Help us improve
Share bugs, ideas, or general feedback.
From lockedin
Draft an interview answer from the LockedIn vault, in English or Korean. Uses the same two-turn writer/reviewer pattern as the resume and cover letter renderers. The user asks an interview question (behavioural, technical, or background); the writer turn pulls evidence from the vault and drafts a STAR-shaped answer; the reviewer turn checks it against a small rubric (clarity, evidence density, persona fit, conciseness, tone) before the final answer is shown. Use when the user says any of <!-- ko-example -->"interview answer", "면접 답변", "STAR 답변", "behavioral question", "tell me about a time…"<!-- /ko-example -->, or names a question and asks for an answer drawn from their experience. Output: a single answer in markdown, with cited entities resolved to natural language, plus a JSON rubric score.
npx claudepluginhub daypunk/lockedin --plugin lockedinHow this skill is triggered — by the user, by Claude, or both
Slash command
/lockedin:lockedin-render-interviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Status: **v1.1 (skeleton)**. Skill scaffold ships with prompts and a
Generates customized interview questions from job descriptions and tailored resumes, categorizing by likelihood, gaps, and behavioral competencies, with practice schedules.
Generates structured interview plans with competency-based questions, scorecards, panel assignments, and debrief templates for consistent candidate evaluation.
Render a Korean 자기소개서 from the lockedin ontology, in 두괄식 + STAR/PAR structure, with banned-phrase filtering and self-evaluation against a 5-dimension rubric. Two-turn writer/reviewer pattern emits a JSON score so the user knows if the draft is ready to submit. Use when the user says: "자소서", "자기소개서", "render jaso", "회사 X 자소서 N번 문항", "지원동기 써줘", "성장과정 써줘", "입사 후 포부", or names a Korean company plus a 자소서 question. Input: company name, question id or text, optional 직무. Output: a Korean cover letter quoting concrete ontology slugs plus a JSON rubric score.
Share bugs, ideas, or general feedback.
Status: v1.1 (skeleton). Skill scaffold ships with prompts and a minimal rubric. Cross-source calibration of the rubric and a fixture set are v1.2 targets. The skill is functional today; quality will tighten with calibration.
lockedin-render-resume-en.lockedin-render-jaso./lockedin init or by ingesting a resume.Writer turn produces the draft. Reviewer turn re-loads RUBRIC.md
fresh in a separate Claude turn and emits a JSON score. Same as the
other renderers; the split is load-bearing.
A single markdown answer, no headers. STAR (Situation / Task /
Action / Result) by default; PAR (Problem / Action / Result) when
the question is incident-shaped. One experience per paragraph with
explicit transitions, mirroring the policy in
lockedin-render-resume-en and lockedin-render-jaso.
The answer pulls evidence from the vault using slug citation
([[type/slug]]); the slugs are resolved to natural language by
lockedin/render/resolve_slugs.py before the artifact is shown to
the user.
SKILL.md
prompt-writer.md writer-turn instruction
prompt-reviewer.md reviewer-turn instruction (separate Claude turn)
RUBRIC.md 5-dimension scoring contract (calibration v1.2)
The rubric and prompts here are v1.1 foundational. Cross-source calibration (interview-coaching guides, hiring-manager interviews, behavioural interview research) is the v1.2 target. Until then the LLM reviewer turn is self-consistent against the rubric, but the rubric itself has not been validated against an external corpus the way the jaso and resume-en rubrics have.