Claude skill
Experiment Pipeline
Experiment Pipeline is a Claude skill in the Mad Science plugin. Break an experiment doc into small vertical slices (stages, phases, experiments) with goals, metrics, status and dependencies, tracked in docs/experiments-pipeline.
What it does
The description in the skill's SKILL.md, which Claude reads to decide when to use it:
Break an experiment doc into small vertical slices (stages, phases, experiments) with goals, metrics, status and dependencies, tracked in docs/experiments-pipeline. Use when the experiment contract is settled and the user wants a run plan, wants to know which experiments can run in parallel, or wants to update experiment status.
The skill's instructions (about 219 words) cover:
- Experiments Workflow
- Experiment Stage <number>
How to use it
- Experiment Pipeline comes inside the Mad Science plugin, so you get it by installing that plugin, along with its 13 other skills. A plugin installs as one unit, with all its skills. The plugin's page has the install steps, and plugins are saved to your Claude account.
- This skill is set to run only when you call it, so Claude will not start it on its own.
- To pick it yourself in Claude chat, type
/or click + and choose experiment-pipeline. In Claude Code and Cowork, type:/mad-science:experiment-pipeline
Source
- Plugin
- Mad Science
- SKILL.md
- View on GitHub
- Repo stars
- 2
- Repo last pushed
- Nov 11, 2026
- Checked
- Nov 16, 2026
More skills in Mad Science
- HypothesysGrill the user relentlessly about a data science or ML hypothesis until it is clear, falsifiable and tied to goal metrics: premises, baseline and success criteria.
- Let It RipImplement or fix an experiment in a Jupyter notebook from its experiment doc and pipeline, expectation-first: run every cell, review the result with /exp-review, then commit.
- Literature ResearchInvestigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.
- Mad Science SetupSet up a repository for the mad-science data science skills: experiment tracker folder, domain glossary, agent instructions block and .env.example.
- Notify Gchat Human WaitSend a Google Chat card through the webhook set in .env (GCHAT_WEBHOOK_URL) when the agent is waiting for human input, with the open question and the project name.
- To ArticleUse when asked to generate, draft, or rewrite a scientific/technical article in Computer Science (conference paper, journal paper, or survey) from a topic/idea plus the repository's code…
- To DocTurn the current conversation into an experiment doc (hypothesis, premises, baseline, success metrics, experiment stories) and publish it to the project docs, with no new interview.
- What I DoOrientation map and canonical catalogue of the mad-science data science skills.
- Critic ReviewReview the project docs and experiments for gaps between what is documented, what was implemented, and the state of the art.
- Developing Data Science NotebooksDevelop production-grade Jupyter notebooks for data science research that follow state-of-the-art code practices (cell structure, modularization, reproducibility) and are designed to transition…
- Exp ReviewReview experiment code and Jupyter notebooks on two axes in parallel sub-agents: standards (does the code follow the repo's documented coding standards?) and quality (reproducibility, fixed seeds…
- Expectation Driven ScienceDevelopment guided by the scientific method and explicit expectations.
- Experiment GraphRender a read-only interactive graph of an experiment pipeline doc: dependencies, status and critical path at a glance.