madbench:madbench-evals

Authors, runs and debugs madbench benches natively — bench YAML, checks, metrics with module/, red-state testdata, the two controls, exit codes;

Part of madbench.

5 reference documents, about 3,135 lines.

The skill itself does not contain them. It reads your question and names the one or two worth opening — which is the point, because loading everything below to answer one question would cost more than the answer is worth.

Start here

Document	Covers	Lines
checks-catalog.md	Check catalog	1140
debugging.md	Debugging madbench benches	349
glossary.md	madbench Glossary — the one table	126
harness-and-sandbox.md	Harness, sandbox and CLI	814
schema.md	Bench and Experiment file schema	706

Reading these

You do not open these yourself in normal use — /madbench:madbench-evals picks for you. Read them directly when you want the reference rather than the answer, or to check what the advice is actually based on.