Art & Design

Build Claude Code content workflows with 8 skills, persistent memory, and a quality gate for cleaner drafts and better SEO.

Governed multi-agent memory for AI agents — hybrid markdown+SQLite, FTS, vector search, LLM reranking. One Go binary, MCP stdio + HTTP + SSE.

An experimental, unofficial Claude skill that reviews content against the Readability Guidelines.

Turn Claude Code into a 28-agent penetration testing assistant for recon, web, AD, cloud, mobile, wireless, and forensics

Run AI image tools for Claude, Cursor, and VS Code with PixelPanda MCP Server for local edits and product photo generation

20 GTM skills for Claude Code — lifecycle segmentation, deal scoring, creative direction, and more. Built by Intempt.

Build and run Claude Code from source with Bun, a TypeScript and React Ink terminal AI coding assistant for Anthropic API and MCP support

Build a production-grade Rust rewrite of Claude Code for agentic coding, native tool calling, and multi-provider support

7-Aspects for AI Agent Skill Engineering — VDA 6.3 Process Turtle Diagram framework for systematic Skill design and evaluation (CN/EN)

Turn any company logo into consistently branded Excel, Word, PPT, PDF, flowcharts & handbooks. A Claude Code skill.

Compact, governance-first agent framework with self-evolving skills and a VSCode UI

AI copilot for TouchDesigner — DeepSeek v4. Standalone .tox (91 tools, in-browser + in-TD chat with font-size toggle) and Claude Code MCP (103 tools). Visual chat, BM25/FTS5 corpora, persistent memory, recipes, multi-model routing, compaction, traces, recovery hints. TD 2025.32820 build support.

Personal fund/stock management platform with Hermes-Lite AI agent, investor profiles, report styles, DCA helper, Skill marketplace and Docker deployment.

Browser automation, one binary. The simpler alternative to Playwright — no Node, no Python, no runtime. Library, CLI, MCP server, and chat UI for any AI agent.

Exercise: Build applications with GitHub Copilot agent mode

Exercise: Build applications with GitHub Copilot agent mode

Rust-native personal AI runtime. ReAct/Plan agents · MCP ecosystem · BM25+vector memory · Multi-entry (TUI/Desktop/Web/Tray/Headless). Pure Rust desktop GUI via egui. Zero runtime deps. Local GGUF inference via Candle.

TUI工具，用来管理agent的skills技能，目前我们有大量的agents技能，也没有特别规范的管理，所以做一个这样的skill切换管理工具

Hermes Agent skill: 5-phase Kanban development task pipeline (Research→Plan→Code→Code Review→Build→Complete)

AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing.

Local guidance bank for coding agents - reusable rules, skills, and project guidance

Exercise: Build applications with GitHub Copilot agent mode

CI-native evidence compiler for agent systems: MCP policy enforcement, evidence receipts, Trust Basis claims, and reviewable artifacts.

Claude Code plugin for HTML/JSX design artifact creation with preview, verifier, starters, Tweaks, and sub-skills.