MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Agent skills for native mobile craftsmanship: clean architecture, SOLID, TDD, testing, audits, CI/CD, Figma to Compose/SwiftUI, API mocking and ADRs.
SkillMIT★ 2Few starsNo key
Lifecycle-shaped Claude Code agent kit: scheduled audits → ready-state issues → developer-agent PRs → multi-persona advisory review. Six named PR reviewers, five audit scanners, one installer. Claude-
SkillMIT★ 9No key
Deterministic UI engine for tests and agents — stable locators and self-healing without ML in core; optional LLM enhancements and MCP tools when you need them.
SkillApache-2.0★ 2Few starsNo key
Everything AI agents need to master the full Kaltura platform — The Agentic Digital Experience Platform. Live-tested API guides with curl examples and end-to-end test scripts. Agent Skill, llms.txt, a
SkillMIT★ 5No key
atomic dsh — a terminal chat UI for DeepSeek. 50+ themes with live preview, powerline status bar. MCP servers and skills load on demand (lazy) — tool schemas stay ~94% smaller. Recursive task tree. Ha
Node.jsMIT★ 1Few starsNo key
The first MCP server for autonomous Flutter testing on real iPhones and Android devices. 110 tools across Android (uiautomator2+adb), iOS (WebDriverAgent+pymobiledevice3), Flutter (Patrol + flutter ru
SkillApache-2.0★ 6No key
Agent Skill for analysis-first prompting: understand the user's intention before writing the prompt, then define what done looks like. For agent briefs, decisions & high-stakes prompts.
SkillMITFew starsNo key
App Store screenshot capture CLI (simctl only, no XCUITest)
SkillMIT★ 3Few starsNo key
Loop engineering for Claude Code — a skill that turns an idea into a production-grade, memory-backed agent loop. Classify, scope, derive state, emit a /loop-ready prompt. Stop prompting; design the lo
SkillMIT★ 5No key
Portable Agent Plugin with reusable Agent Skills and MCP integrations for rigorous software research, planning, code audits, documentation, UI design, and development workflows.
SkillMITFew starsNo key
Cross platform Bash based Coding Agent with minimal UI, most used tool_calls plugins in built and good token efficiency
SkillApache-2.0★ 2Few starsNo key
10 agent skills across the full software-engineering lifecycle (plan, design, build, secure, ship, operate) with deterministic checks, graded evals, and one-line install for Claude Code, Codex, and Co
SkillMITFew starsNo key
本地优先的 Agent 桌面基础设施：MCP 网关 + 可插拔连接器 + 权限层 + Tauri 外壳，无托管控制平面。
SkillMITFew starsNo key
Mutation testing for Playwright UI tests: sabotage the DOM and find out whether your end-to-end suite actually notices.
SkillMIT★ 1Few starsNo key
Open-source game development skills — reusable workflows for texture processing, audio, level generation, asset optimization, and more.
SkillMIT★ 9No key
Turn Playwright trace.zip into flows, API sequences, and ready-to-run tests
Node.jsMIT★ 2Few starsNo key
Ready-made, tested GDScript building blocks for Godot 4.7+: cooldowns, screen shake, loot tables, state machines, saves, UI, networking. Step-by-step guides for every module, plus an AI-assistant skil
SkillMITFew starsNo key
Spec & Impact by WillGT: give AI agents a spec they can prove they built. Change impact, technical design, executable spec packages. Claude Code plugin, Apache-2.0.
SkillApache-2.0Few starsNo key
Voice-first agent ecosystem: speaker-gated, local LLM brain (D-VOICE), tunable TTS, real-time task narration.
PythonMIT★ 2Few starsNo key
A collection of production-grade, language-agnostic skills for AI coding agents, providing engineering standards, security guardrails, operational checklists, design guidance, and best practices acros
SkillMIT★ 1Few starsNo key
DomainText is a compact and agent-friendly Domain Modeling DSL for describing software entities, relationships, inheritance, and ownership.
SkillMITFew starsNo key
OCC (Orchestrator Chain Chimera) YAML-first LLM orchestrator. Multi-model chains with auto-parallelism, 30 pre-tools at zero token cost, React canvas, MCP, REST API. 70% faster/cheaper than naive appr
SkillMIT★ 7No key
End-to-end tests and debugging for live JUCE WebView UIs (WKWebView/WebView2): click and fill the DOM, eval JS, inspect console/network, check native C++ state, capture WebGL/canvas screenshots. Also
SkillMIT★ 5No key
Who stands behind it
