63 packages found
A curated system of production-ready Claude Code skills with quantitative evaluation reports, golden test fixtures, and
⚠️ Experimentelle Skill-Sammlung für deutsches Recht (Arbeits-, Gesellschafts-, Insolvenz-, Datenschutz-, Prozessrecht u
Autonomous multi-agent SDLC harness: describe a feature in plain English and AI agents scope, code, test, review, and op
Transform natural language project rules into Claude Code automation hooks - Write rules in plain English and let Claude
acrawl — LLM-powered web crawler. Describe what you want in plain English, get structured data back. Single Rust binary,
AI 測試大師 — MCP server driving pytest / Jest / Cypress / Go / Maestro. Analyze, generate, run, advise. Web + Mobile (iOS/A
VexJoy AI Agent with Intelligent Routing - /do routes plain-English requests to the right specialist agent and gates the
Self-installing personal AI orchestrator. Hand the latest blueprint file to a Claude Code session and it builds a full m
Run your entire company with Claude Code. 15 AI Agents + 5 Skills + Approval Pipeline. Battle-tested in production for 1
Local QA agent — maps frontend routes to backend APIs, probes every endpoint live, scores pages 0–100, and explains why
Heimdall — MCP server for the Apple App Store Connect API & App Store Server API (StoreKit 2). 982 tools generated from
Zero-dependency browser automation CLI. 70+ commands, 10 test assertions, smart commands (click/fill by text — no LLM ne
Autonomous LLM build orchestrator: plans a goal into tasks, edits code with anchored SEARCH/REPLACE, and verifies every
Automated Jira daily digest via Claude Code CLI. Queries for Jira Self Hosted API, generates team activity reports (Done
MCP Server for editing VBA code and controls on an MS Access .ACCDB database via LLM (tested just with Claude Code)
Permanent guardrails for AI-coded apps
Combining a five-level AI framework with git-native memory overcomes session amnesia, enabling anticipation of problems
AI-powered E2E testing for 10 platforms. 253 MCP tools. Zero config. Works with Claude, Cursor, Windsurf, Copilot. Test
Advanced DESIGN.md toolkit for Claude Code — extract specs from URLs (Playwright) and generate from quiz answers
AI-powered MCP server that provides natural language control for browser automation. Built on Playwright with an intelli
Claude Code dynamic workflow for autonomous software engineering. Zero human intervention. Spec-driven, doc-as-ground-
Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.
Drawdown-first portfolio tool with a read-only MCP addon for Claude — a deterministic core computes every number; the AI
Nudge — a typed, replayable, budget-aware programming language for LLM agents. Compiles to Python & TypeScript. Traces a
Open-source MCP server for AI-autonomous Godot game development. Deterministic playtesting, multiplayer testing, DAP deb
AI coding workstation: Claude Code + web UI + 7 AI CLIs + headless browser + 50+ tools
Claude Code plugin for visual docs — annotated screenshots, feature demos, flow walkthrough recordings (gif/mp4), termin
Udemy Instructor API + browser scanner MCP — Claude Desktop/Cursor üzerinden kurs/yorum/Q&A yönetimi
LinkedIn for AI assistants (MCP) — profiles, people/job/company search, feed & messaging as structured JSON, plus gated
Google search MCP. One MCP replaces search + fetch + academic-paper extractor.
HttpRunner 是一款开源的 API/UI 测试框架,简单易用,功能强大,具有丰富的插件化机制和高度的可扩展能力。
Model Context Protocol (MCP) server exposes tools to read multiple document types including DOCX, PDF, Excel, and TXT. T
全能协议分析工具:浏览器抓包 + MITM 代理 + 指纹伪装 + AI 分析 + MCP Server 无缝对接 AI Agent/IDE | All-in-one protocol analysis toolkit — built
MCP (Model Context Protocol) server for Chrome automation using Puppeteer. Persistent browser sessions, visual testing,
这是一款基于 Playwright 开发的小红书自动搜索和评论工具,作为 MCP Server,可通过特定配置接入 MCP Client(如Claude for Desktop),帮助用户自动完成登录小红书、搜索关键词、获取笔记内容及发布A
LLM-agent-native backtest framework for futures research — MCP server, in-package skills, catalogued error codes, typed
Record any browser page as GIF or video via MCP — powered by Playwright + ffmpeg
Lingua Universale -- a verification language for AI agent protocols. Like mypy for multi-agent communication. 3696 tests
Claude Code plugin that stops "almost done" loops — declare your stages in workflow.json, runs them as a state machine t
Universal, language-agnostic development standards for software projects. Includes coding standards, git workflows, test
AI quantitative trading platform for crypto, stocks, and forex with backtesting, live trading, market data, and multi-ag
The control plane for game-dev agents — close the loop with verified compile, test, and cross-model review across Unity,
10 battle-tested marketing skills for AI agents - SEO setup, card news, decks, newsletters, cold email, CRM, meeting res
AI coding assistant skills that structure the full development lifecycle into planning → implementation → testing → rele
A Claude Code skill that makes AI argue with itself to stress-test your ideas.
一个基于 Project Context 进行 Prompt优化 的 Claude Code SKILL,并配置有界面进行迭代优化;Advanced Claude Code skill for systematic prompt engin
Claude Code / ARIS skills for turning a loose repository into a readable, testable, maintainable open-source project.
三竞赛 (CUMCM/MCM/电工杯) 数学建模 skill — harness-agnostic, 同时支持 Claude Code 与 Codex CLI, 全程问答式 (Friendly Mode), 10 阶段 + 4 反馈层 +