Claude
Tools

MCP server giving Claude (and other MCP clients) human-like control of Windows — virtual cursor, OCR, emergency stop, Electron manager. 64 tools.

Agent Skill 设计案例库 — 从已发布 skill 反推产品决策与工程范式，沉淀 AI-native API 设计法则。首个案例：微信读书 Skill 拆解。

Claude Code skill: persona-based strategic product analysis — 5 users, 3 recommendation layers, elevation moves

把硬核长内容拆成obsidian的思维导图 · 通用 AI 提示词框架(Claude/ChatGPT/Gemini)

PubMed reference resolver / 査読支援スキル (References → PubMed 逆引き + 統合監査レポート)

General-purpose runtime for spawning CLI AI agents (Claude Code, Codex, Gemini CLI) as subprocesses with structured event streaming, MCP tool forwarding, and Claude Code permission auto-setup. MIT.

Local SQLite cache for OpenAI and Anthropic API calls. One env var, 60-80% cheaper dev loops. Works with every existing tool.

Extensión Chrome para monitorear el uso semanal de tokens en Claude Code

Multi-agent finance close assistant built with the Anthropic Claude API — analyst, researcher, writer, and critic agents with tool use, extended thinking, and an eval suite.

Static + runtime linter for LLM agent prompts, skills, and tool definitions. Model-aware policy for Claude, GPT, OpenRouter.

把小红书图文笔记完整地读进 Claude Code 当上下文 — 标题 + 正文 + 全部图片 + 互动数据 + 评论区。一条链接就够。

A Claude Code skill that packages HTML eLearning modules into SCORM-compliant zips. Supports SCORM 1.2, 2004 2nd, 3rd, and 4th Edition. Drop it into your .claude/commands/ folder and run /package-scorm.

反封号.skill — Claude Code / Anthropic / OpenAI account suspension risk detection, IP cleanliness scoring, compliance preflight, and appeal-packet skill. Compliance-only; no ban evasion.

AI-native startup founder playbook skill for Claude — based on Anthropic's The Founder's Playbook (2026)

Anthropic-compatible proxy that routes Claude Code opus4.7/sonnet4.6 Haiku , the VS Code extension & JetBrains ACP to free or local model providers.

Multi-agent code audit skill for Claude Code — Opus orchestrator + parallel Sonnet specialists + Haiku baseline. Modes: full, differential, targeted.

A Claude Code skill that audits third-party repos for malicious code, supply-chain risk, and dangerous patterns — before you install or run it.

Claude Code agent di WhatsApp + Telegram. Voice, vision, file analysis, RAG, multi-tool reasoning. Run di Termux Android. One-click installer.

A pi extension that gives your agent scheduled and event-driven routines

A Claude Code skill that produces presentations worth sending — research-first, narrative-driven 5-phase workflow inspired by Genspark AI Slides.

Multi-agent deep research on Claude models: a Claude Code plugin + Agent SDK CLI sharing one source of truth. Orchestrator -> parallel researcher subagents -> triangulate -> synthesize -> cite -> report. Built-in tools only; OAuth subscription or API key; self-hosted plugin marketplace.

Autonomous AI agent that triages URLs for phishing and malware: a barefoot Anthropic tool-use loop driving 10 classical analysis tools plus a hardened Docker browser sandbox.

My agentic-engineering workbench — Claude Code skills, subagents, and CI workflows I reuse across projects.

The Claude Code handbook you actually finish. Bilingual (EN/FR), free. Hooks, sub-agents, skills, plan-first dev, audit loop. For developers and knowledge workers.