experiments

Orchestrates lifecycle, execution, monitoring and reporting of experiments.

29|3|Updated Mar 20, 2026
One-click install
npx skills add https://github.com/Vincentwei1021/Synapse --skill experiments
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: experiments
Source: https://github.com/Vincentwei1021/Synapse/tree/main/public/synapse-plugin/skills/experiments
Command: npx skills add https://github.com/Vincentwei1021/Synapse --skill experiments

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) and references (resource) components.

What problem does it solve?

It eliminates the friction of planning, executing, and reliably reporting research experiments across compute, sessions, and experiment lifecycle states.

Core Features & Use Cases

  • Experiment lifecycle management: draft plans, run self-review, move through pending review/start, and handle revisions.
  • Compute and execution orchestration: reserve GPUs, start experiments, run workloads with resilient logging/SSH access, and support parallel sub-agents.
  • Progress reporting and durable reporting: heartbeat monitoring for long runs, capture incidents when reusable lessons exist, submit results, and always save a full Markdown experiment report (including uploaded figures via the documents skill).

Use case: You have multiple approved experiment cards and want to start, track progress during long training runs, recover from execution issues, then produce a complete results writeup with charts and artifacts.

Quick Start

Ask your AI agent to run the experiments skill to check your assigned experiments, start the selected pending_start experiment, and then submit results followed by saving the full experiment report.

Frequently Asked Questions about experiments

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

FAQPage Schema
How do I manage the research lifecycle for Synapse experiments?

Manage Synapse experiment lifecycles by drafting plans, running self-reviews, moving through pending review to start, and handling revisions via correct tool-driven lifecycle transitions.

Can I reserve GPUs and orchestrate compute workloads for long training runs?

Reserve GPUs and start compute workloads to run long tasks with resilient logging, SSH access, and parallel sub-agents for complex experiment execution.

How does experiment monitoring work for long-running research tasks?

Experiment monitoring uses periodic progress heartbeats to track long runs and captures incident lessons during execution to ensure durable completion hygiene.

What is the best way to submit structured results and generate Markdown experiment reports?

Submit structured results and save full Markdown experiment reports with uploaded figures to ensure durable completion hygiene and comprehensive research documentation.

Does this experiment orchestration approach support AI agents and human researchers simultaneously?

Orchestrate Synapse experiments for both human researchers and AI agents by applying tool-driven lifecycle transitions to plan, execute, monitor, and report research tasks.

What are the limitations when running experiments without proper lifecycle transitions?

Skipping correct lifecycle transitions prevents proper compute reservation, blocks progress heartbeats, and fails to capture incident lessons or save durable Markdown experiment reports.