run-experiment

Orchestrate Phase 2 experiment runs and write result_{n}.md files.

Updated Apr 19, 2026

Search Tags:#automation #orchestration #pipeline #experiment #fidelity #phase-2

Ready to run

npx skills add https://github.com/YurainSoon/research-director --skill run-experiment-yurainsoon

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: run-experiment
Source: https://github.com/YurainSoon/research-director/tree/main/.claude/skills/run-experiment
Command: npx skills add https://github.com/YurainSoon/research-director --skill run-experiment-yurainsoon

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Main Agent orchestration skill for Phase 2 experiment execution coordinates the entire lifecycle: it launches runs for fidelity-passed module sets, tracks progress, and writes phase_2_verification/results/result_{n}.md for analysts to interpret, while remaining backend-agnostic and ensuring runs detach safely.

Core Features & Use Cases

Orchestrates Launch / Finalize workflows for Phase 2 experiments.
Writes structured result files, plus logs and sentinel checks for completion.
Supports multiple backends (local, SSH, SLURM, containers) and abstracts execution details.

Quick Start

Trigger Run in Launch mode once all fidelity reports are ALL CLEAR and the spec is ready; the skill will orchestrate background execution and artifact creation.

Frequently Asked Questions about run-experiment

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

FAQPage Schema

How do I orchestrate end-to-end experiment pipelines after module fidelity checks pass?▼

Orchestrating experiment pipelines requires triggering Launch mode once all fidelity reports are ALL CLEAR. The skill then manages the full lifecycle, detaching long-running processes safely and writing structured result files for analyst interpretation.

What is the Phase 2 experiment execution lifecycle contract and how does it work?▼

The Phase 2 experiment lifecycle contract ensures runs are launched and finalized correctly using sentinel-based completion checks. It manages run and log operations while remaining backend-agnostic, detaching background execution safely.

Can I run experiment workflows on SSH or SLURM backends?▼

Yes, experiment workflows support SSH, SLURM, local, and container backends. The skill abstracts execution details and remains backend-agnostic, allowing designated workflow runners to execute across multiple environments.

How do I generate structured result files for analyst interpretation from experiment runs?▼

Generating structured result files happens automatically during the Finalize phase of experiment execution. The skill writes phase_2_verification/results/result_{n}.md files along with logs and sentinel checks upon run completion.

Do I need a designated runner available to execute experiment workflows?▼

Yes, a designated runner is required to execute experiment workflows. The skill applies to environments where modules are ready, fidelity reports are ALL CLEAR, and a runner is available to handle the workflow.

When should I not use this approach for experiment automation?▼

You should not use this approach if fidelity reports are not ALL CLEAR or if modules are not ready. It requires a designated runner and only applies when the spec is ready and the environment supports safe background process detachment.