Skip to content
Automation
Skill

/summarize-rms-project

Normalize a user-provided Yonsei RMS JSON or Excel-transcribed project snapshot into a privacy-minimized summary of project identity, period, budget, participant counts, and supplied workflow state. Use when a researcher needs an offline project overview without querying or

Boost this skill
@mrcha033mrcha033@mrcha033
From plugin
yonsei-skills
952 skills1 MCP
Install
$ npx -y skills add mrcha033/yonsei-skills --skill summarize-rms-project --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/summarize-rms-project

Context preview

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

Normalize a user-provided Yonsei RMS JSON or Excel-transcribed project snapshot into a privacy-minimized summary of project identity, period, budget, participant counts, and supplied workflow state. Use when a researcher needs an offline project overview without querying or

SKILL.md

summarize-rms-project.SKILL.md
name: summarize-rms-project
description: Normalize a user-provided Yonsei RMS JSON or Excel-transcribed project snapshot into a privacy-minimized summary of project identity, period, budget, participant counts, and supplied workflow state. Use when a researcher needs an offline project overview without querying or changing RMS.

Summarize RMS Project

Summarize one supplied RMS project snapshot and expose internal contradictions.

Run

Provide `captured_at`, optional `source_format`, and a `project` object:

python3 "$SKILL_DIR/scripts/summarize_rms_project.py" --input rms-project.json

The declared `project` contract requires `project_code`, `title`, `status`, `period` (`start_date`, `end_date`), `budget` (`currency`, `total`, `executed`, optional `committed` and `remaining`), `workflow` (`stage`, optional `pending_action`), and `participants`. Each participant needs a pseudonymous `participant_key`, `role`, and optional `status`. Do not include names or institutional identifiers.

Amounts may be JSON numbers or decimal strings and are returned as decimal strings. Review `issues` and `complete`; the workflow values remain the snapshot's opaque labels, not interpreted live states.

Boundaries

  • Process only user-supplied JSON or Excel-transcribed data.
  • Reject credentials, government identifiers, bank accounts, and tax identifiers.
  • Do not query RMS, infer undocumented fields, or expose participant keys in output.
  • Do not save, approve, submit, or alter any project or workflow.

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

Read more
Read it on GitHub ↗
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
Stats
PythonBashLinuxGitHubAnthropic
+1 tag
OpenAI
9
Stars
0
Forks
Maintained
Maintenance
Python
Language
1mo ago
Last commit
1mo ago
Created

Repo: mrcha033/yonsei-skills

In this plugin
52 skills1 MCP
See everything inside

Other skills on yonsei-skills.

See all 52 skills in yonsei-skills