Art & Design

Claude Code Skill：上传 PDF/PPTX 课件，从易到难逐题测验，每题打分，错题解析，直到完全掌握

Figma → code workflow skills for Claude Code: analyze, audit, implement, refactor

React + Tailwind v4 starter pre-wired with the Paperclip design system and a Claude Code design-guide skill

个人 Claude Code skills 集合（plugin marketplace）— 含 feature-test：功能文档驱动测试用例 + UX 双审计 + 优先级测试报告

A Claude Code skill that fingerprints a codebase's coding style so new or AI-written code is indistinguishable from the author's own.

VLESS-XHTTP-REALITY 中转 + WireGuard 落地多出口代理链的 Claude Code skill（playbook + 脚本，非一键），出口 IP 为落地机 | Claude Code skill: build a VLESS-XHTTP-REALITY relay backhauled over WireGuard to one or many landing VPS via SNAT multi-exit, so the exit IP is the landing's — architecture, MTU pitfalls, verification & helper scripts

Image2-first Codex skill for generating PPT page images, QA contact sheets, PPTX wrappers, and timed scripts.

Turn AI agents into team SMEs. Kluris builds a shared, human-curated knowledge brain (decisions, constraints, incidents, tribal knowledge) as markdown in a git repo. Queryable via slash commands from Claude Code, Codex, Cursor, Windsurf, Cline, Gemini CLI.

Securely scale AI usage across your organization. Control plane for building, securing and monitoring your agents, mcp and skills.

Hand off a coding requirement and watch AI agents (Claude Code, Codex, Gemini CLI) ship merged PRs. Decomposes the work, runs stories in parallel git worktrees with per-story ephemeral Postgres, reviews and tests every change, escalates failures through 5 tiers, merges what passes. Event-sourced, Go, Mac/Linux.

An AI agent starter template that implements the DORA AI Capabilities Model — built for GitHub Copilot, Claude Code, Cursor, and Codex

Stack of ready-to-use skills and MCP servers for AI agents, focused on libraries, scholarly information, and research workflows.

AI-native project scaffold: describe your idea → agent writes all context files. Includes skills (skills.sh), MCP tools, UI system, and agent review workflow.

cb-agent - 可拆解、可审计的 LLM Agent 框架，支持 Function Calling 工具循环与 GSSC 上下文构建。默认轻量 Markdown 记忆，零依赖快速启动；可选完整 RAG/向量记忆。提供 CLI 与 Ink/React TUI 双界面，支持多会话隔离、自动/手动上下文压缩、MCP 集成、Skill 能力扩展。

Distill claude-mem into CLAUDE.md, skills, and an Obsidian long-term-memory vault — with built-in AgentOps (monitoring, alerting, adoption metrics, redaction). Set up from Claude Cowork chat.

A complete security skill suite for OpenClaw, Hermes, PicoClaw and NanoClaw agents (and variants). Protect your SOUL.md (etc') with drift detection, live security recommendations, automated audits, and skill integrity verification. All from one installable suite.

Codex workflow skill and terminal UI for coordinating multi-agent coding runs

Operation TEMPEST — a self-improving, self-healing multi-agent Binance USD-M futures trading desk built as a Claude Code skill (paper-by-default; live double-gated behind a graduation verdict).

A Claude Code skill that turns long-form agent output into a designed HTML report — TOC, callouts, framed figures, footnotes, light/dark themes, and one-click export back to Markdown.

One-prompt Claude Code starter kit with phase gates, ledgers, skills, and agents.

Brand building skills for Claude Code and AI agents. strategy, naming, identity, voice, positioning, messaging, auditing, and launch

Fullstack project scaffolding skill for Claude Agent - supports Web (Next.js), Backend (Spring Boot), Android (Kotlin/Compose), iOS (SwiftUI), and Docker deployment

Up to 99% token savings on AI agent context. Free. Provider-agnostic (Claude, Cursor, Codex, Cline, any MCP agent). 91.62% over 626.8M auditable tokens. Try: nuxs.ai/playground

AI product manager skills for Codex/Claude: brainstorming, product research, PRD workflows, requirements review, and planning handoff.