vercel-labs/agent-skills
Vercel's official skills
OpsBerry
CybersecurityAI-Powered Identity Security by OpsBerry AI
seoGeek
SEOAll-in-one SEO and digital marketing tool
lotabout/write-a-C-interpreter
Write a simple interpreter of C. Inspired by c4 and largely based on it.
ResumAI
AI ChatbotsExpert Software Consulting Services by Starbelly Software
GEPA (2025)
Reflective evolution outperforms GRPO by 6–20 pts with fewer rollouts
MCPAGENTSEEK
Search ToolsGlobal search engine for MCP tools and AI agents
SferaAI
MarketingAll-In-One Software Built For Retail Service Businesses
Internal Safety Collapse in Frontier LLMs (2026)
Introduces TVD framework and ISC-Bench — frontier models fail at 95.3% rate on dual-use professional tasks where capability and harm co-occur; advanced models are *more* vulnerable than earlier LLMs because their capabilities become liabilities
AI Engine on Meow Apps
Website BuildersElevate Your WordPress with AI Engine by MeowApps
FormHug
Forms & SurveysAI form builder for registration, surveys, quizzes, assessments, bookings, and payments
Buzz Chat
Social Media ManagementBuzz Chat: Africa's AI-Powered Social Network Revolution
Docker Model Runner
Developer ToolsDocker Model Runner - Run AI Models Locally With Docker
Formisoft AI
Forms & SurveysGet patients ready. Keep care on schedule.
exoticknight/mcp-file-merger
文件合并工具,适用于 AI 聊天长度限制。
FormStory io
Forms & SurveysNever miss a client – capture lost leads and fix broken forms.
Pipecat
Open Source framework for voice and multimodal conversational AI. 
GenZ 4 Meme
I help u understand the lingo & the latest memes
AgapeVerse.app
New AI ToolsThe AI poem studio for meaningful moments
jonas/tig
Text-mode interface for git
Treblle
New AI ToolsEnterprise Runtime Intelligence for APIs and AI Agents
Memory in the LLM Era: Modular Architectures in a Unified Framework (April 2026)
Decomposes agent memory into 4 modules (extraction, management, storage, retrieval); systematic benchmark comparison of all methods; composite design from existing modules surpasses prior SOTA
Combee: Scaling Prompt Learning for Self-Improving Agents (April 2026)
Berkeley/Stanford (Stoica, Zou, Gonzalez): scales parallel prompt learning with up to 17x speedup over ACE/GEPA via parallel scans and dynamic batching; evaluated on AppWorld, Terminal-Bench, FiNER
Ask Seneca
Task ManagementSeneca: The Minimalist's Choice for Note-Taking