Skip to main content
skill CX Codex

paper-reading-experiment-design — Claude Code skill for experiment design

The paper-reading-experiment-design skill turns a research method’s claims into an experiment plan, covering evidence, metrics, baselines, and checks. Use it once the method has a clear thesis and target.

no license ★ 240 updated 2026-09-18

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add franklee16/academic-research-skills --skill paper-reading-experiment-design -a claude-code
Open on GitHub

What paper-reading-experiment-design does

The skill helps plan experiments around a method’s central claims. It links claims to observable evidence and measurement protocols, then guides choices about tasks, datasets, baselines, and metrics. When the thesis, target failure, or intervention point is still unsettled, it routes the work back to method definition.

The workflow creates an experiment folder under workspace/experiment-designs/ and builds a set of planning artifacts: a claim-evidence map, experiment design, baseline matrix, metric map, and ablation and control plan. Decisions are handled in small steps, with user confirmation before dependent choices proceed. A fully automatic run produces a provisional sketch, not a final plan.

Install it in Claude Code with npx skills add franklee16/academic-research-skills --skill 07-experiment-design -a claude-code. An uncommitted method keeps the resulting design provisional, so it is not ready to present as a finalized experiment plan.

What it helps with

  • connect a method’s claims to observable evidence
  • choose tasks, datasets, and baselines for an experiment
  • map claims to metrics and measurement protocols
  • plan ablations, confound checks, and stress tests
  • prepare a study plan that addresses likely reviewer objections

Example prompts for the agent

  • Design experiments for my committed method, and show me the source decision first.
  • Map the method’s main claims to metrics, measurement protocols, and validity risks.
  • Draft a provisional experiment sketch and flag decisions that still need review.

How to install paper-reading-experiment-design

1Skills CLI (Vercel)

npx skills add franklee16/academic-research-skills --skill paper-reading-experiment-design -a claude-code

2Manually: put the files in place

~/.claude/skills/07-experiment-design/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/07-experiment-design/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about paper-reading-experiment-design

How do I install paper-reading-experiment-design in Claude Code?

Run npx skills add franklee16/academic-research-skills --skill 07-experiment-design -a claude-code. The skill file is at ~/.claude/skills/07-experiment-design/SKILL.md.

What does paper-reading-experiment-design do?

It guides experiment planning for a research method, including evidence routes, tasks, datasets, baselines, metrics, and ablations. It also helps connect each key claim to a measurement protocol.

Does the skill require a committed method?

A committed method design is the preferred starting point. If the method’s thesis or target intervention is unsettled, the skill recommends returning to method definition; a provisional source leads to a provisional plan.

Similar skills

All skills for Science and research →

From the same set98

The whole set →
18-writeup 18-writeup drafts academic research papers in LaTeX across 12 focused passes, grounding every claim in workspace evidence without guessing. GP ChatGPT ★ 240repo stars thesis-idea This skill turns a rough economics thesis idea into a screened research question, design path, and dissertation outline. CX Codex +1 ★ 240repo stars journal-adapt journal-adapt — a dynamic writing skill generator that analyzes target-journal style from a corpus of published papers, then helps you revise your manuscript to match its conventions. CX Codex +1 ★ 240repo stars paper-evidence-distiller paper-evidence-distiller extracts structured evidence cards from academic papers in PDF or Markdown format. Links every empirical claim directly to its source section or table. CX Codex +1 ★ 240repo stars nature-paper2ppt nature-paper2ppt turns a research paper into a finished .pptx file: works out what the authors argue, keeps the figures the story needs, writes slide text and speaker notes. CX Codex +1 ★ 240repo stars academic-manuscript-review academic-manuscript-review runs a pre-submission review of a scholarly manuscript: flags weak theory, thin evidence and prose trouble, then returns a long candid diagnosis instead of a polite summary. CX Codex +1 ★ 240repo stars proof-readability proof-readability edits a math proof that already passed verification so a reader can follow it in one go: reordered steps, added lead-ins, fixed references. The claims stay as they are. CX Codex +1 ★ 240repo stars management-science-writing The management-science-writing skill guides management science and operations research papers from topic and journal choice through modeling, algorithms, experiments, and managerial conclusions. CX Codex +1 ★ 240repo stars

Project sponsors

Companies that keep this analytics open