Skip to content
Automation
Skill

/check-rms-participants

Check a privacy-minimized, user-provided Yonsei RMS participant snapshot for project-period bounds, duplicate assignments, missing allocation data, and overlapping allocation above 100 percent. Use when a researcher wants an offline participant consistency review without

From plugin
yonsei-skills
952 skills1 MCP
Install
$ npx -y skills add mrcha033/yonsei-skills --skill check-rms-participants --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/check-rms-participants

Context preview

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

Check a privacy-minimized, user-provided Yonsei RMS participant snapshot for project-period bounds, duplicate assignments, missing allocation data, and overlapping allocation above 100 percent. Use when a researcher wants an offline participant consistency review without

SKILL.md

check-rms-participants.SKILL.md
name: check-rms-participants
description: Check a privacy-minimized, user-provided Yonsei RMS participant snapshot for project-period bounds, duplicate assignments, missing allocation data, and overlapping allocation above 100 percent. Use when a researcher wants an offline participant consistency review without querying or changing RMS.

Check RMS Participants

Check declared participant periods and allocations within one supplied project.

Run

Provide `captured_at`, `project_code`, `project_period`, and `participants`:

python3 "$SKILL_DIR/scripts/check_rms_participants.py" --input rms-participants.json

`project_period` and every participant assignment use ISO `start_date` and `end_date`. Each assignment requires a locally chosen, pseudonymous `participant_key` and `role`; `status` and `allocation_percent` are optional. Do not include names, contact details, student or employee IDs, government identifiers, or financial identifiers.

The checker reports assignments outside the project period, exact duplicate assignments, and overlapping supplied allocations above 100 percent. Missing allocation values remain in `unknowns`; they are never guessed.

Boundaries

  • Process only user-supplied JSON or Excel-transcribed data.
  • Treat role and status labels as opaque snapshot values; do not infer RMS policy.
  • Reject credentials and direct identifiers rather than echoing them.
  • Do not invite, remove, approve, save, or submit a participant change.

Official manual context: <https://research.yonsei.ac.kr/research/data_manual.do?articleNo=114666&mode=view>

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.