By mastra-ai
Build Mastra AI applications by setting up projects via CLI or manual TypeScript configs with Next.js/Express, looking up embedded node_modules docs and remote references for exact APIs, implementing agents/workflows/tools/memory/RAG with Postgres/MongoDB/OpenAI/Anthropic, and troubleshooting migrations.
npx claudepluginhub mastra-ai/skills --plugin mastra-skillsOfficial Mastra skills for agents working with the Mastra framework. Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack.
npx skills add mastra-ai/skills
Mastra also supports the .well-known skills discovery standard:
npx skills add https://mastra.ai/
Single comprehensive skill for all Mastra development. Uses progressive disclosure with reference files covering:
references/create-mastra.md): CLI and manual project setupreferences/embedded-docs.md): Find APIs in node_modules/@mastra/*/dist/docs/references/remote-docs.md): Fetch from https://mastra.ai/llms.txtreferences/common-errors.md): Common errors and solutionsreferences/migration-guide.md): Version upgrade workflowsMain skill file teaches core concepts and routes to appropriate reference files based on user questions.
git clone https://github.com/mastra-ai/skills.git
Then configure your agent to load skills from the cloned directory.
.well-known skills discoveryThis repository is served via the RFC 8615 Well-Known URI at https://mastra.ai/.well-known/skills/.
Agents can discover available skills by fetching:
https://mastra.ai/.well-known/skills/index.jsonhttps://mastra.ai/.well-known/skills/mastra/SKILL.mdThis enables automatic skill discovery without manual configuration.
Contributions welcome!
SKILL.md filesApache-2.0 - See LICENSE for details
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Design fluency for frontend development. 1 skill with 23 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer