skills.rest
Wenwen555
Wenwen555COMMUNITY
Explore all skills by this author →
GitHub

experiment-plan

Convert research proposals into claim-driven experiment plans with run trackers.

Updated Apr 1, 2026
Search Tags:#reproducibility#research-design#paper-writing#evaluation-protocol#milestone-tracking#experiment-plan#ablation-study
One-click install
npx skills add https://github.com/Wenwen555/ARIS-LVLM --skill experiment-plan-wenwen555
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: experiment-plan
Source: https://github.com/Wenwen555/ARIS-LVLM/tree/main/skills/experiment-plan
Command: npx skills add https://github.com/Wenwen555/ARIS-LVLM --skill experiment-plan-wenwen555

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill helps researchers transform a refined research proposal into a concrete, claim-driven plan that maps claims to supporting evidence and the exact run order needed to defend the method in a paper.

Core Features & Use Cases

  • Claim-driven design: extract primary/secondary/anti-claims and minimum convincing evidence.
  • Compact experimental storytelling: define experiment blocks (main anchor, novelty isolation, simplicity, frontier necessity, and diagnosis) with prioritization for must-run vs nice-to-have.
  • Execution planning and artifacts: specify datasets, splits, metrics, backbones, hyperparameters, seeds, budgets, and timelines; produce structured plan and run tracker.
  • Reproducible outputs: generate refine-logs/EXPERIMENT_PLAN.md and refine-logs/EXPERIMENT_TRACKER.md to guide implementation.

Quick Start

Turn the refined research proposal into a complete claim-driven experiment plan with blocks, run order, and budget estimates, and generate refine-logs/EXPERIMENT_PLAN.md and refine-logs/EXPERIMENT_TRACKER.md.

Frequently Asked Questions about experiment-plan

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

FAQPage Schema
How do I convert a research proposal into a claim-driven experiment plan?▼

A claim-driven experiment plan extracts primary, secondary, and anti-claims from your proposal and maps them to minimum convincing evidence with a specific run order.

How do I structure ablation studies for paper-ready validation in ML workflows?▼

Structure ablation studies by defining experiment blocks for novelty isolation, simplicity, and frontier necessity, then prioritize must-run evaluations versus nice-to-have diagnostics.

What is the best way to estimate compute budgets and timelines for LLM or VLM experiments?▼

Estimate compute budgets and timelines by specifying datasets, backbones, hyperparameters, and seeds within structured execution blocks to produce a reproducible run tracker.

Can I generate an evaluation protocol and run tracker for diffusion or RL experiments?▼

Yes, you can generate an evaluation protocol and run tracker by defining metrics, splits, and phase-based outputs that produce reproducible markdown artifacts for tracking runs.

How do I ensure reproducibility when planning an experiment run order?▼

Ensure reproducibility by generating structured markdown files that log datasets, hyperparameters, seeds, and explicit run orders to guide implementation and track execution.

Related Skills

Explore More Education & Research Skills→
jeremylongshorejeremylongshore
2

autoresearch

Generate hypotheses, design experiments, and analyze results for research topics.

Community
Advanced
CyapstayeCyapstaye
9

research-paper-writing

Coordinate ML research paper writing with experiment tracking and citation verification.

Community
Advanced
jaredcroxtonjaredcroxton

weights-and-biases

Log ML experiment metrics, configurations, artifacts, and lineage via W&B SDK.

Community
Advanced
dogekikidogekiki

experiment-plan

Transform research proposals into claim-driven experiment roadmaps with ablation matrices and baseline comparisons.

Community
Advanced