Skip to content
Automation
Skill

/draft-yonsei-attendance-correction

Create an unsent Korean attendance-correction draft and evidence checklist from a user-confirmed discrepancy found on the authorized live attendance page; use a screenshot, pasted record, export, or JSON only when the live page is unavailable or intentionally supplied. Use when

From plugin
yonsei-skills
952 skills1 MCP
Install
$ npx -y skills add mrcha033/yonsei-skills --skill draft-yonsei-attendance-correction --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/draft-yonsei-attendance-correction

Context preview

The summary Claude sees to decide when to auto-load this skill.

Create an unsent Korean attendance-correction draft and evidence checklist from a user-confirmed discrepancy found on the authorized live attendance page; use a screenshot, pasted record, export, or JSON only when the live page is unavailable or intentionally supplied. Use when

SKILL.md

draft-yonsei-attendance-correction.SKILL.md
name: draft-yonsei-attendance-correction
description: Create an unsent Korean attendance-correction draft and evidence checklist from a user-confirmed discrepancy found on the authorized live attendance page; use a screenshot, pasted record, export, or JSON only when the live page is unavailable or intentionally supplied. Use when the user wants a reviewable request draft while official submission, status changes, attendance check-in, and external communication remain disabled.

Draft Yonsei Attendance Correction

Create one deterministic, unsent correction draft.

Prepare the input

Accept the disputed record and evidence in ordinary language or as an attached screen. Convert only the confirmed fields to a private temporary JSON file. Do not ask the user to write JSON, and do not infer a recipient or requested status that the user did not state.

Run

python3 "$SKILL_DIR/scripts/draft_correction.py" --input correction.json

Provide `captured_at` and a `correction` object containing course code, title, class date, recorded status, requested status, reason, and an `evidence` array. `recipient` is optional and is never inferred.

Review the structured fields, message text, evidence checklist, and `ready_for_user_review`. The output always states `draft_only: true` and `submitted: false`.

Boundaries

  • Never accept or execute `submit`, `send`, `apply_change`, or automatic-action flags.
  • Never enter an attendance code, attest presence, use location or beacon data, or perform check-in.
  • Process only user-supplied attachments, statements, or JSON and reject credential/session fields.
  • Do not claim a correction was accepted; the user must review and submit through the official path.
Read more
Ships withyonsei-skills

연세대학교 생활에서 자주 반복되는 확인·정리 작업을 자연어로 처리하는 비공식 오픈소스 플러그인 모음입니다. 연세대학교 공식 서비스가 아닙니다. 학교 계정 권한을 늘리거나 수강신청·출석·예약 제한을 우회하지 않습니다.

Get the whole plugin

Other skills on yonsei-skills.