#claude-code

AI Agent 中文學習地圖 — 從零開始的結構化學習路徑，每階段有必做練習跟必修閱讀。三語對照（繁中／简中／English）。歡迎社群一起貢獻、優化內容。

職人 Shokunin 62 AI agent skills for OpenCode, Claude Code, Cursor, Windsurf. ChromaDB memory, MCP servers, declarative self-updates. Multi-model, open source, zero cost.

My whole life. One folder. No vendor. myPKA is a Personal Knowledge Architecture with a 4-person AI team baked in. Plain markdown files on your machine. ICOR® methodology. Works in Claude Code, Codex, Gemini, Cursor, Obsidian.

Claude Code 零基础入门教程，claude code 大陆如何使用教程

Persistent shared memory and handoffs across any combination of AI coding agents — Claude Code, Codex CLI, Cursor, Aider — using nothing but markdown.

Real-time hook event monitoring dashboard for Claude Code and Codex (expand in the furure), with session timelines, diff views, and token usage analytics.

Open-source CLI and agent skills for Prevu — preview/staging environments for coding agents like Claude Code, Codex, Cursor, OpenHands, even OpenClaw and Hermes Agent

Turn community chat into a structured product backlog — Telegram + dashboard + MCP for Claude Code.

Give Claude Code a durable objective and it won't stop until the work is done — budgets, deadlines, notes, and a Stop-hook guard in a single file with no dependencies.

TEDI - Terminal Environment & Development Infrastructure. Forked of terax-ai.

Claude Statusline: a lightweight Bash + jq statusline for Claude Code with model, context, rate limit, git/worktree, cost, duration, and install/uninstall support. No heavy runtime required.

Desktop GUI for running multiple Claude Code agents in parallel, organized by task

The most advanced MCP server for Obsidian. Hybrid retrieval (BM25 + ML embeddings + BGE reranker, RRF-fused), HNSW + int8 quantization, standalone .base file execution, GraphRAG-light wikilink communities, PDFs + OCR, stateful remote MCP. For Claude Code, Claude Desktop, Cursor, ChatGPT, Codex.

Curated AI coding skills focused on reducing AI-generated technical debt — reuse before create, convention discovery, token discipline, structured review and handoff.

ARM64 trace evidence analysis & cipher algorithm recovery — Claude Desktop plugin with skills + local MCP server driving the native ak_search engine over GB-scale trace files

Local-first repository context and native macOS HUD for Claude Code and Codex.

skiLL.Md is a structured, open-source collection of reusable, self-contained markdown modules that describe how to perform specific software engineering tasks.

Self-hosted lifecycle platform for software powered by Claude Code. Configurable pipelines, devices you control, no credentials on the server. Apache-2.0.

A fake CLI agent for testing orchestration tooling — emits Claude-shaped hooks, MCP traffic, and stream-json without calling any LLM.

macOS menu bar + CLI that watches Claude Code session usage across multiple accounts and switches to whichever has server-side headroom. Local-first, no telemetry.

Put a harness on AI before it guesses. Clarifies vague app ideas into precise requirements via Socratic questioning. Works with Claude Code / Cursor / Codex / Hermes / OpenClaw.

Plugin-first AI terminal workspace for Codex and Claude Code with planning, CI/CD debugging, reusable agents, skills, TODOs, and MCP tool integrations.

Programmatic video production pipeline. Treatment-driven, Claude-controlled, beat-synced. Single-stem VO + music bed + chapter timings.

Engineering craft for Claude Code — TDD, verification, code quality, and SDLC discipline.

Trading agent that learns from his mistakes

Toolkit for keeping Claude Code and Codex instructions, skills, and hooks synchronized.

AI-powered multi-platform C2C resale toolkit — 8 Claude Code skills + MCP server for automating second-hand selling

AI-powered knowledge base on a USB stick. 3D graph, markdown wikilinks, works with Claude Code & OpenCode. Zero install, fully portable.

Drop any video file. Get a short-form cut with no timeline scrubbing. Claude transcribes, scores and renders — you tick the candidates.

npx claude-code-up — bootstrap a Claude Code project with curated agents, skills, MCPs, scaffolders & lib bundles. JSON-driven decision tree, e2e verified.

AI Testing Agent Framework · 16 experts + 32 skills + 49 utils · Multi-LLM (Claude/OpenAI/Qwen/etc) · MCP-native · Open-source · Learn-while-using

Build a Team With Claude Code — Vibe Coding Workshop · EBS Tallinn · Live: https://ahmed-aleryani.github.io/claude-code-team-workshop/

Multi-platform agent skills (Claude Code + Gemini CLI + OpenAI Codex) for EU AI Act compliance, anchored on ISO/IEC 42001 (AIMS) and ISO/IEC 27090 (AI cybersecurity). Citation-grade. Decision-support, not legal advice.

GitHub repo 展示层管家 Claude Skill — 一句『按 X 风格写 README』 → README 重写（17 段配方）+ GitHub 描述润色（公式化 100 字）+ Topic 加标 10-15 个（6 类分布）三件套；与 8+ 个 git 操作向 skill 严格分工，专填 repo 展示层空白

Cross-session coordination for Claude Code — file locks, build locks, knowledge sharing, and a real-time dashboard

Auto-archive Claude Code sessions to your Obsidian vault as a Karpathy-style LLM wiki. Passive, hook-driven, knowledge converges instead of accumulating.

An opinionated 6-agent solo-founder team for Claude Code. Same numbered roster, every project.

Capsule CRM tools for Claude. Local install via npx, org-wide via Custom Connectors. Read-only mode supported.

Autonomous job search and resume tailoring agent for Claude Code