Mine candidate domain concepts and their vocabulary from every naming source of a legacy system — database schema, UI labels, REST/URL paths, configuration, code identifiers, documentation. Produces a regenerable CONCEPTS.md (aliases, evidence, frequency, co-occurrence) and seeds a human-owned GLOSSARY.md with canonical terms, both in the analyzed project's migration/ folder. First step of a legacy-to-BCE migration; composes with bce and sbce. Invoke explicitly as /concept-extractor on the system to analyze. Not for mechanical 1:1 ports (use j2ee-migration) and not for carving business components — it only produces the vocabulary later steps consume.
$npx -y skills add adambien/airails --skill concept-extractorInstalls into the current project.
Run `npx skills use "https://github.com/adambien/airails" --skill "adambien/airails/concept-extractor"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/adambien/airails" that are relevant to the current task. Run `npx skills add "https://github.com/adambien/airails"` and select the relevant skills, then follow their instructions.