68 packages found
Autonomous orchestration framework for Claude Code with MemPalace-inspired memory (4-layer stack, 818-token wake-up), pa
MCP Server for editing VBA code and controls on an MS Access .ACCDB database via LLM (tested just with Claude Code)
Regression testing for AI agents. Snapshot behavior,diff tool calls,catch regressions in CI. Works with LangGraph, CrewA
The control plane for game-dev agents — close the loop with verified compile, test, and cross-model review across Unity,
acrawl — LLM-powered web crawler. Describe what you want in plain English, get structured data back. Single Rust binary,
LoopSense is an open-source MCP server that closes the feedback loop for AI coding agents — giving them real-time visibi
🎯 Claude Code workflow engine - SPEC-first planning, TDD automation, GPT delegation, and context engineering. From idea
CLI-first API testing tool. YAML-defined tests, structured JSON output, built for AI-assisted workflows.
Claude Code plugin that stops "almost done" loops — declare your stages in workflow.json, runs them as a state machine t
AI 測試大師 — MCP server driving pytest / Jest / Cypress / Go / Maestro. Analyze, generate, run, advise. Web + Mobile (iOS/A
Close the agentic coding loop for web animation. Give your coding agent the ability to scroll your page while recording,
Advanced Claude Code CLI toolkit - agents, hooks, skills, MCP servers, phased development, site intelligence dev-scan, a
Turn ad-hoc Claude Code / Codex / Cursor sessions into a repeatable loop — research → plan → wave-execute → close. Paral
DevoxxGenie is a plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud
🧬 Clone any website with a team of AI agents — pixel-perfect UI clone + reverse-engineered architecture docs. A Claude
Self-installing personal AI orchestrator. Hand the latest blueprint file to a Claude Code session and it builds a full m
A Claude Code skill that turns Claude into an infinite development loop: spec → feature list → implement → test → commit
Pre-execution governance for AI agents. Sub-millisecond tool call validation, drift detection, circuit breakers, human-i
A curated system of production-ready Claude Code skills with quantitative evaluation reports, golden test fixtures, and
A set of 8 global skills for Claude Code that enforce disciplined, test-driven agentic development. Install once, use in
Stop prompting. Start crafting. — Transforms Claude Code into 6 reactive AI agents (PO, Architect, Frontend, Backend, QA
CLI to control iOS and Android devices for AI agents
Claude Code dynamic workflow for autonomous software engineering. Zero human intervention. Spec-driven, doc-as-ground-
AI-driven SDLC harness for Claude Code — multi-agent TDD workflow (plan → tests → code → review → PR) with Azure DevOps,
A native desktop application for developing, testing, and debugging Model Context Protocol servers.
Give your AI agent a real browser — with a human in the loop. Open-source MCP-native browser agent.
The most comprehensive MCP server for Polymarket — 48 tools spanning direct trading, market discovery, smart money track
Claude Code skills for medical research — literature search, reporting guidelines, statistical analysis, publication fig
Safe MCP server + CLI for testing, inspecting, and operating n8n workflows with a constrained scope
Agentic QA boilerplate built on Playwright + KATA + TypeScript. Multi-agent skills following the agentskills.io spec, or
达尔文.skill —— 一个让你的Skill无限进化的系统:评估→改进→测试→保留或回滚 | Autoresearch-inspired autonomous skill optimization for Claude Code. Eva
The open-source web-browsing backend for AI agents & workflow engines. Ships a 42-tool MCP server for Claude Code/Cursor
Screen-reader navigation cost analyzer — models the real effort to discover, reach, and operate interactive web content
Battle-tested CLAUDE.md templates, agent definitions, and process docs for multi-agent Claude Code orchestration. Free a
A MCP (Model Context Protocol) client that uses Google Gemini AI models for intelligent tool usage and conversation hand
A Model Context Protocol (MCP) server that provides advanced code analysis and reasoning capabilities powered by Google'
Universal, language-agnostic development standards for software projects. Includes coding standards, git workflows, test
Automated Claude Code QA gate for AI-assisted development — Codex code review + Playwright browser smoke testing before
ABAP Accelerator is an MCP server that helps organizations create, test, document, and transform SAP ABAP code faster an
Claude Code / ARIS skills for turning a loose repository into a readable, testable, maintainable open-source project.
Reusable Claude Code skills for structured strategy debates, idea generation, and decision pressure-testing
Visual testing tool for MCP servers
Build Claude Code–style deep agents in Python: tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints
MCP server for Pipedrive CRM. 155 contract-tested tools, v2-first API, gated destructive ops. Works with Claude Desktop,
Claude Code plugin marketplace: 145 framework-aware code-review skills plus AI-writing detection, doc and test-plan gene
23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle
Claude Code agents and skills for automated Playwright E2E test generation, debugging, and planning using the Page Objec
A Claude Code skill that systematically eliminates unexpected output from a Ruby on Rails RSpec test suite
Deterministic AI workflow for ESP32 firmware development — structured missions, implementation contracts, debug playbook
Lightweight Red/Green TDD skill suite for Claude Code, Cursor, Codex, and Gemini CLI. Tests before code, always.