Art & Design

Exercise: Build applications with GitHub Copilot agent mode

Claude Code subagents and skills that let a PM stress-test a PVD/PRD or Figma design from the point of view of a specific persona — or all personas at once. Insider ICP personas included; architecture is portable.

A Claude skill for building production-ready web forms — contact forms, lead capture, job applications, surveys, requirements gathering, and more.

Portable AI agent skill for controlled X/Twitter posting, replying, liking, topic discovery, and image-upload workflows.

32 AI agent skills for credit, finance, data intelligence, and document generation. ClawHub-ready skill registry.

Comprehensive research co-pilot for Claude Code and claude.ai — 13 skills covering literature review, methodology, ethics review, data analysis, qualitative coding, brainstorming, manuscript drafting, replication design, grant writing, talk building, citations, survey design, and peer review. A peer collaborator, not a subservient assistant.

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

Intelligent skill routers for Claude Code — execution, research, review, debugging, design, and security testing with optional multi-model orchestration via OpenCode

Your AI writes scripts. Mine builds systems. — AI coding agent skill for architect-level discipline.

Reusable AI agent skills for Django, OpenAI, web UI, Python packaging, and structured LLM workflows.

Shared config, skills, and update scripts for Claude Code, Codex, and Gemini CLI

蓝湖设计稿转前端代码的 Claude Code Skills 工具集 | Lanhu design-to-code workflow for Claude Code

AI agentic skills framework for spec-driven development, built on the organizational model of mafia.

think. build. ship. tasteful & useful crypto apps. using a curated skills + knowledge base for AI agents on solana contracts & integrations

Multi-agent primitives for Claude Code: consensus, debate, fanout research, skill building, and measured optimization.

OpenClaw/Claude Code SKILL.md for gpt-image-2 via Codex OAuth, no OPENAI_API_KEY required

Codex skill for securely setting up and accessing Google Sheets/Docs/Slides with Google Cloud service accounts.

Kali Linux penetration testing skill for AI agents (Claude Code, OpenClaw, Hermes Agent). 200+ CLI tools, 15 scenario playbooks. Autonomously plans attack paths, selects tools, and integrates results across phases to adapt the penetration strategy — with human approval gates for high-risk actions.

Floom Starter Pack. 65 hand-picked AI agent skills for Claude Code, Codex, Cursor, Kimi, OpenCode. One install, auto-activates. +18.6pp pass-rate lift.

TypeScript AI agent framework — 40+ LLM providers, 100+ tools, multi-agent orchestration, RAG, guardrails, circuit breakers, HITL, budget enforcement. Open-source CrewAI / LangChain alternative. — For Building Production-Grade Multi Agents in Minutes at Scale

Run Claude Code from any folder or USB drive with no install on Windows, macOS, and Linux

Harness for DeepSeek V4-Pro / V4-Flash. Python lib (pip install deepseek-harness) + dsh CLI + MCP server (npx @deepseek-harness/mcp) + Anthropic SKILL.md. 16 documented protocol quirks, 12 probes, 270+ trials.

Codex skill for repeatable LLM hosting, debugging, and deployment specs on OCI GPU Compute. Meant to do quick testing.

Open collection of Claude Code skills for AWS diagrams, presentations, SVG graphics, paper search, browser automation, and more.