Chief

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.

What its author says it does

Copied from the file, not written here

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.

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

Gives 0 of the 12 instructions most agent orchestration skills give in 622 tokens

Counted across 742 of the 995 authors here whose files we hold, read 2026-08-06

run the full test suite after integrating changesin 53 of 742, across 20 files
reference existing artifacts by path or URLin 52 of 742, across 22 files
dispatch one agent per independent problem domainin 50 of 742, across 17 files
verify fixes do not conflictin 45 of 742, across 13 files
include a suggested skills section in the documentin 45 of 742, across 15 files
redact sensitive informationin 41 of 742, across 11 files
save to the temporary directory of the operating systemin 39 of 742, across 9 files
tailor the document to user-provided focus argumentsin 39 of 742, across 9 files
spot check agent changes for systematic errorsin 34 of 742, across 7 files
write a handoff document summarising the current conversationin 31 of 742, across 6 files
assign each agent a specific scopein 23 of 742, across 8 files
provide specific scope and clear goalin 23 of 742, across 5 files

Said here and by no other author read

clone the repository
install the package in editable mode
execute ml training jobs via cli
execute model fine-tuning jobs via cli
generate api projects via cli
generate docker configurations via cli

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.