what-i-dolisted
Install: claude install-skill samuhs/mad-science
# What I Do
This skill is the orientation map for the experiment-driven workflow — and the **canonical catalog** of every skill in this repo. It explains how the data-science commands fit together, tells you which one to invoke next, and lists every skill with its role. It does not implement anything itself — it routes.
> **Catalog governance:** every skill in this repo must be registered here, below,
> before it is considered final. If a skill changes the experiment flow, the
> *Main Flow* and/or *Flow Checks* sections must be updated to reflect it. The
> `README.md` of the repo mirrors this file; this file wins on divergence.
## Main Flow: Hypothesis → Notebook Experiment
You have a hypothesis and want to test it. The flow has four steps, in order:
1. **`/hypothesys`** — Understand and sharpen the user's hypothesis through a short interview. This is the first step: it clarifies the hypothesis, the premises, and the goal metrics of the experiment before anything is built.
2. **`/to-doc`** — Write the experiment doc for the idea to be developed. This fixes and consolidates the ideas, giving the next step a stable contract to implement against.
3. **`/experiment-pipeline`** — Transform the doc into a pipeline workflow, breaking it into small slices to run and tracking the experiment rounds.
4. **`/let-it-rip`** — Implement the hypothesis safely in a notebook.
- Follows the rules of `/expectation-driven-science` so the science code stays rigorous (expectation before tru