens original MIT

threadnote-context

9777

Kashkovsky/threadnote

Skill Claude CodeCodex

Recall and read decisions or handoffs from the Personal Cursor Cloud Git memory shares before non-trivial work.

not rated 23 +3 changed 4d ago C 25 tokens AGPL-3.0

onpage-seo-audit

9778

linhan-dev/onpage-seo-audit

Skill Claude CodeCodex

An on-page SEO audit tool for checking a live website or local project source code. SEO means improving how pages can be understood and found by search engines; the audit checks items such as metadata, links, routes, and semantic HTML.

not rated 23 +2 1mo ago A 66 tokens original MIT

rhino-architect

9779

tanishqbhattad/rhino-mcp

Skill Claude CodeCodex

Architectural modeling in Rhino 3D through the rhino-architect MCP tools. Use whenever the user wants to model, edit, analyze, or document buildings in Rhino - massing studies, floor plates, cores, facades, openings, floor plans, sections, area schedules, materials, or viewport captures. Also use when tracing…

not rated 23 +2 changed 15d ago A SkillSpector: pass 85 tokens original MIT

juniors-best-practice

9780

siberiacancode/agent-skills

Skill Claude CodeCodex

Juniors-focused React and TypeScript best practices. Use this skill when writing or reviewing code to enforce clear, consistent, and maintainable patterns across common scopes like React, TypeScript, styling, devtools, assets, and Git.

not rated 23 +4 yesterday A SkillSpector: pass 55 tokens original MIT

kb-create

9781

BeppeTemp/cartographer

Skill Claude CodeCodex

Operator procedure to declare and provision a new Knowledge Base GitOps-style, so it survives pod restarts; also covers authoring the KB's artifacts (skills, subagents, hooks, MCP descriptors) and the SOPS encryption flow.

not rated 23 +2 changed 4d ago A SkillSpector: warn 50 tokens original Apache-2.0

engram

9782

techtheist/engram

Skill Claude CodeCodex

Read and write the project's durable reasoning memory (decisions, principles, cautions, problems, insights) through the Engram MCP tools. Recall relevant memory before non-trivial work; capture decisions and knowledge silently at natural stopping points; keep the graph honest (judge suspects, close answered problems…

not rated 23 +4 changed today A 74 tokens copy · 92% MIT

write-model-paper

9783

chengziyue1222/math-model-agent

Skill Codex

Generate rigorous, readable mathematical-modeling papers from problem analysis, models, results, figures, tables and verifiable sources. Use when Codex needs a competition paper or a grounded modeling report.

not rated 23 +7 1mo ago A 42 tokens original MIT

awesome-ai-agent-tools

9784

michielhdoteth/awesome-ai-agent-tools

Skill Claude CodeCodex

Install and manage AI agent skills, MCP servers, and agent workflows from the Awesome AI Agent Tools collection. Use this when the user wants to install skills, set up MCP servers, browse agent workflows, or explore the AI agent tool ecosystem. Supports Claude Code, Cursor, Codex, OpenCode, Gemini CLI, Copilot, and…

not rated 23 +2 yesterday A SkillSpector: warn 77 tokens original CC0-1.0

pitch

9785

SlideSpeak/slide-design-skill

Skill Claude CodeCodex

High-stakes startup pitch decks. Bold, confident, one-claim-per-slide, founder-voice. Use when the user asks for 'pitch deck', 'investor deck', 'fundraising deck', 'demo day deck', 'YC-style', 'seed pitch', 'series A deck'.

not rated 23 +2 2mo ago A 61 tokens original MIT

interactive-course

9787

ericffu/interactive-course

Skill Claude CodeCodex

A guide for creating interactive courses as HTML pages, with lessons, visual explanations, animations, demonstrations, quizzes, and optional exercises. HTML is the standard format used to structure web pages.

not rated 23 +3 1mo ago A 148 tokens

laohu-visual-assets

9788

LaohuAD/laohu-ai-visual

Skill Codex

A visual-asset planning guide for AI projects that identifies which characters, places, objects, products, colors, and styles should stay consistent across generated images. It defines those assets, their dependencies, prompts, checks, and later use.

not rated 23 +1 changed 7d ago A SkillSpector: pass 82 tokens original

ux-design

9790

bacnh85/pi-extensions

Skill Claude Code

Anti-slop UI/UX design discipline for AI-generated interfaces. Enforces industrial-design principles (Dieter Rams: honest, thorough to the last detail, as little design as possible) so output is a defensible system, not statistical-default slop (purple glow, shadow-as-texture, missing states) — and equally not the…

not rated 23 +4 changed yesterday A 219 tokens

1start-mathmodel

9791

LiXiang106991/MathModelAgent

Skill Claude Code

A workflow entry point for the Chinese national mathematical modelling competition. It coordinates problem analysis, modelling, programming, diagrams, paper writing, and verification.

not rated 23 +1 19d ago A 69 tokens original MIT

vetto-sandbox

9792

shleder/vetto

Skill Claude CodeCodex

Enforce zero-daemon Landlock/Seatbelt security boundaries, network isolation, and subagent capability controls when executing untrusted commands or running subagents. Use when running terminal commands, testing untrusted scripts, isolating AI subagent workflows, or performing read-only session recovery for Codex and…

not rated 23 +3 today A SkillSpector: pass 67 tokens original Apache-2.0

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: