agentsclimarketplace

Chief

Skill muhammederem/chief

Multi-agent orchestration framework for automating ML/AI, backend, and DevOps workflows. Use when building ML pipelines, training models, creating APIs, deploying to cloud, or setting up infrastructure.From its SKILL.md

Install
npx -y skills add muhammederem/chief

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.7 KB, 622 tokens by cl100k_base, as published. Nobody here has run it

Chief Orchestration Framework

Chief is a powerful multi-agent orchestration framework that automates complex workflows across ML/AI, backend development, and DevOps.

When to Use

Use Chief when you need to:

  • Train or fine-tune ML models (PyTorch, Hugging Face, LangChain)
  • Build backend APIs (FastAPI, GraphQL, REST)
  • Deploy to cloud (AWS Lambda, SageMaker, ECS)
  • Create CI/CD pipelines (GitHub Actions, GitLab CI)
  • Generate infrastructure (Terraform, Docker, Kubernetes)
  • Build RAG applications with vector databases

Installation

git clone https://github.com/muhammederem/chief.git
cd chief
pip install -e .

Quick Commands

ML/AI Workflows

# Train a PyTorch model
chief exec /train model_type=cnn dataset=/data/images epochs=50

# Fine-tune Hugging Face model
chief exec /finetune model=bert-base-uncased dataset=custom_data output_dir=/models/bert

# Build RAG pipeline
chief exec /rag llm=gpt-4 vector_db=pinecone data=/documents

Backend Development

# Generate FastAPI project
chief exec /api project_name=my_api framework=fastapi features=auth,database

# Add Docker configuration
chief exec /dockerize app_type=fastapi port=8000 include_compose=true

# Integrate database
chief exec /database type=postgresql orm=sqlalchemy

DevOps & Deployment

# Deploy to AWS Lambda
chief exec /deploy service=lambda app_name=processor runtime=python3.9

# Create CI/CD pipeline
chief exec /pipeline platform=github stages=test,build,deploy

# Generate Terraform config
chief exec /terraform provider=aws resources=ec2,s3,rds region=us-west-2

Project Templates

Generate complete project scaffolds:

# List available templates
chief template list

# Generate PyTorch project
chief template generate pytorch-starter my_project

# Generate FastAPI microservice
chief template generate fastapi-microservice my_api

# Generate MLOps pipeline
chief template generate mlops-pipeline my_pipeline

Key Features

  • Multi-Agent System: ML Engineer, Backend Architect, DevOps Engineer
  • Intelligent Routing: Automatically routes tasks to the right agent
  • Domain Knowledge: Auto-loads skills for PyTorch, Hugging Face, FastAPI, AWS, etc.
  • Project Templates: Ready-to-use scaffolds for common architectures
  • Load Balancing: Work-stealing, round-robin strategies for parallel execution

Documentation

See docs/ for complete documentation.

Repository

https://github.com/muhammederem/chief

What ships with it: 92 files

563.4 KB alongside SKILL.md, 66 of them executable

.claude/

chief/

52 more files not listed here. See all 92 in the repository.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.