Art & Design

The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Built on Andrej Karpathy's pattern. An Obsidian alternative for personal knowledge management, AI second brain, and durable Claude Code / Codex / OpenClaw memory.

Codex skill for configuring Shandian admin IVR smart Agent scripts by API token.

Codex skill for polished GitHub README homepages, visual proof, and original README logo heroes

bstack P12 — Persistent Loop Discipline. Cross-context restart loop with state in the filesystem. Closes the long-horizon context-rot failure mode. Composes with bstack P5/P6/P7/P10/P11.

Youmind Claude/Codex skill with browser automation and smart-add workflow

Claude Code, Codex, and OpenClaw skill for turning rough requirements into copy-ready AI agent prompts

The Terraform for AI agents. Define your team once, deploy to Claude Code, OpenClaw, Cursor, Codex, Gemini, Copilot, Kiro. Declarative language (.at files) + Claude Code skill + interactive visualizer.

A reusable visual recipe for single-file analytical HTML articles - agent skill for Claude Code and Cursor. Dark/light theme, inline SVG diagrams, zero external dependencies, under 300KB.

Manage and execute startup strategies directly from your terminal with efficient, skill-based tools built for founders.

skills i built using claude

Codex skill for turning segmented design images into high-fidelity UnoCSS page code.

Formula Recruitment — Claude Code BD Skills

Claude skill for generating HTML PPT in McKinsey-inspired visual language. 12 layouts + dual-theme switching (Paper/Dark) + engineering discipline (SCQA, Ghost Deck Test, Brand Style). v5.1

Quản lý Context Engineering, Agent Skills, và tất cả file .md Ai trong team cũng có thể đóng góp. Không chứa code chạy được.

BenchClaw is a Codex/OpenCode skill workflow for benchmark construction, evaluation, and maintenance. It standardizes the full pipeline—from idea drafting and data generation to evaluation, reporting, failure diagnosis, and skill refinement—so agents can build reproducible, auditable benchmarks with clear quality gates, lineage, and rollback.

Personal workflow and core skills framework for coding agents, with installable guidance for Codex, OpenCode, and Claude Code.

Codex skill for guided active reading of English articles for Korean learners.

从品牌情感关键词生成完整 UI 色彩系统 · AI Skill for Cursor / Codex / Claude / Copilot / OpenClaw

Chinese-friendly Codex skill manager suite for syncing, localizing, cataloging, and discovering skills.

Smart per-project skill management for Claude Code. Analyzes project tech stack, recommends relevant skills, one-click configuration. 智能管理 Claude Code 项目级 Skill 配置。分析项目技术栈，推荐相关 skill，一键配置。

Simple workflow for agent coding with skills

Claude skill + Python scripts to analyze construction drawings that automates sheet splitting, polygon extraction, and drawing classification for GCs, estimators, and PMs.

Autonomous software delivery with AI agents — your BACKLOG runs itself, guided by encoded engineering discipline. No sprints, no hand-holding.

Zero-dependency CLI that audits your Claude Code skills — triggers, collisions, oversized bodies, and context budget — as a self-contained HTML report.