Receber por email
← Voltar para o catálogo

lockedin-render-jaso

Writes a Korean 자기소개서 from the user's experience. Two-turn writer/reviewer with a 5-dimension Korean rubric and banned-phrase filter. Activate when the user says "자소서", "자기소개서", "지원동기 써줘", "성장과정 써줘", "입사 후 포부", or names a Korean company plus a 자소서 question.

138estrelas
Atualizado há 5 meses

Ver no GitHub ↗ Licença: MIT

Como adicionar

/plugin marketplace add daypunk/LockedIn

O comando exato pode variar conforme o repositório. Confira o README no GitHub.

Para o autor da skill

Cole no README do seu repo

Mostra que sua skill está catalogada na Skillteca, gera backlink e tráfego rastreável.

[![Skillteca](https://www.skillteca.com.br/api/badge/lockedin-render-jaso/svg)](https://www.skillteca.com.br/skills/lockedin-render-jaso)

Skills relacionadas

Ver todas de Desenvolvimento →

Alerta por categoria

Receba novas skills de Desenvolvimento toda segunda

1 email curto, só com as skills novas de Desenvolvimento. 4 minutos de leitura, sem spam, cancela com 1 clique.

Você confirma o email no primeiro envio. Sem spam. Cancela com 1 clique.

Ler descrição completa

render-jaso

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.

Use this when

  • User names a Korean company and asks to write a 자소서.
  • User points at a 자소서 question (e.g., 지원동기 / 성장과정 / 성격의

장단점 / 입사 후 포부).

  • User asks to "polish my 자소서" against the rubric.

Do NOT use when

  • User wants an English resume → use render-resume-en.
  • The vault is empty (no ontology nodes to quote) → seed first via

/lockedin init or lockedin init --fixture FILE.

Required design constraints (locked)

  1. 두괄식 — conclusion / 핵심 / 차별점 in the first paragraph; the

rest of the answer scaffolds the lead.

  1. 구조화된 문맥 — within Korean 4-question convention (지원동기 /

성장과정 / 성격의 장단점 / 입사 후 포부 etc.), use STAR or PAR per paragraph.

  1. 두루뭉술한 표현 제거 — banned-phrase regex check runs before

the reviewer rubric pass. See banned_phrases.json.

  1. 초개인화된 경험 기반 — every claim quotes a concrete ontology

node by slug (e.g., [[role/lead-pm-fintech-2024]]). Vague generalities cost the 구체성 dimension.

  1. 회사·직무 fit — query the ontology for nodes with edges to the

target company / 직무 / industry; surface the top-3 most relevant before drafting.

Two-turn writer/reviewer pattern

Run as two separate Claude turns:

  1. Writer turn — produce the 자소서 draft. Quote ontology slugs.

Apply banned-phrase filter to the draft.

  1. Reviewer turn — clear the writer context. Re-load 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.

Final checklist

  • Banned-phrase regex pass ran (and was clean) before rubric.
  • Reviewer turn was a separate Claude context with fresh RUBRIC.md load.
  • Output JSON has all 5 dimensions ≥ 4 (or one revise cycle ran).
  • Concrete ontology slugs are quoted in the rendered text.

Files in this directory

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)
Compartilhar X LinkedIn