Claude
Tools

Multi-signal stock prediction & monitoring for Windows: 39 data collectors, an ML ensemble and an optional Claude advisor in a tkinter desktop app, plus a Bloomberg-style browser terminal (SEC filings, insiders, options, FRED macro, live quotes). Research tool, not financial advice.

Claude Code plugin marketplace by Digital Process Tools. Add with: /plugin marketplace add Digital-Process-Tools/claude-marketplace

Sistema operativo cognitivo para Claude Code: orquesta 7 modos de pensamiento según 5 fases de proyecto, con hooks deterministas contra el efecto ancla y la convergencia prematura.

WWA Transform — Turn any website into an AI-powered agentfront. Claude Code plugin + Codex agent + CLI.

Claude Code plugin — emotion-aware prompt-hygiene audit for CLAUDE.md files, skills, and agent definitions. Based on Anthropic's emotion-concepts paper https://transformer-circuits.pub/2026/emotions/index.html . Flags framings that push Claude toward desperation, sycophancy, harshness, or concealment. Report + diff, no auto-apply.

Summarize YouTube videos with yt-dlp, cache transcripts locally, and answer follow-up questions without re-downloading. Works across Claude Code, Cursor, OpenCode, and any agent implementing the Anthropic Agent Skills Specification.

Claude Code self-improvement: proactive memory recall via hooks + rules. Lightweight, no API, fork-friendly.

Persistent SSH PTY session manager for MCP clients with actor-aware input tracking, split dashboard rendering, and automatic session cleanup.

Auto-generated SKILL.md files from official Anthropic/Claude blog posts (KR + EN). Updated hourly.

Claude Code plugin marketplace with Agent Skills for Claude. Install via /plugin marketplace add bgorkem/bgorkem-skills

Free Claude skills for sales: daily briefs, meeting prep, follow-ups, deal nudges, and pipeline reviews. Claude connector and plugin, plus the same skills for ChatGPT, Copilot & Gemini. Built by Arrows.

A multi-agent orchestration framework for Claude Code — enforces your coding agreements through system-level hooks, not prompts.

Hackable, interactive LLM agent harness for the terminal — streaming REPL, tool-using agent loop, persistent PTY shells, sub-agents, planning, hooks, prompt caching, rate-limit-aware retry, mid-turn-checkpointed sessions. Anthropic + OpenAI.

PRCSS — Claude Skill* A Design Thinking framework for Designers, Design Ops & Design Managers — now as a Claude Skill. Structure your design projects directly in your AI workflow: phases, deliverables, and tracking built in. Free to use. ☕

AI agent skills for Claude Code and compatible agents — workflow, coding, design, Claude Code meta, media, productivity, and writing

Curated Claude Code resources for Chinese developers — tutorials, mirror services, tools, CLAUDE.md templates. Companion to the international awesome-claude-code list.

Terminal, filesystem, and background-job tools for Claude Desktop on Linux. Zero-dependency MCP extension, MIT-licensed.

team-os — 102 agentes e 112 skills em 11 squads (Dev, Sites, Social, Traffic, PM, Sales, Brand, Finance, Legal, SEO, Security) para Claude Code Agent Teams. /team-os monta e orquestra o time com smart-memory; /team-os-creator instala, atualiza e audita as squads; /sala-de-controle comanda todas as sessões com painel ao vivo. MIT.

Bridge Claude Code CLI to Anthropic's claude-desktop-buddy hardware via BLE - approve tool calls with physical buttons on an M5StickC Plus

Team collaboration protocol skill for OPC collectives — handoff/checkpoint flow, CURRENT/NEXT/RISKS structure, hard constraints for AI agents (Claude Code, Codex CLI, Cursor, Cline, Continue, Gemini CLI). Follows Anthropic Agent Skills open specification.

Evidence-based audit + cleanup for Claude Code installations. Decide what to keep, delete, or refresh across plugins, skills, and rules — grounded in your actual session history.

Claude Code 实战工作流 starter：22 条硬规则 + memory 常识 book + error book + 数据飞轮自动门禁 hook + skills。源自 vLLM-Omni × HunyuanImage-3.0 接入项目（已脱敏）。

GitGauge — Chrome extension that scores GitHub repository authenticity from stars/forks/watchers/issues ratios.