Agent skills to find and fix software bugs

Chrome DevTools for coding agents

Fluent argument validation for fluent software development.

An MCP server to allow you to debug webpages using LLMs

File-backed workflow harness for reliable Claude Code and Codex sessions.

A workflow framework for statistical package development

OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

Unofficial Ruby SDK for Claude Agent

A structural code search engine for Al agents.

Keeping your agents out of trouble with sandboxed coding agent automation

Use sidecar next to CLI agents for diffs, file trees, conversation history, and task management with td

Multi-Agent Harness for Production AI

O Specsfy ajuda você a transformar uma ideia em software testado sem espalhar requisitos, planos e tarefas por vários arquivos.

Real-time visualization of Claude Code agent orchestration — see your agents think, branch, and coordinate as they work.

Agentic Software Engineering (ASE)

The secure, validated skill registry for professional AI coding agents. Extend Antigravity, Claude Code, Cursor, Copilot and more with absolute confidence.

Open-source local workbench for multi-agent software development.

Agent-SDK without CLI dependencies, as an alternative to claude-agent-sdk, completely open source

The graph based agentic IDE

Terraform & OpenTofu Skill for AI Agents - testing, modules, CI/CD, and production patterns

Session lifecycle management for Claude Code — persistent memory, soul purpose, reconcile, harvest, archive

Unified execution environment for Python code, shell commands, and programmatic MCP tool calls.

Containment for AI agents - user isolation, sandboxed execution, network controls, backup/rollback. TLA+ verified.

A collection of MATLAB coding rules and guidelines optimized for use with AI coding assistants like Cursor, Windsurf, Claude Code, and GitHub Copilot