Testing Skills

lllllllama/RigorPilot-Skills

RigorPilot Skills provides a research-first suite of agent skills designed to keep AI-assisted deep learning experiments grounded in reproducibility, evidence, and auditable changes.

ThreeMoonsLab/agents-shipgate

Agents Shipgate is a deterministic merge gate for AI-generated agent capability changes, analyzing tool sources and configurations locally without agent execution or network calls.

nf-core/modules

This skill provides instructions and coding standards for AI agents working within the nf-core/modules repository, governing Nextflow module and subworkflow development.

microsoft/PromptKit

PromptKit is a composable, version-controlled library of agentic prompt components designed to engineer reliable, repeatable prompts for software and engineering tasks.

agentspan-ai/agentspan

AGENTS.md guide for the Agentspan Python SDK, detailing architecture, compilation pipelines, testing standards, and development workflows for AI agents contributing to the codebase.

SolidInvoice/SolidInvoice

SolidInvoice is a comprehensive guide and assistant framework for the SolidInvoice open-source invoicing and billing application built on Symfony and PHP.

infiniflow/ragflow

RAGFlow is an open-source Retrieval-Augmented Generation engine based on deep document understanding. It provides robust ingestion, OCR, parsing, and workflow canvas components for building enterprise-grade RAG applications.

vercel-labs/agent-browser

A high-performance browser automation CLI written in Rust designed specifically for AI coding agents and automated workflows.

CherryHQ/cherry-studio

This skill defines the development guidelines, architecture rules, and testing standards for contributing to the Cherry Studio project.

adrianco/retort

This skill acts as a qualitative analysis tool for Retort Design of Experiments (DoE) runs, aggregating factor effects, evaluating replicate variance, and surfacing code divergence.

wshobson/agents

A comprehensive multi-harness agentic plugin marketplace providing production-ready building blocks, agents, skills, and commands from a single Markdown source of truth.

microsoft/playwright

Playwright is a comprehensive framework for cross-browser web automation and end-to-end testing, supporting AI agent integrations via CLI and MCP protocols.

QoderAI/better-harness

Better Harness provides open-source insights for the Agent Work Loop, turning project and session evidence into prioritized improvements and verifiable next steps across multiple coding agents.

HugoRCD/evlog

This skill defines the development guidelines, rules, and commands for contributing to the evlog TypeScript logging library monorepo.

chamilo/chamilo-lms

This skill guides the creation of Playwright and Gherkin test suites for Chamilo LMS features by analyzing live application instances rather than relying solely on static source code.

msaad00/agent-bom

This repository provides engineering and operating guidelines for developing agent-bom, an open security scanner and self-hosted control plane for AI-era infrastructure.

soden46/syarif-laravel-ai-skills

Syarif Laravel AI Skills is a comprehensive library of 72 installable Laravel skills designed to extend AI coding assistants with specialized PHP and Laravel workflows. It features a lightweight orchestrator, least-code minimization gates, and risk-aware execution protocols.

idavidov13/agentic-playwright

Acts as the primary intent router and workflow orchestrator for an AI-assisted Playwright test automation scaffold. Manages an 8-phase execution protocol that enforces strict confidence gates, exploratory evidence gathering, and task-specific routing.

hotosm/ui

AI coding agent operational guidance and architecture specification for the hotosm/ui shared web components repository.

callstackincubator/cali

Cali is a role-oriented CLI platform for React Native and Expo teams designed to automate mobile QA, code reviews, performance evaluations, and implementation tasks.

DHTMLX/gantt

This skill provides guidance and structural context for AI coding agents working with the open-source DHTMLX Gantt Community Edition JavaScript library.

TulipaEnergy/TulipaEnergyModel.jl

An AI agent configuration and developer guide for TulipaEnergyModel.jl, a Julia package for energy system modeling and optimization.

gsd-build/gsd-browser

A native Rust browser automation CLI designed for AI agents and developers, providing deterministic control over Chrome/Chromium via Chrome DevTools Protocol (CDP).

painted-porch/marcus

Epictetus is an AI code auditor and grading system that systematically evaluates software projects, code quality, and the agents or developers who built them.

dev-toolings/superpowers-symfony

Superpowers Symfony is an expert Claude Code plugin providing 44 specialized skills, 7 subagents, and 13 slash commands tailored for Symfony 7.4/8.x and API Platform v4 development.

RedHatProductSecurity/prodsec-skills

A comprehensive library of tool-agnostic security skills designed to help AI coding assistants shift security left during development.

gjw199513/babel-agent-os

Babel AgentOS is a local-first platform for building, debugging, publishing, and operating AI applications, workflows, and tools. This instruction set provides backend development and architecture guidelines for the Python/Flask API repository.

VoltAgent/awesome-agent-skills

A comprehensive, hand-picked collection of official Agent Skills created and used by leading development teams and the community.

leboncoin/spark-web

This configuration provides AI agents with guidelines and workflows for interacting with the Nx monorepo and React design system components within the spark-web repository.

stbenjam/skillsaw

Skillsaw is a configurable, rule-based linter designed for validating agentic contextual building blocks, prompts, and plugins across various AI ecosystems.

DenisSergeevitch/repo-task-proof-loop

Repo Task Proof Loop enforces a rigorous, verifiable workflow for complex coding tasks by separating implementation from independent verification. It maintains durable task state and artifacts directly within the repository under `.agent/tasks/`.

jnPiyush/AgentX

AgentX is a comprehensive multi-agent workflow and orchestration system featuring 26 specialized agent roles, rigorous quality loops, and strict pipeline governance.

JamesonRGrieve/ServerFramework

An AI development and coding skill focused on the Zephyrex FastAPI-based server framework, enforcing strict architectural guidelines, testing protocols, and design patterns.

abhigyanpatwari/GitNexus

GitNexus is an advanced code intelligence and graph-analysis skill set that integrates with AI coding agents to provide deep structural awareness, impact analysis, and workflow orchestration.

wly12312/issue-proof-for-codex

IssueProof for Codex is a Windows-based verification tool that records privacy-filtered evidence for open-source maintenance tasks. It helps developers reproduce issues, ingest Codex JSONL traces, and generate audit receipts.

martaldsantos/gh-copilot-for-enterprise

A comprehensive enterprise-grade hackathon resource featuring 19 challenge tracks to master GitHub Copilot across various roles and tech stacks.

probabl-ai/skills

Executes and audits machine learning experiment reports using a read-only Python script runner and generates markdown digests for narrative tracking.

intersystems-community/iris-agentic-dev

An MCP server and toolset that enables AI coding assistants to interact directly with InterSystems IRIS database instances for development and testing.

cuellarfr/design-skills

This skill guides developers and designers through conducting comprehensive WCAG 2.2 accessibility audits for digital products.

moonbitlang/openseek

OpenSeek is a MoonBit-based foundation for a DeepSeek-backed coding agent, providing agent orchestration, durable session storage, and a built-in terminal UI.

Nink1992/Starbucks-Design-main

This skill guides AI agents through a structured, multi-phase workflow for developing and maintaining design system components and page templates using React and Vue. It enforces strict separation between base components, business components, and page templates while aligning with Figma designs and Arco Design tokens.

baimard/gestion

AI development guidelines and setup instructions for Gestion, a business management and invoicing application built for Nextcloud.

willcoliveira/qualiow-playwright-skills

This skill provides a command-line interface for browser automation, enabling AI agents to navigate web pages, interact with elements, fill out forms, and extract page data using Playwright.

duhuazhu/BugPack

This skill enables AI agents to automatically retrieve bug details, locate relevant codebase files, apply bug fixes, and update bug status using the local BugPack server.

facebookresearch/autoform-bot

A multi-agent pipeline designed to translate LaTeX mathematics into verified Lean 4 proofs using Mathlib.

eobarretooo/ClawLite

ClawLite is a Python-based autonomous agent framework and gateway featuring background loops, multi-channel support, and provider routing.

clivejefferies/mobile-debug-tools

An MCP server skill package providing AI assistants with mobile app debugging and testing capabilities for Android and iOS.

stbenjam/claudelint

Claudelint is a configurable, rule-based linter designed to validate Claude Code plugins and plugin marketplaces. It detects structural issues, checks metadata correctness, and supports custom validation rules.

aj-geddes/unicorn-team

A comprehensive Claude Code plugin that encodes advanced software engineering expertise into a coordinated team of 6 specialized agents and 15 composable skills.

Codagent-AI/agent-validator

Agent Validator provides a configurable feedback loop runner for AI-assisted development, executing relevant tests, linters, and AI reviews when code changes.

luojiyin1987/typos-skill

A portable skill that integrates the typos CLI with a structured, LLM-reviewable workflow to safely detect and correct spelling issues.

frenzymath/Archon

Archon is an autonomous multi-agent orchestration framework designed for formal theorem proving and complex project execution using Lean 4 and various LLM backends.

StonyBrookNLP/appworld

AppWorld is an interactive benchmark and simulation environment featuring 9 apps and 457 APIs for evaluating function calling and coding agents.

addyosmani/adverse

Multi-agent adversarial code review skill that spawns three distinct reviewer subagents (Auditor, Adversary, Pragmatist) in parallel, conducts a cross-examination phase, and deterministically synthesizes the results.

lobehub/lobehub

Development guidelines and architecture rules for AI coding agents working within the LobeHub repository.

xun404/dify-agent-skill-plugin

An intelligent agent plugin for Dify that dynamically activates specialized development skills like code analysis, documentation generation, and testing based on user queries.

ColdBox/coldbox-cli

ColdBox CLI is a CommandBox module designed to scaffold and manage ColdBox framework and BoxLang applications, alongside integrated AI coding agents and skills.

root-gg/plik

AI agent instructions and architectural guide for developing and maintaining Plik, a temporary file-sharing system written in Go with a Vue 3 web UI and CLI client.

alaminfirdows/agentic-engineering-demo

This skill provides comprehensive development guidelines, architectural rules, and integration workflows for building Laravel applications using AI agents like Claude Code.

getcellm/cellm

A systematic triage skill for resolving Sentry production bugs through root cause analysis, failing tests, and minimal fixes.