agentsclimarketplace

Experiment design

Skill dongzhigang13305312738-art/paper-skills/experiment-design

📝 124 个 SCI/SSCI 论文写作 AI 技能合集：选题→文献综述→实验→图表→写作→润色→去AI痕迹→投稿，一个 paper-studio 总入口全流程调度。支持 Claude Code / WorkBuddy。

Install
npx -y skills add dongzhigang13305312738-art/paper-skills --skill experiment-design

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

  • 16 days oldThe repository was created 16 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Design experiment plans with progressive stages — initial implementation, baseline tuning, creative research, and ablation studies. Plan baselines, datasets, hyperparameter sweeps, and evaluation metrics. Use when planning experiments for a research paper.

SKILL.md

2.9 KB, 637 tokens by cl100k_base, as published. Nobody here has run it

Experiment Design

Design structured, progressive experiment plans for research papers.

Input

  • $0 — Research idea, plan, or method description

References

  • 4-stage progressive experiment prompts: ~/.claude/skills/experiment-design/references/stage-prompts.md

Scripts

Generate experiment design

python ~/.claude/skills/experiment-design/scripts/design_experiments.py --plan research_plan.json --output experiment_design.json
python ~/.claude/skills/experiment-design/scripts/design_experiments.py --method "contrastive learning" --task classification --format markdown

Generates baselines, ablation matrix, hyperparameter grid, metric selection. Stdlib-only.

4-Stage Progressive Framework (from AI-Scientist-v2)

Stage 1: Initial Implementation

  • Focus on getting a basic working implementation
  • Use a simple dataset
  • Aim for basic functional correctness
  • Completion: at least one working (non-buggy) implementation

Stage 2: Baseline Tuning

  • Tune hyperparameters (learning rate, epochs, batch size)
  • Do NOT change model architecture
  • Test on at least TWO datasets
  • Completion: stable training curves, improvement over Stage 1

Stage 3: Creative Research

  • Explore novel improvements and insights
  • Be creative and think outside the box
  • Test on at least THREE datasets
  • Completion: demonstrated novel improvement

Stage 4: Ablation Studies

  • Systematic component analysis
  • Each ablation tests a different aspect
  • Use same datasets as Stage 3
  • Completion: all planned ablations done

Output Format

{
  "stages": [
    {
      "name": "initial_implementation",
      "goals": ["Basic working baseline", "Simple dataset"],
      "max_iterations": 5,
      "completion_criteria": "Working implementation with non-zero accuracy"
    }
  ],
  "baselines": ["Method A", "Method B"],
  "datasets": ["Dataset1", "Dataset2", "Dataset3"],
  "metrics": ["accuracy", "F1", "inference_time"],
  "ablation_components": ["component_A", "component_B"],
  "hyperparameter_grid": {
    "lr": [1e-4, 1e-3, 1e-2],
    "batch_size": [32, 64, 128]
  },
  "num_seeds": 3
}

Rules

  • Always start simple (Stage 1) before complex experiments
  • Each stage builds on the best result from the previous stage
  • Multi-seed evaluation for statistical significance
  • Document every experiment run in notes.txt
  • Generate figures for training curves and comparisons

Related Skills

Gives 0 of the 12 instructions most plan spec skills give in 637 tokens

Counted across 1,100 of the 1,860 authors here whose files we hold, read 2026-08-06

  • ask one question at a timein 46 of 1100, across 38 files
  • Break plans into vertical slicesin 28 of 1100, across 10 files
  • Publish issues in dependency orderin 27 of 1100, across 9 files
  • Iterate until user approves the breakdownin 24 of 1100, across 6 files
  • Explore the repository to understand the codebase statein 24 of 1100, across 7 files
  • Use domain glossary vocabularyin 23 of 1100, across 5 files
  • Apply correct triage labels to published issuesin 23 of 1100, across 5 files
  • Write failing tests before implementation codein 23 of 1100, across 18 files
  • Prefer AFK slices over HITLin 22 of 1100, across 7 files
  • ask clarifying questions until requirements are concretein 21 of 1100, across 13 files
  • Respect existing architecture decision recordsin 20 of 1100, across 5 files
  • write a specification before writing any codein 20 of 1100, across 12 files

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.