Help us improve
Share bugs, ideas, or general feedback.
From lockedin
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.
npx claudepluginhub daypunk/lockedin --plugin lockedinHow this skill is triggered — by the user, by Claude, or both
Slash command
/lockedin:lockedin-render-jasoThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Research-based calibration. RUBRIC.md ships with five dimensions and
Builds, critiques, rewrites, and quality-controls resumes to 8.5+ scores using hallucination-free expert panels. Tailors for roles, handles from-scratch creation, and exports to .docx.
Creates detailed scoring rubric from job posting by extracting requirements into standardized evaluation criteria, without performing assessment.
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.
Share bugs, ideas, or general feedback.
Research-based calibration. RUBRIC.md ships with five dimensions and
score bands. prompt-writer.md, prompt-reviewer.md, and
banned_phrases.json (28 cross-source-confirmed entries) all ship.
Named human domain reviewer engagement is in progress. See
reviewers.md for the engagement format.
render-resume-en./lockedin init or lockedin init --fixture FILE.banned_phrases.json.[[role/lead-pm-fintech-2024]]). Vague
generalities cost the 구체성 dimension.Run as two separate Claude turns:
RUBRIC.md
fresh. Score on 두괄식 / 구조화 / 구체성 / 표현 / 적합성 (0–5
each). Emit JSON. If any dimension < 4 OR revisions_required: true,
return to the writer turn once with the review notes.Same-turn self-evaluation inflates scores by ~1 point. Do not skip the separation.
SKILL.md (this file)
research-notes.md citations with URL + ISO date + 2-sentence gloss
RUBRIC.md 5-dimension scoring contract + score bands
banned_phrases.json 28 cross-source-confirmed regex entries
prompt-writer.md writer-turn prompt
prompt-reviewer.md reviewer-turn prompt (re-loaded fresh)
reviewers.md engagement format; v1.1 named reviewer placeholder