Documentation

Why research-kit — the failures in one research project each piece of the kit replaced
How to use — a research thread as you say it to the agent, and the commands underneath
Getting started — the records as written, a failed check, a card, the dashboard
Scope — what the kit assumes, what the agent does without asking, what it is not
Install — the routes, the supported agents, the optional tools, updating
What goes online, and what runs — the online commands, the hosts they call, the environment variables they read
Glossary — every word the skills use, one line each
The bindings files — flow.toml, library.toml and formal.toml as init writes them, every binding explained
The checks — every code flow check and library check can report, what the formal checks verify, the exit codes
Development — the layout, the tests, how a release is cut; the CHANGELOG beside the README

Each skill is documented by its own SKILL.md under plugins/, which is also what the agent reads.