Home / Subagents / ml_engineer

ml_engineer

josstei/maestro-orchestrateSubagent

Machine learning engineering specialist for designing, training, evaluating, and shipping production ML models. Use when the task requires feature pipeline design, model training code, evaluation harnesses, or integrating models into application code. For example: building a classifier training pipeline, wiring a model behind a REST endpoint, or reproducing a paper's baseline.

ScannedSubagentSource: GitHub
486 stars Updated 16d ago License Apache-2.0 Context ≈98 tokens in your chat
59popular

Why this score

Stars8/35
Usage (forks)1/15
Upkeep25/25
License15/15
Owner history10/10

This repo hosts 40 subagents, so its 486 stars are split between them (about 12 each) for scoring.

Popularity score: 59/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

What it can use

    Tools listed in the file: read_file

    The agent file

    ---
    name: ml_engineer
    kind: local
    description: "Machine learning engineering specialist for designing, training, evaluating, and shipping production ML models. Use when the task requires feature pipeline design, model training code, evaluation harnesses, or integrating models into application code. For example: building a classifier training pipeline, wiring a model behind a REST endpoint, or reproducing a paper's baseline."
    max_turns: 25
    tools:
      - read_file
      - list_directory
      - glob
      - grep_search
      - write_file
      - edit
      - run_shell_command
      - todo_write
      - skill
      - read_many_files
      - ask_user_question
      - web_search
    ---
    
    Agent methodology loaded via MCP tool `get_agent`. Call `get_agent(agents: ["ml-engineer"])` to read the full methodology at delegation time.
    

    Apache-2.0 license, from josstei/maestro-orchestrate at commit 192203abcb33.

    Security

    Scanned Oct 21, 2026 at commit 192203abcb33, with Cisco's open-source skill-scanner.

    None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

    A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

    Alternatives

    Other makers' add-ons that do the same job, next to this one.

    NameScoreStarsContextUpdated
    This oneml_engineer josstei/maestro-orchestrate · Subagent 59★ 486≈98 in chat16d ago
    ml-engineering stas00/ml-engineering · Skill Both about ml and engineering 88★ 20k≈22 always19d ago
    domain-ml moeru-ai/auv · Skill Same job: machine learning 59★ 118≈53 always16d ago
    ml-research-lab AnastasiyaW/codex-claude-code-config · Skill Both about ml and classifier 62★ 212≈112 always16d ago
    autoresearch-ml proyecto26/autoresearch-ai-plugin · Skill Both about ml and training 47★ 13≈23 always4mo ago
    ml-product-analysis joomcode/joompulse-skills · Skill Both about ml 52★ 54≈25 always1mo ago