experiment-bridge

Convert EXPERIMENT_PLAN.md into executable GPU experiments and initial results.

1|Updated Mar 25, 2026

Search Tags:#automation #planning #deployment #pipeline #execution #gpu #experiment

Ready to run

npx skills add https://github.com/HeXiao-55/Auto-SurveyMind --skill experiment-bridge-hexiao-55

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: experiment-bridge
Source: https://github.com/HeXiao-55/Auto-SurveyMind/tree/main/skills/experiment-bridge
Command: npx skills add https://github.com/HeXiao-55/Auto-SurveyMind --skill experiment-bridge-hexiao-55

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Bridge the gap between idea discovery and automated experiments by turning an experiment plan into executable code, deploying it to GPUs, and collecting initial results.

Core Features & Use Cases

Reads and interprets EXPERIMENT_PLAN.md
Generates runnable experiment scripts and deployment configuration
Tracks initial results across GPUs and logs to EXPERIMENT_TRACKER.md
Use Case: researchers can go from plan to running experiments with minimal hand-offs.

Quick Start

Run /experiment-bridge with EXPERIMENT_PLAN.md to initialize implementation and deployment workflows.

Frequently Asked Questions about experiment-bridge

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

FAQPage Schema

How do I automate GPU deployment from an experiment plan?▼

To automate GPU deployment from an experiment plan, the tool reads EXPERIMENT_PLAN.md to generate runnable scripts, configure deployment, and collect initial results across GPUs. It tracks execution parameters like MAX_PARALLEL_RUNS and AUTO_DEPLOY.

What files do I need to turn an experiment plan into executable code?▼

To turn an experiment plan into executable code, you need refine-logs/EXPERIMENT_PLAN.md and EXPERIMENT_TRACKER.md, plus FINAL_PROPOSAL.md and IDEA_CANDIDATES.md. Configuration flags like BASE_REPO, CODE_REVIEW, and SANITY_FIRST are also interpreted to generate executable experiments.

Can I run sanity checks before full automated experiment deployment?▼

Yes, you can run sanity checks before full deployment by setting the SANITY_FIRST configuration flag. This ensures initial validation occurs before executing broader automated experiments and collecting results across GPUs.

How does parallel execution work for automated experiments?▼

Parallel execution for automated experiments is controlled by the MAX_PARALLEL_RUNS configuration flag. It manages concurrent GPU deployments and logs progress directly into EXPERIMENT_TRACKER.md during results collection.

Does the experiment automation pipeline support code review?▼

Yes, the experiment automation pipeline supports code review through the CODE_REVIEW configuration flag. This allows automated generation of runnable experiment scripts to be validated before GPU deployment and execution.