Claude
Tools

Harness Claude for autonomous implementation — turn every failure into a guardrail and let context persist across sessions and worktrees.

🤖5 分钟跑通，7 天读懂，从 0 实现一个能规划、能调用工具、能审批、能回退、能记忆的 Claude Code / Cursor 式本地 Agent。

20 power-user skills for Claude Code — session management, multi-agent orchestration, adversarial testing, calibrated estimation, decision archaeology, and more. Drop-in SKILL.md files that turn your AI coding agent into a senior engineering partner.

Reverse-engineered source code architecture of Claude Code CLI — 4,756 TypeScript files reconstructed from cli.js.map. Deep analysis of QueryEngine, Tools, Bridge, MCP integration, Ink UI, and more.

Curated prompts, workflows, and frameworks for lawyers using Claude AI. Built by Donna Scaffidi, The Legal AI Architect | Head of AI & Legal Innovation at Ruli AI.

Document-based project control for AI-human collaboration. A Claude Code skill that lets any agent resume work from files alone — no external memory needed. Tracks progress across sessions, detects interrupted phase transitions, coordinates multiple projects via file-based inbox/outbox.

Architecture patterns for multi-agent systems with orchestrators, sub-agents, and tool coordination

Portable agent harness configuration. Convert rules, skills, hooks, memory and MCP configs between Claude Code, Cursor, Windsurf, Copilot, OpenCode and Codex CLI.

Claude Code skill: analyze any project and build a three-tier knowledge base (LLM context packs + Obsidian wiki). Inspired by Karpathy.

Agent Pipeline Development — enforced Claude Code development framework with pipeline gates, guard hooks, and memory system

VeriFlow-Agent: Agent-based RTL Design Pipeline A LangGraph-powered RTL design automation tool that transforms hardware design from manual coding to agent-based workflows. Features 7-stage pipeline (Architect → Synthesis), multi-backend LLM support (Claude/Anthropic/LangChain), and three interfaces: Claude Code Agent, Web UI, and CLI.

Fetch, share, and sync Claude skills between GitHub and your Cowork sessions

Autonomous Claude Code agent — 14 specialized agents, 10-parallel execution, project-specific skill learning, mechanical checkpointing, wave-based planning with acceptance gates, caveman ultra (~75% token savings). One prompt → finished project.

Community fork of elirantutia/vibeyard with a working Windows build pipeline and an opt-in approach to global Claude Code hooks. MIT.

Control a Divoom Tivoo 16x16 pixel LED screen from macOS via Bluetooth RFCOMM. 57 animated presets, AI pixel art generation (Claude/OpenAI with extended thinking), scrolling text with CJK support, Claude Code hooks for workflow notifications, character emotion sets (Claude/Luna).

Time awareness hook for autonomous Claude Code agents — inject current time into agent context via PostToolUse, so long-running autonomous sessions know what time it is.

A prose linter that catches AI writing patterns. Based on Wikipedia's Signs of AI Writing.

Cross-conversation memory for Claude Code and Cowork

Your Claude Code sessions, now with a soundtrack. Zero config, full hook coverage.

A Claude Code skill for crafting portfolio-ready design case studies. Structured template, tone guide, and slide layout for UX, product, and design portfolios.

A Claude Code skill that generates beautiful HTML reports instead of long terminal output

Free open-source Agent Skills for voice-to-instrument AI music production — recording best practices, instrument-specific tips, and prompt engineering

Free Claude Code skill to humanize AI-generated text. Bypass GPTZero, Turnitin, and other AI detectors. Powered by DiaIQ.

Code Intelligence: Token-budgeted codebase context for Elixir agents. Solves context window limitations by providing a deterministic Elixir semantic graph and agent-ready Repo Map for LLMs.