skills.rest
open-thoughts
open-thoughtsOFFICIAL
Explore all skills by this author →
WebsiteGitHub

supervisor-init

Bootstrap the lab supervisor role to orchestrate subagents, crons, and tools.

276|37|Updated Dec 5, 2025
Search Tags:#workflow#monitoring#orchestration#secrets#supervisor#ml-ops#init-checklist
One-click install
npx skills add https://github.com/open-thoughts/OpenThoughts-Agent --skill supervisor-init
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: supervisor-init
Source: https://github.com/open-thoughts/OpenThoughts-Agent/tree/main/.claude/skills/supervisor-init
Command: npx skills add https://github.com/open-thoughts/OpenThoughts-Agent --skill supervisor-init

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Bootstrap the supervisor role at the start of a session — the human-facing lab supervisor who manages a large multi-experiment ML-ops operation: the single interface between the user and subagents / crons / top-level tools, keeper of secrets, and tracker of everything in flight. Run this FIRST in a fresh session (or when the user says "set up", "init", "take over", "you're the supervisor", "get oriented"). It walks an init checklist (orient in .claude, load the local env, take custody of secrets, survey in-flight work + crons + subagents), states the operating discipline (verify subagent work, fix proactively without gating unless needed, secrets only via env vars), and concludes by (re)creating the 3-hour sweep loop (monitor-restore) and running an initial sweep (monitor-cron-sweep).

Core Features & Use Cases

  • Single interface between the user and subagents, crons, and top-level tools, coordinating multi-step work.
  • Enforce operating discipline and verify subagent deliverables to ensure reliable results.
  • Centralize secret management by using environment variables and avoiding raw secrets in prompts or files.
  • Survey in-flight work and trackers, maintain state, and bootstrap the 3-hour monitoring loop for continuous oversight.
  • Provide a repeatable startup sequence for fresh sessions to reduce setup time and errors.

Quick Start

Run this skill at the start of a fresh session to orient in .claude, load the local environment, take custody of secrets, survey in-flight work, and initialize the 3-hour monitor loop.

Frequently Asked Questions about supervisor-init

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I bootstrap an ML-ops supervisor to orchestrate subagents and crons?▼

To bootstrap an ML-ops supervisor, run a session initialization sequence that orients in .claude, loads the local environment, takes custody of secrets via environment variables, surveys in-flight experiments, and establishes a 3-hour monitoring loop.

What is the best way to coordinate multiple ML experiments across fresh sessions?▼

Coordinating multiple ML experiments across sessions requires a supervisor role that tracks in-flight work, enforces operating discipline by verifying subagent deliverables, and maintains state so you can reliably resume orchestration without losing context.

How do I securely manage secrets when orchestrating subagents in a multi-experiment setup?▼

Securely manage secrets by taking custody of them during initialization and ensuring they are only passed via environment variables, strictly avoiding raw secrets in prompts or files during subagent orchestration.

When should I run a session initialization checklist for ML-ops monitoring?▼

Run a session initialization checklist at the start of every fresh session or when you need to take over, get oriented, or set up the supervisor role to ensure all experiments, crons, and subagents are properly surveyed before work begins.

How does continuous monitoring work in a multi-experiment ML-ops environment?▼

Continuous monitoring works by establishing a 3-hour sweep loop during initialization, running an initial sweep immediately after setup to survey ongoing experiments, track in-flight tasks, and maintain operational oversight across sessions.

Do I need specific dependencies to set up automated ML-ops orchestration?▼

No specific dependencies are required to set up automated ML-ops orchestration; the initialization relies on orienting in the local .claude environment, loading existing configurations, and establishing the supervisor role from scratch.

Related Skills

Explore More Software Engineering Skills→
Camilo8902Camilo8902

env-secrets-manager

Manage environment variables and secrets with encryption, rotation, and provider integration.

Community
Advanced
open-thoughtsopen-thoughts
276

monitor-restore

Restore the 3-hour Jupiter+Leonardo cluster sweep loop via /loop 3h or CronCreate.

Official
Advanced
caio-moliveiracaio-moliveira
36

deep-agents-orchestration

Coordinate subagents, plan tasks, and enforce human approval in AI workflows.

Community
Advanced
founderphantomfounderphantom

weights-and-biases

Track ML experiments and manage hyperparameter sweeps with Weights & Biases.

Community
Advanced