agentleFS
s-choungs-choung/Research-Skills/skills/meetingnote-paperwork/SKILL.md

meetingnote-paperwork

Skill36 starsChanged 6 months agoMITView on GitHub

Generate Korean research project meeting notes (회의록) in a fixed paperwork template. Use when the user asks for 회의록, meeting note paperwork, 과제 회의록 써줘, 회의록 부탁, or types /meetingnote-paperwork. Takes a 과제명 as input (asks once if missing) and drafts content in a computational chemistry / materials design voice (screening, DFT, descriptor, ML, benchmark, reaction path).

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Look at the user's message for a 과제명.

    line 16
  2. Very specific:

    Use this template verbatim for each note (preserve the X/X, XX:XX, XX,000원, XX동 XXX호 placeholders.

    line 30
  3. Very specific:

    If generating multiple notes, prefix each with 1), 2), ...

    line 46

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Meeting Note Paperwork Skill

Drafts Korean meeting notes (회의록) in the fixed paperwork template the user uses for project reporting. Content is grounded in computational chemistry / materials design themes: screening, DFT, descriptor analysis, ML model comparison, benchmarking, reaction path analysis.

Invocation flow

Step 1. Get the 과제명

Look at the user's message for a 과제명.

  • 과제명이 있으면 그대로 사용. 키워드에서 과제 주제를 추론해서 내용을 작성.
  • 없으면 한 번만 물어본다. Example: "어떤 과제 회의록이에요? 과제명 주세요." 유저는 본인 과제명을 알고 있으니 리스트를 펼치지 말 것.

Step 2. Figure out how many notes

Default: one note.

The user may say "회의록 2개", "1) ... 2) ...", or paste two placeholder blocks. In that case generate exactly that many, numbered 1), 2), ...

Step 3. Draft in the fixed template

Use this template verbatim for each note (preserve the X/X, XX:XX, XX,000원, XX동 XXX호 placeholders; those are filled in later by hand):

X/X XX:XX XX,000원
회의참석자 (성명/직급/소속) :
회의 시간/장소 : XX:XX ~ XX:XX / XX동 XXX호
회의 목적/내용 :
<one-line overall purpose tied to the 과제>

- <bullet 1>
- <bullet 2>
- <bullet 3>
(- <bullet 4, optional>)

If generating multiple notes, prefix each with 1), 2), ... on its own line before the X/X ... line.

Step 4. Content rules (computational chemistry voice)

Content should read like the user's group doing calculation-side work for the project. Safe, recurring motifs:

  • 후보 소재/조성 스크리닝 기준 논의 / 재정의
  • DFT 흡착 에너지 / 반응 경로 / 활성화 에너지 분석
  • Descriptor 기반 분석 (d-band center, work function, E(O*), p-d coupling, charge gradient 등)
  • ML 모델 (RF / XGBoost / GNN) 성능 비교, uncertainty-aware ranking
  • Microkinetic / AIMD 모델링 결과 해석
  • 실험 그룹과의 협업 조성/물질 선정 및 전달
  • 벤치마크: PBE vs meta-GGA, 계산 정확도/속도 비교, 슬랩 모델 축소 전략
  • 파이프라인 자동화 (VASP-ASE 연동 등) 현황 공유

Each bullet should read like a real discussion outcome, not a todo. Examples: "X 논의", "Y 결과 공유", "Z 기준 재조정", "N종 선정 및 전달안 확정". 2 to 4 bullets per note is normal.

Tie the content to the 과제. 과제명의 키워드(예: N2O 저감, MLCC 유전체, 암모니아 SOFC, 수전해, 탄산광물화, LOHC, BTX 분리, de novo 효소 등)에서 주제를 추론하고, 해당 주제에 맞는 계산 방법론과 소재군을 bullet에 반영.

Step 5. Output

Output only the meeting notes. No preamble, no trailing explanation. Plain text (not wrapped in a code block). Keep everything in Korean. Do not invent participant names or real times (those stay as XX:XX placeholders).

Tonal anchors

Three reference example sets from when the skill was created: (a) spinel oxide / microkinetic, (b) BCC/FCC/HCP 초기 구조 + VASP-ASE 자동화, (c) descriptor 최적화 + ML uncertainty ranking. Use them as tonal anchors for the bullet voice, not as templates to reproduce literally.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.