Use when cutting, shipping, releasing, or publishing a new LaNorme version (a "0.x.y" bump, a tag, a PyPI release). Runs every release gate (unit tests, the dogfood, generated docs in sync), records a eval audit (precision/recall/F1 per scored rule plus end-to-end performance, stamped with the version and hardware) to evals/results/, bumps the version, tags, and creates the GitHub Release that auto-publishes to PyPI and deploys the versioned docs.
Decide whether a change is ready to merge, and review it to that bar. Use when reviewing a pull request or deciding whether to merge a branch, to check that the change does what it claims, is DRY, clean, idiomatic and maintainable, has a solid test base that would actually catch a regression, holds up on performance, and ships with the right docs.
Audit the LaNorme docs for accuracy, currency, no-archeology, clarity, and coverage, then fix what it finds. Use before a release or after changing the CLI, the rules, or any Markdown doc, or when asked whether the docs are solid, current, or up to date. It runs the docs-audit workflow, which checks every documented flag, rule code, config key, and output example against the real tool, flags changelog-style narration outside CHANGELOG and any bluff, and lists undocumented surface.
metadata is a scalar, not a map.
Name does not match the parent directory.
Links to a file that does not exist.
A valid skill whose description is a folded block scalar spanning multiple lines, to make sure the parser does not call it empty.
A valid skill that links to a bundled reference file.