badguyjudo/claude-plugins (build-personas)

Use after the study modules exist (modules/*.md) and the candidate is ready to practice against realistic interviewers. Derives the interviewer panel from the target role and seniority in PREP_PLAN.md — the archetypes change with the role and level, so it invents the right cast each time rather than reusing a fixed one — and writes one persona file per interviewer, each with a question bank and answer key built directly from the finished modules so practice stays consistent with what the candidate studied. It also writes the shared mock-interview protocol into the persona pack and materializes the chosen scoring rubric into the workspace. Optional modeling of a specific, real interviewer is supported only under strict safety rules — public professional information, practice-not-prediction framing, archetype by default. Produces personas/*.md, personas/_how-to-run-a-mock.md, and the rubric. Works for any role, any field, and any level. Run it after build-study-modules and before running mock interviews. Triggers on "build interviewer personas," "make my mock panel," "set up practice interviewers," or "create the interview rubric."

Claude Skills are markdown + scripts loaded into Claude Code; scanned with the same pipeline.

Source:

github.com/badguyjudo/claude-plugins

Provenance:

Found by crawling (provenance, not a security rating)

We found this by crawling public sources and nobody has attested to it. That is how most of the registry gets here, and it is not a mark against the artifact — it only means no authenticated act of publication is on record. An artifact can be the vendor's own and still appear here.

3 critical findings reported by cisco-skill-scanner. The composite score alone does not reflect this — read the per-scanner reports below.