Overview
experiment-plan is an open-source data skill for Claude Code and compatible agents, published by wanshuiyin. Its author describes it as: “Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `research-refine`, or when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol…”. The project has 15k stars on GitHub and is available under the MIT license. Add it to your setup with `git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ~/.claude/skills/experiment-plan`.
What experiment-plan does
Refine and concretize: **$ARGUMENTS**
What’s inside
The SKILL.md for experiment-plan is organised into these sections:
- Overview
- Constants
- Workflow
- Phase 0: Load the Proposal Context
- Phase 1: Freeze the Paper Claims
- Phase 2: Build the Experimental Storyline
- Phase 3: Specify Each Experiment Block
- Phase 4: Turn the Plan Into an Execution Order
- Phase 5: Write the Outputs
- Output Protocols
- Key Rules
- Composing with Other Skills
Installation
Add experiment-plan to your agent with:
git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ~/.claude/skills/experiment-planReview a skill’s source before installing it — skills can instruct your agent to run commands. This command comes from the skill’s public repository, which is the source of truth for setup steps. New to skills? Read how to install Claude Code skills.
Supported agents
- Claude Code — declared in the repository topics
- Codex — declared in the repository topics
License
experiment-plan is published under the MIT license.
Strengths
- Clear MIT license — safe to read and adapt within its terms
- Ships in wanshuiyin/Auto-claude-code-research-in-sleep, an established project with 14,858 GitHub stars
- Works with Claude Code, Codex
- Actively maintained — repository updated in the last 90 days
Author
Topics
Frequently asked questions
- What does experiment-plan do?
- Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `research-refine`, or when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, or paper-ready validation that supports the core problem, novelty, simplicity, and any LLM / VLM / Diffusion / RL-based contribution.
- How do I install experiment-plan?
- Run git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ~/.claude/skills/experiment-plan in your agent, then reload your skills. Review the source at https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep before installing.
- Is experiment-plan free to use?
- Yes. experiment-plan is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Which agents does experiment-plan work with?
- experiment-plan lists Claude Code and Codex — named in its SKILL.md, its plugin marketplace or its repository topics. Skills use the portable SKILL.md format, so other agents that read that format may load it too.
- Where does experiment-plan come from?
- experiment-plan ships inside wanshuiyin/Auto-claude-code-research-in-sleep, a repository that contains 41 catalogued skills in total. The repository's 14,858 GitHub stars apply to that whole collection, not to this skill on its own.