convez.ai
MCP Server
AdSoares

ai-playbook

AdSoares/ai-playbook

Ver no GitHub
BomPluginScore · de 0 a 100

Curated collection of LLM and agent artifacts: prompts, agents, skills, MCP servers, and evals.

Instalação

$npx convez-ai AdSoares/ai-playbook

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
0
Acompanhando
0
Saúde
85%
Último commit
há 5 meses
Versão
—
Issues abertas
0
Contribuidores
1

README

A tradução para o português deste README ainda está na fila.

AI Playbook

A curated collection of artifacts for working with LLMs and agents: prompts, agents, skills, MCP servers, and evals.

License: MIT PRs Welcome Markdown Lint

This repository is an open playbook: reusable, battle-tested artifacts ready to copy, adapt, and share. The goal is to shorten the gap between "I have an idea for an agent" and "I have something working."


📂 Structure

ai-playbook/
├── prompts/        ← prompt templates and libraries
├── agents/         ← agent definitions (AGENTS.md, system prompts, configs)
├── skills/         ← reusable skills (packaged capabilities)
├── mcp/            ← Model Context Protocol servers and configs
├── evals/          ← evaluation suites and benchmarks
├── examples/       ← end-to-end code examples
└── docs/           ← guides and supporting material

Each folder has its own README.md explaining its conventions, artifact format, and how to contribute.

FolderWhat you'll findStart here
prompts/System prompts, few-shot templates, instruction patternsprompts/README.md
agents/Complete agents: role, tools, guardrailsagents/README.md
skills/Packaged capabilities, portable across agentsskills/README.md
mcp/MCP servers and client configurationsmcp/README.md
evals/Datasets, rubrics, and evaluation scriptsevals/README.md
examples/Runnable example projectsexamples/README.md

🚀 How to use

  1. Browse the folder for the artifact type you need.
  2. Each artifact is self-contained — read its header/README for prerequisites.
  3. Copy, adapt to your context, and give credit where it makes sense.

🤝 Contributing

Contributions are welcome! See the contribution guide and the code of conduct. Each category defines a standard template — follow it to keep things consistent.

📜 License

Released under the MIT license. Use, modify, and share freely.


Maintained by Ad Soares.

Ver o original no GitHub

Relacionados