experiment-plan

Convert research proposals into claim-driven experiment plans with run order and budgets.

Updated Apr 18, 2026
One-click install
npx skills add https://github.com/THUFanZd/Sewed_pipeline --skill experiment-plan-thufanzd
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: experiment-plan
Source: https://github.com/THUFanZd/Sewed_pipeline/tree/main/.agents/skills/experiment-plan
Command: npx skills add https://github.com/THUFanZd/Sewed_pipeline --skill experiment-plan-thufanzd

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill converts a refined research proposal or method idea into a detailed, claim-driven experiment roadmap that defends the core contributions. It helps researchers turn concept into concrete experiments, run orders, budgets, and risk analyses, ready for paper submission or internal validation.

Core Features & Use Cases

  • Convert proposals into a compact, claim-driven experimental plan with an evidence map
  • Define a concise run order, data/compute budgets, and success criteria
  • Generate an execution-ready plan and tracker files (EXPERIMENT_PLAN.md and EXPERIMENT_TRACKER.md)

Quick Start

Provide me with a refined proposal and I will generate a complete experiment plan and execution roadmap.

Frequently Asked Questions about experiment-plan

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

FAQPage Schema
How do I turn a research proposal into a paper-ready experiment plan?

To create an experiment plan, you provide a refined research proposal to generate a claim-driven roadmap with run orders, budgets, and risk analyses. This process maps core contributions to concrete experiments, yielding execution-ready outputs for paper submission.

What is a claim-driven experiment plan for machine learning research?

A claim-driven experiment plan is a structured roadmap that directly maps research contributions to evaluation protocols and ablation plans. It enforces explicit success and failure criteria, ensuring every experiment defends a specific claim from the proposal.

How do I define run order and compute budgets for ML experiments?

Defining run order and compute budgets involves structuring deterministic experiment sequences and allocating data resources. The plan establishes a concise execution roadmap with explicit milestones, ensuring experiments are sequenced logically within resource limits.

Can I use this for data science projects that need ablation plans?

Yes, this works for typical data science projects by generating ablation plans alongside the core experiment plan. It structures the evaluation protocol to isolate variables, directly supporting validation requirements for data science research.

What files do I need to track experiment progress and milestones?

You need an execution tracker file to monitor progress and milestones. The workflow generates EXPERIMENT_PLAN.md and EXPERIMENT_TRACKER.md files, providing structured blocks and deterministic run sequencing to document success and failure criteria.

Does this experiment planning approach handle risk analysis?

Yes, the experiment planning approach includes risk analysis across the full workflow. It converts your proposal into a detailed plan that addresses potential failures through explicit success criteria and structured risk mitigation blocks.